DETAILED ACTION
This is a Final Office Action on the Merits in response to communications filed by applicant on February 13th, 2026. Claims 1-2, 4-16, and 18-22 are currently pending and examined below.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
The amendments to the Claims, filed on February 13th, 2026, have been entered. Claims 1-2, 4-10, 13-14, 16, and 18-20 are currently amended and pending, claims 11-12 and 15 are original, unamended, and pending, claims 3 and 17 have been canceled, and claims 21 and 22 are new and pending.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1, 7, and 21-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami").
Regarding claim 1, Kokido teaches an autonomous driving control apparatus, comprising (Kokido: Figure 1, Column 3 lines 35-45, “FIG. 1 is a block diagram depicting a driving assist apparatus to which the lane division line recognition apparatus, according to Embodiment 1 of this invention, is applied.”):
a sensor device including a first sensor and a second sensor different from the first sensor (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”. The cited passages clearly teach a first sensor and a second sensor different from the first sensor.);
wherein each of the first sensor and the second sensor is configured to capture an image of lane markings of a road on which a host vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”. The cited passages clearly shows that the first and second sensors are configured to capture images of the lane markings of the road.);
a memory storing at least one instruction (Kokido: Column 3 lines 46-52, “The frontward driving lane detection unit 3, the periphery driving lane detection unit 4, the base vehicle driving lane determination unit 5, the steering control unit 7, and the lane deviation determination unit 8 are implemented by a central processing unit (CPU), which executes arithmetic processing, and these blocks are stored in a storage unit (not illustrated) as software.”); and
a controller operatively connected with the sensor device and the memory (Kokido: Column 3 lines 46-52, Column 3 lines 53-57, Column 3 lines 58-63. The cited passages show that a CPU is configured to receive the image data from the two sensors and to execute the instructions stored in memory. One of ordinary skill in the art would recognize that the CPU is functioning as a controller and that it is connected to the sensors and memory.),
wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of the first sensor or the second sensor, or any combination thereof (Kokido: Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”. The cited passages clearly show that the system is configured to determine lane detection result based on the image captured by both sensors, i.e., one detection result for the forward sensor and one detection result for the peripheral sensor.);
wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”. The cited passages clearly shows that a lane detection result is determined for both the first and second sensors.);
Kokido does not teach generate at least one driving route, based on the at least one lane detection result; and
determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route
generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result;
generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof;
and control the host vehicle to travel based on the generated final driving route.
Kurakami, in the same field of endeavor, teaches generate at least one driving route, based on the at least one lane detection result (Kurakami: Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”); and
determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route (Kurakami: Figure 8, Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly show that the system is configured to select the at least one driving route as the final driving route.);
generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result (Kurakami: Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”, Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”. The cited passage clearly teach generating multiple paths for the vehicle, the second of which is based on the lane detection result and the third of which is based on the two previously predicted paths.);
generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof (Kurakami: Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 10 line 15-18, “A state where it is determined that there is no divergence is a state where an appropriate travel path can be maintained even if the subject vehicle 100A continues to travel along either one of the prediction paths.”. The cited passages clearly show that the reliability of each predicted path is used to select the final driving path. Furthermore, one of ordinary skill the divergence between the first and second predicted path is clearly a measure of the similarity of the two paths.);
and control the host vehicle to travel based on the generated final driving route (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to control the vehicle based on the driving route.).
Kokido teaches an autonomous driving control apparatus, comprising: a sensor device including a first sensor and a second sensor different from the first sensor; wherein each of the first sensor and the second sensor is configured to capture an image of lane markings of a road on which a host vehicle is traveling; a memory storing at least one instruction; and a controller operatively connected with the sensor device and the memory, wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of the first sensor or the second sensor, or any combination thereof. Kokido does not teach generate at least one driving route, based on the at least one lane detection result; and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route; generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result; generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof; and control the host vehicle to travel based on the generated final driving route. Kurakami teaches generate at least one driving route, based on the at least one lane detection result; and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route; generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result; generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof; and control the host vehicle to travel based on the generated final driving route. A person of ordinary skill in the art would have had the technological capabilities required to have combine the apparatus taught in Kokido with generate at least one driving route, based on the at least one lane detection result; and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route; generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result; generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof; and control the host vehicle to travel based on the generated final driving route taught in Kurakami, Furthermore, the apparatus taught in Kokido is already configured to detect a lane in which the vehicle is travelling using a second sensor, and modifying the apparatus to generate and determine a driving route based on the lane detection would only require the addition of the trajectory planning using the methods taught in Kurakami. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous driving control apparatus, comprising: generate at least one driving route, based on the at least one lane detection result; and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route; generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result; generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof; and control the host vehicle to travel based on the generated final driving route.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine autonomous driving control apparatus taught in Kokido with generate at least one driving route, based on the at least one lane detection result; and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route; generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result; generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof; and control the host vehicle to travel based on the generated final driving route taught in Kurakami with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Regarding claim 7, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in an opposite direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the right lane is detected in the periphery driving lane detection or vice versa.):
determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.); and
generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route based on a driving route corresponding to reliability value with a higher value between the first reliability value and the second reliability value. (Kurakami: Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly show that the system is configured to select the prediction path as the final driving path based on which prediction path has the higher reliability value.).
Regarding claim 21, Kokido in view of Kurakami teaches wherein: the first sensor is positioned at a front portion of the host vehicle and configured to capture, from a first image capturing direction, a first image of lane markings of a road on which the host vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”),
the second sensor is positioned at a side portion of the host vehicle and configured to capture, from a second image capturing direction different from the first image capturing direction, a second image of lane markings of the road on which the host vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”),
and the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to determine, based on a comparison of the first driving route and the second driving route, the final driving route for autonomous driving of the host vehicle (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to determine the final driving route based on a comparison of the two driving routes.).
Regarding claim 22, Kokido teaches a vehicle, comprising (Kokido: Figure 1, Column 3 lines 35-45, “FIG. 1 is a block diagram depicting a driving assist apparatus to which the lane division line recognition apparatus, according to Embodiment 1 of this invention, is applied. In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5, a vehicle state notification unit 6, a steering control unit 7, a lane deviation determination unit 8, a steering wheel control unit 9, and an audio output unit 10.”):
a first sensor positioned at a front portion of the vehicle and configured to capture, from a first image capturing direction, a first image of lane markings of a road on which the vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”);
a second sensor positioned at a side portion of the vehicle and configured to capture, from a second image capturing direction different from the first image capturing direction, a second image of lane markings of the road on which the vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”);
a memory storing at least one instruction (Kokido: Column 3 lines 46-52, “The frontward driving lane detection unit 3, the periphery driving lane detection unit 4, the base vehicle driving lane determination unit 5, the steering control unit 7, and the lane deviation determination unit 8 are implemented by a central processing unit (CPU), which executes arithmetic processing, and these blocks are stored in a storage unit (not illustrated) as software.”); and
a processor, wherein the at least one instruction is configured to, when executed by the processor, cause the vehicle to (Kokido: Column 3 lines 46-52, “The frontward driving lane detection unit 3, the periphery driving lane detection unit 4, the base vehicle driving lane determination unit 5, the steering control unit 7, and the lane deviation determination unit 8 are implemented by a central processing unit (CPU), which executes arithmetic processing, and these blocks are stored in a storage unit (not illustrated) as software.”):
generate, based on the first image of lane markings, a first lane detection result regarding a lane in which the vehicle is traveling (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”);
generate, based on the second image of lane markings, a second lane detection result regarding the lane in which the vehicle is traveling (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”);
Kokido does not teach generate, based on the first lane detection result, a first driving route;
generate, based on the second lane detection result, a second driving route;
determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and
control the vehicle to travel based on the final driving route.
Kurakami teaches generate, based on the first lane detection result, a first driving route (Kurakami: Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”, Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”);
generate, based on the second lane detection result, a second driving route (Kurakami: Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”, Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”);
determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to determine the final driving route based on a comparison of the two driving routes.); and
control the vehicle to travel based on the final driving route (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to control the vehicle based on the driving route.).
Kokido teaches a vehicle, comprising: a first sensor positioned at a front portion of the vehicle and configured to capture, from a first image capturing direction, a first image of lane markings of a road on which the vehicle is traveling; a second sensor positioned at a side portion of the vehicle and configured to capture, from a second image capturing direction different from the first image capturing direction, a second image of lane markings of the road on which the vehicle is traveling; a memory storing at least one instruction; and a processor, wherein the at least one instruction is configured to, when executed by the processor, cause the vehicle to: generate, based on the first image of lane markings, a first lane detection result regarding a lane in which the vehicle is traveling; generate, based on the second image of lane markings, a second lane detection result regarding the lane in which the vehicle is traveling;. Kokido does not teach generate, based on the first lane detection result, a first driving route; generate, based on the second lane detection result, a second driving route; determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and control the vehicle to travel based on the final driving route. Kurakami teaches generate, based on the first lane detection result, a first driving route; generate, based on the second lane detection result, a second driving route; determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and control the vehicle to travel based on the final driving route. A person of ordinary skill in the art would have had the technological capabilities required to have combine the vehicle taught in Kokido with generate, based on the first lane detection result, a first driving route; generate, based on the second lane detection result, a second driving route; determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and control the vehicle to travel based on the final driving route taught in Kurakami, Furthermore, the vehicle taught in Kokido is already configured to detect a lane in which the vehicle is travelling using a second sensor, and modifying the apparatus to generate and determine a driving route based on the lane detection would only require the addition of the trajectory planning using the methods taught in Kurakami. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of a vehicle comprising: generate, based on the first lane detection result, a first driving route; generate, based on the second lane detection result, a second driving route; determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and control the vehicle to travel based on the final driving route.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the vehicle taught in Kokido with generate, based on the first lane detection result, a first driving route; generate, based on the second lane detection result, a second driving route; determine, based on a comparison of the first driving route and the second driving route, a final driving route for autonomous driving of the vehicle; and control the vehicle to travel based on the final driving route taught in Kurakami with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 2, 13, 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 2021/0009161 A1 ("Kim").
Regarding claim 2, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine, using the first sensor, the first lane detection result about an area including a forward direction of the host vehicle and include at least one first camera (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”); and
determine, using the second sensor, the second lane detection result about an area including a sideward direction of the host vehicle, wherein the second sensor includes at least one second camera mounted on at least one area of a side mirror of the host vehicle (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”. The cited passages clearly show periphery camera can be installed on the side mirrors of the vehicle.).
Kokido in view of Kurakami does not teach wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine, using the first sensor, the first lane detection result about an area including a forward direction of the host vehicle, wherein the first sensor includes at least one first camera mounted on at least one area of a wind shield of the host vehicle.
Kim, in the same field of endeavor, teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine, using the first sensor, the first lane detection result about an area including a forward direction of the host vehicle, wherein the first sensor includes at least one first camera mounted on at least one area of a wind shield of the host vehicle (Kim: Figure 1 stereo camera 310a, ¶ 0122, “The camera 310 may be located on an appropriate portion outside the vehicle to acquire an external image of the vehicle. The camera 310 may be a mono camera, a stereo camera 310a (as depicted in FIGS. 1 and 2), an around view monitoring (AVM) camera 310b (as depicted in FIG. 2) or a 360-degree camera.”, ¶ 0123, “In some implementations, the camera 310 may be disposed adjacent to a front windshield within the vehicle to acquire a front image of the vehicle. Alternatively or in addition, the camera 310 may be disposed adjacent to a front bumper or a radiator grill.”. The cited figure and passages clearly show that the camera can be mounted on the windshield of the vehicle.).
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous driving control apparatus taught in Kokido in view of Kurakami with wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine, using the first sensor, the first lane detection result about an area including a forward direction of the host vehicle, wherein the first sensor includes at least one first camera mounted on at least one area of a wind shield of the host vehicle taught in Kim with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because it would have required a simple substitution of the location of the sensor for another. Simply changing the location would have been well within the technological capabilities of one of ordinary skill in the art. Additionally, simply moving the sensor would not change or introduce new functionality. No inventive effort would have been required.
Regarding claim 13, Kokido in view of Kurakami in further view of Kim teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine at least one piece of route information corresponding to the first driving route (Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane. The left deviation amount may be calculated by using positional information of the left edge l00EL of the subject vehicle 100A or by using information about the center position of the subject vehicle 100A in the vehicle width direction.”. The cited passage clearly teaches that at least one piece of route information corresponding to the first driving route. Such information includes the position of the vehicle in the lane width, the lane width, the curvature of the lane, and the speed, acceleration, and heading of the vehicle.);
determine a similarity value between the first driving route and the second driving route based on whether a difference between the at least one piece of route information is greater than a threshold (Kurakami: Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 14 lines 39-42, “Referring back to the flowchart in FIG. 8, the driving support controller 2 performs a branching process in step S102 in accordance with whether the divergence flag is in the ON mode.”, Column 14 lines 43-49, “If the divergence flag is in the OFF mode, it is not necessary to reselect the travel path, thus the travel-path selection process illustrated in FIG. 8 is ended. In this case, the control in the hands-off driving mode MD2 is continuously performed based on the image from the stereo camera 18 while, for example, the location of the subject vehicle 100A is acquired from the map locator 4.”); and
generate the final driving route based further on the similarity value (Kurakami: Figure 8 Column 14 line 39 – Column 15 line 12. The cited figures and passages describe the method by which the final driving path is determined. In the case that the similarity value (which is difference between the two paths) is greater than a threshold, the final path is further determined using the reliability value of each predicted path. In the case where the similarity value is below a below a threshold, the system is configured to use the first predicted path as the final path.).
Regarding claim 14, Kokido in view of Kurakami in further view of Kim teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine location information of a control target point, based on a driving vehicle speed of the host vehicle and an estimated driving time to the control target point (Kurakami: Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 16 line 65 – Column 17 line 3, “As illustrated in FIG. 15, the left deviation amount for the left edge l00EL of the subject vehicle l00A after a predetermined time period (e.g., after 2.5 seconds) corresponds to a distance between a center line CL of the left lane line WLL and the position of the left edge l00EL after the predetermined time period.”, Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”. The cited passages clearly teach that the divergence of the predicted paths is determined at a future location of the vehicle. This future location is determined based on the travel time and the velocity, acceleration, and heading of the vehicle. This location clearly functions as a control point as it is the location where divergence is checked for. Furthermore, one of ordinary skill in the art would recognize that when determining a location of a vehicle after a set amount of time (in this example 2.5 second), the velocity, acceleration, and heading of the vehicle would have to be used.); and
determine the similarity value between the first driving route and the second driving route, based on at least one of a first curvature of the first driving route, a first heading of the first driving route, a second curvature of the second driving route, or a second heading of the second driving route, or any combination thereof, the first heading, the second curvature, and the second heading being identified on the basis of the location information (Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane. The left deviation amount may be calculated by using positional information of the left edge l00EL of the subject vehicle 100A or by using information about the center position of the subject vehicle 100A in the vehicle width direction.”. The cited passage clearly teaches that the similarity (i.e. the divergence between the two paths) is can be based on a first curvature of the first driving route, a first heading of the first driving route, a second curvature of the second driving route, or a second heading of the second driving route. Furthermore, one of ordinary skill in the art would see that the heading and curvature would be based on the location information, as the divergence is calculated at a location that occurs 2.5 seconds in the future for the vehicle.).
Claim(s) 4 and 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of KR 20230073832 A ("Kim Sang").
Regarding claim 4, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.).
Kokido in view of Kurakami does not teach generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and
generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value.
Kim Sang, in the same field of endeavor, teaches generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”. The cited passage clearly teaches that the system is configured to select final driving path as the path with a reliability greater than a predetermined reliability threshold.); and
generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value (Kim Sang: Abstract, ¶ 0008, ¶ 0112. One of ordinary skill in the art would recognize that because the system is configured to select the path that has the highest reliability and is greater than a predetermined threshold, the system would select the second path as the driving route when the first reliability is less than the threshold and the second reliability is greater than the threshold.).
Kokido in view of Kurakami teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine the first reliability value of the first driving route and the second reliability value of the second driving route. Kokido in view of Kurakami also teaches setting the driving route based on whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami does not teach generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value. Kim Sang teaches generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami already teaches determining a reliability value for each path, comparing the reliability of each path to each other, and selecting the path based on this comparison, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and select the driving path based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with generate the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generate the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Regarding claim 16, Kokido teaches an autonomous driving control method, comprising (Kokido: Figure 1, Column 3 lines 35-45, “FIG. 1 is a block diagram depicting a driving assist apparatus to which the lane division line recognition apparatus, according to Embodiment 1 of this invention, is applied.”):
determining, by a controller, at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of a first sensor included in a sensor device or a second sensor included in the sensor device, or any combination thereof (Kokido: Column 3 lines 46-52, “The frontward driving lane detection unit 3, the periphery driving lane detection unit 4, the base vehicle driving lane determination unit 5, the steering control unit 7, and the lane deviation determination unit 8 are implemented by a central processing unit (CPU), which executes arithmetic processing, and these blocks are stored in a storage unit (not illustrated) as software.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”. The cited passages clearly show that the system is configured to determine lane detection result based on the image captured by both sensors, i.e., one detection result for the forward sensor and one detection result for the peripheral sensor.);
Kokido does not teach wherein the determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor;
generating, by the controller, at least one driving route, based on the at least one lane detection result;
determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route;
determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route
by generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value, or generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value;
and controlling, by the controller, the host vehicle to travel based on the generated final driving route.
Kurakami, in the same field of endeavor, teaches determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 5 lines 22-29, “The map locator 4 includes, for example, a global navigation satellite system (GNSS) receiver 21 and a map database (DB) 22 in which high-resolution map data is stored, and is capable of identifying a high-precision current location of the vehicle 100 serving as the subject vehicle. In detail, in addition to being capable of identifying the road on which the vehicle 100 is traveling, the map locator 4 is also capable of identifying the travel lane.”, Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”. One of ordinary skill in the art would recognize that the cited passages of Kurakami teach a lane detection result from a first sensor and a lane detection result from a second sensor. The first sensor is clearly a camera used to detect the lane and the second sensor is a map in combination with a position sensor used to determine the lane. Furthermore, the cited passages clearly teach determining a first diving route based on the first detection result and a second driving route based on the second detection result.);
generating, by the controller, at least one driving route, based on the at least one lane detection result (Kurakami: Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”);
determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.);
determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route (Kurakami: Figure 8, Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly show that the system is configured to select the at least one driving route as the final driving route.)
and controlling, by the controller, the host vehicle to travel based on the generated final driving route (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to control the vehicle based on the driving route.).
Kokido teaches an autonomous driving control method, comprising: determining, by a controller, at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of a first sensor included in a sensor device or a second sensor included in the sensor device, or any combination thereof. Kokido does not teach determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor; generating, by the controller, at least one driving route, based on the at least one lane detection result; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route; determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route and controlling, by the controller, the host vehicle to travel based on the generated final driving route. Kurakami teaches determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor; generating, by the controller, at least one driving route, based on the at least one lane detection result; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route; determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route and controlling, by the controller, the host vehicle to travel based on the generated final driving route. A person of ordinary skill in the art would have had the technological capabilities required to have combine the method taught in Kokido with determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor; generating, by the controller, at least one driving route, based on the at least one lane detection result; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route; determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route and controlling, by the controller, the host vehicle to travel based on the generated final driving route taught in Kurakami, Furthermore, the method taught in Kokido is already configured to detect a lane in which the vehicle is travelling using a second sensor, and modifying the apparatus to generate and determine a driving route based on the lane detection would only require the addition of the trajectory planning using the methods taught in Kurakami. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous driving control method, comprising: determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor; generating, by the controller, at least one driving route, based on the at least one lane detection result; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route; determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route and controlling, by the controller, the host vehicle to travel based on the generated final driving route.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine autonomous driving control method taught in Kokido with determining of the at least one lane detection result comprises generating, by the controller, a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor; generating, by the controller, at least one driving route, based on the at least one lane detection result; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route; determining, by the controller, a final driving route for autonomous driving of the host vehicle, based on the at least one driving route and controlling, by the controller, the host vehicle to travel based on the generated final driving route taught in Kurakami with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami does not teach by generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value, or generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”. The cited passage clearly teaches that the system is configured to select final driving path as the path with a reliability greater than a predetermined reliability threshold. Additionally, one of ordinary skill in the art would recognize that because the system is configured to select the path that has the highest reliability and is greater than a predetermined threshold, the system would select the second path as the driving route when the first reliability is less than the threshold and the second reliability is greater than the threshold.).
Kokido in view of Kurakami teaches an autonomous vehicle control method further comprising: generating, by the controller, a first driving route based on a first lane detection result identified using the first sensor and generating, by the controller, a second driving route based on a second lane detection result identified using the second sensor; determining, by the controller, first reliability value of the first driving route and second reliability value of the second driving route. Kokido in view of Kurakami also teaches setting the driving route based on whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami does not teach generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value. Kim Sang teaches generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami with generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value; and generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value taught in Kim Sang. Furthermore, because the method taught in Kokido in view of Kurakami already teaches determining a reliability value for each path, comparing the reliability of each path to each other, and selecting the path based on this comparison, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and select the driving path based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: by generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value, or generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami with by generating, by the controller, the final driving route based on the first driving route, when the first reliability value is greater than or equal to reference reliability value, or generating, by the controller, the final driving route based on the second driving route, when the first reliability value is less than the reference reliability value and when the second reliability value is greater than or equal to the reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 5 and 8 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20240400095 A1 ("Lee") in further view of KR 20230073832 A ("Kim Sang").
Regarding claim 5, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in an opposite direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the right lane is detected in the periphery driving lane detection or vice versa.):
determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.);
generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
Kokido in further view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value.
Lee, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold.).
Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result: determine the first reliability value of the first driving route and the second reliability value of the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route. Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value. Lee teaches determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is greater than a threshold using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Kim Sang, in the same field of endeavor teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Lee teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route. Kokido in view of Kurakami in further view of Lee also teaches determining whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. Kim Sang teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami in further view of Lee already teaches determining a reliability value for each path, comparing the reliability of each path to each other, determine the similarity of the paths, and performing an action based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Regarding claim 8, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in the same direction as a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in the same direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the left lane is detected in the periphery driving lane detection or vice versa.):
determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.);
generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route (Kurakami: Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”. The cited passages clearly teach that the final driving route is generated based on the route information corresponding to the first predicted route.).
Kokido in further view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value.
Lee, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold.).
Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in the same direction as a second line included in the second lane detection result: determine the first reliability value of the first driving route and the second reliability value of the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route. Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value. Lee teaches determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is greater than a threshold using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on at least one piece of route information corresponding to the first driving route, when the similarity value is greater than or equal to the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Kim Sang, in the same field of endeavor teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Lee teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route. Kokido in view of Kurakami in further view of Lee also teaches determining whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. Kim Sang teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami in further view of Lee already teaches determining a reliability value for each path, comparing the reliability of each path to each other, determine the similarity of the paths, and performing an action based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 6 and 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20240400095 A1 ("Lee") in further view of KR 20230073832 A ("Kim Sang") in further view of US 20230071612 A1 ("Takeuchi").
Regarding claim 6, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in an opposite direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the right lane is detected in the periphery driving lane detection or vice versa.):
determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.);
generate the final driving route including information about the first line and the second line (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Lee, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generate the final driving route including information about the first line and the second line when the similarity value is less than the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result: determine the first reliability value of the first driving route and the second reliability value of the second driving route; and generate the final driving route including information about the first line and the second line. Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Lee teaches determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is less than a threshold using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Kim Sang, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Lee teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route. Kokido in view of Kurakami in further view of Lee also teaches determining whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. Kim Sang teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami in further view of Lee already teaches determining a reliability value for each path, comparing the reliability of each path to each other, determine the similarity of the paths, and performing an action based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee in further view of Kim Sang does not teach generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Takeuchi, in the same field of endeavor, teaches generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value (Takeuchi: ¶ 0043, “For example, the first travel path information which the first travel path generation part 60 outputs and the second travel path information, which the second travel path generation part 70 outputs, are equivalent of determining each of the coefficients for a lateral position deviation, an angle deviation, a path curvature, and a path curvature deviation, with respect to a host vehicle and an approximated curve. It is worth noticing that, henceforth, the first travel path information and the second travel path information are abbreviated as the first travel path and the second travel path, respectively.”, ¶ 0044, “From the information of the first travel path generation part 60, the host vehicle position and azimuth detection part 10, the road map data 20, the second travel path generation part 70, the front camera sensor 30, and the vehicle sensor 40, the travel path weight setting part 90 sets a weight, which denotes the certainty between the first travel path of the first travel path generation part 60 and the second travel path of the second travel path generation part 70, that is, the ratio of possibility. The integrated travel path generation part 100 outputs an integrated travel path which is the one integrated to a single path, on the basis of the information of the first travel path generation part 60, the second travel path generation part 70, and the travel path weight setting part 90.”, ¶ 0054, “After that, in the integrated travel path generation part 100, an integrated travel path Path_total, on which a host vehicle should travel, is computed by the Equation 4, from the paths computed in Step SlO0 and Step S200 and the weights to the respective paths computed in Step S400 (Step S500).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. One of ordinary skill in the art would see from the cited passages that the system is configured to determine the curvature of the two potential paths of the vehicle, thew weights associated with the curvature of each path, and determine an integrated path using the two potential paths and their weights. This integrated driving path will be used to control the vehicle. As can be seen in Figure 19, the integrated path will fall roughly in the middle of the two potential paths and will have a lower curvature than at least one of the potential paths. This clearly teaches generating a final driving path based on path with a low curvature between the first and second driving paths.).
Kokido in view of Kurakami in further view of Lee in further view of Kim Sang teaches an autonomous vehicle control apparatus configured to generate the final driving route including information about the first line and the second line when the similarity value is less than the reference similarity value. Kokido in view of Kurakami in further view of Lee in further view of Kim Sang does not teach generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Takeuchi teaches generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang with generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang is already configured to determine multiple potential driving paths, the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and a final driving path based on the first and second driving paths. The apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang could be modified to determine the final driving route based on a driving route with a low curvature between the first and second driving routes as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus configured to: generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang with generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Regarding claim 9, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in the same direction as a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in an opposite direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the left lane is detected in the periphery driving lane detection or vice versa.):
determine the first reliability value of the first driving route and the second reliability value of the second driving route (Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.);
generate the final driving route including information about the first line and the second line (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Lee, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generate the final driving route including information about the first line and the second line, when the similarity value is less than the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: when a first line included in the first lane detection result corresponds to a line in the same direction as a second line included in the second lane detection result: determine the first reliability value of the first driving route and the second reliability value of the second driving route; and generate the final driving route including information about the first line and the second line. Kokido in view of Kurakami does not teach determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Lee teaches determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is less than a threshold using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is greater than or equal to the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with determine a similarity value between the first driving route and the second driving route; and generate the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Kim Sang, in the same field of endeavor, teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Lee teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route. Kokido in view of Kurakami in further view of Lee also teaches determining whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Lee does not teach determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. Kim Sang teaches determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami in further view of Lee already teaches determining a reliability value for each path, comparing the reliability of each path to each other, determine the similarity of the paths, and performing an action based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee with determine a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Lee in further view of Kim Sang does not teach generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Takeuchi, in the same field of endeavor, teaches generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value (Takeuchi: ¶ 0043, “For example, the first travel path information which the first travel path generation part 60 outputs and the second travel path information, which the second travel path generation part 70 outputs, are equivalent of determining each of the coefficients for a lateral position deviation, an angle deviation, a path curvature, and a path curvature deviation, with respect to a host vehicle and an approximated curve. It is worth noticing that, henceforth, the first travel path information and the second travel path information are abbreviated as the first travel path and the second travel path, respectively.”, ¶ 0044, “From the information of the first travel path generation part 60, the host vehicle position and azimuth detection part 10, the road map data 20, the second travel path generation part 70, the front camera sensor 30, and the vehicle sensor 40, the travel path weight setting part 90 sets a weight, which denotes the certainty between the first travel path of the first travel path generation part 60 and the second travel path of the second travel path generation part 70, that is, the ratio of possibility. The integrated travel path generation part 100 outputs an integrated travel path which is the one integrated to a single path, on the basis of the information of the first travel path generation part 60, the second travel path generation part 70, and the travel path weight setting part 90.”, ¶ 0054, “After that, in the integrated travel path generation part 100, an integrated travel path Path_total, on which a host vehicle should travel, is computed by the Equation 4, from the paths computed in Step SlO0 and Step S200 and the weights to the respective paths computed in Step S400 (Step S500).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. One of ordinary skill in the art would see from the cited passages that the system is configured to determine the curvature of the two potential paths of the vehicle, thew weights associated with the curvature of each path, and determine an integrated path using the two potential paths and their weights. This integrated driving path will be used to control the vehicle. As can be seen in Figure 19, the integrated path will fall roughly in the middle of the two potential paths and will have a lower curvature than at least one of the potential paths. This clearly teaches generating a final driving path based on path with a low curvature between the first and second driving paths.).
Kokido in view of Kurakami in further view of Lee in further view of Kim Sang teaches an autonomous vehicle control apparatus configured to generate the final driving route including information about the first line and the second line when the similarity value is less than the reference similarity value. Kokido in view of Kurakami in further view of Lee in further view of Kim Sang does not teach generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Takeuchi teaches generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang with generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang is already configured to determine multiple potential driving paths, the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and a final driving path based on the first and second driving paths. The apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang could be modified to determine the final driving route based on a driving route with a low curvature between the first and second driving routes as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus configured to: generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Lee in further view of Kim Sang with generate the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 10 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20230071612 A1 ("Takeuchi") in further view of KR 20230073832 A ("Kim Sang").
Regarding claim 10, Kokido in view of Kurakami teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the first driving route identified using the first sensor before the host vehicle enters a section with a deviation of a specified value or more (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to control the vehicle based on the first driving route identified using the first sensor. Furthermore, the cited passages show that the vehicle is configured to determine when the vehicle will enter a section in which the predicted paths have a divergence greater than a threshold.).
when determining that the host vehicle is expected to enter the section (Kurakami: Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”. The cited passages show that the system is configured to check for divergence in advance, which in the example given is every 2.5 seconds in advance. One of ordinary skill in the art would recognize that this is a method of determining when the vehicle is expected to enter the section in which the divergence begins.)
Kokido in view of Kurakami does not teach when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more,
and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle.
Takeuchi, in the same field of endeavor, teaches when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more (Takeuchi: ¶ 0049, “First, in the first travel path generation part 60, a target point sequence (a point sequence arranged fundamentally in the lane center) of a lane on which a host vehicle is traveling presently and the state of the host vehicle are computed as an approximate expression on a host vehicle reference coordinate system, from the information of the host vehicle position and azimuth detection part 10 and the road map data 20. The expression is represented as the Equation 1 (Step Sl00).”, ¶ 0051, “Next, in the second travel path generation part 70, the travel path on which a host vehicle should travel is computed from the information of a division line which is detected with the front camera sensor 30, where the division line is ahead of a host vehicle. The expression is represented as the Equation 2 (Step S200).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. The cited passages show that the system is configured to generate a trajectory of a vehicle in advance and is further configured to determine the curvature of a road is greater than a series of thresholds.),
Kokido in view of Kurakami teaches an autonomous vehicle control apparatus configured to: wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the first driving route identified using the first sensor before the host vehicle enters a section with a deviation of a specified value or more when determining that the host vehicle is expected to enter the section. Kokido in view of Kurakami does not teach control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more. Takeuchi teaches control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami with control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more taught in Takeuchi. Furthermore, the apparatus taught in Kokido in view of Kurakami is already configured to determine multiple potential driving paths and the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and when the vehicle is expected to enter a section with a divergence greater than a threshold.. The apparatus taught in Kokido in view of Kurakami could be modified to determine when the vehicle is expected to enter a section of the road with a curvature greater than a threshold as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus configured to: control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami with control the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters a section with a curvature of a specified value or more, when determining that the host vehicle is expected to enter the section taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Takeuchi does not teach and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle.
Kim Sang, in the same field of endeavor, teaches and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Takeuchi teaches an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Takeuchi does not teach and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle. Kim Sang teaches and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi with and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle taught in Kim Sang. Furthermore, because the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi already teaches determining a reliability value for each path, comparing the reliability of each path to each other, and determining the final driving path based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the apparatus to compare the reliability values of the paths to a predetermined threshold and determine the final driving path based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Takeuchi with and that the first reliability value of the first driving route and the second reliability value of the second driving route are greater than or equal to reference reliability value, based on an estimated driving route of the host vehicle taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 11 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20230071612 A1 ("Takeuchi") in further view of KR 20230073832 A ("Kim Sang") in further view of US 10030969 B2 ("Tateishi").
Regarding claim 11, Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section.
Tateishi, in the same field of endeavor, teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section (Tateishi: Column 4 lines 34-44, “The map data 15 further contains road gradient information. The road gradient information corresponds to each road section stored in the map data 15. In the map data 15, the road gradient information of each road section represents a direction and magnitude of its road gradient.”, Column 10 lines 46-50, “FIG. 5 is a view showing a flow chart of the curvature detection process performed by the white line recognition device 20 in the in-vehicle system 1 as the road curvature detection device according to the exemplary embodiment shown in FIG. 1.”, Column 11 lines 7-13, “The control section 21 determines the lane boundary line candidate to be a lane boundary line when the lane boundary line candidate reaches a predetermined likelihood threshold value. The control section 21 specifies a lane boundary line which extends in the forward direction of the own vehicle as a calculation target for calculating a curvature of the lane boundary line. The operation flow progress to step S215.”, Column 11 lines 19-33, “At this time, the control unit 11 specifies a gradient accuracy of the obtained gradient information for the specified current road section. In other words, the control unit 11 detects a density of the gradient information for the specified current road section obtained from the map data 15. The control unit 11 determines the gradient accuracy of the gradient information for the specified current road section on the basis of the detection result. As previously described, the gradient information and the current road sections are stored in one-to-on correspondence in the map data 15. The control unit 11 calculates an average value A of lengths of the current road sections corresponding to the gradient information stored in the map data 15. When the average value A is gradually reduced, the control unit 11 recognizes that the gradient information has a high degree.”, Column 11 lines 34-37, “Specifically, the control unit 11 determines that the gradient accuracy of the gradient information is high when the average value A is smaller than a first predetermined value A1 (A<A1).”, Column 11 lines 38-44, “The control unit 11 determines that the gradient accuracy of the gradient information is medium when the first predetermined value A1 is not more than the average value A and the average value A is not more than a second predetermined value A2 (A1<=A<=A2), where The first predetermined value A1 is smaller than the second predetermined value A2 (A1<A2).”, Column 11 lines 45-48, “The control unit 11 determines that the gradient accuracy of the gradient information is low when the second predetermined value A2 is smaller than the average value A (A2<A).”. The cited passages teach a method of determining the curvature of a section of road using the accuracy of the gradient information of the road section. The cited passages further teach that this gradient accuracy is checked against various thresholds. One of ordinary skill in the art would recognize that the gradient of a section of road represents how curved that section of road is.).
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang teaches an autonomous vehicle control apparatus. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section. Tateishi teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in with wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section taught in Tateishi. Furthermore, the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang is already configured to select the second predicted driving path as the final driving path when the reliability of the second driving path is greater than the first driving path (i.e. when the reliability of the first driving path is low). Additionally, the apparatus is already configured to determine the curvature of the predicted paths. A person of ordinary skill in the art would be able to modify the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang to determine if the accuracy of the curvature information is less than a threshold and select the second travel path as the final travel path using the methods taught in Tateishi, as the accuracy of the curvature information detected by a sensor would clearly have an effect on the reliability of the path determined using this information. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus configured to wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang with wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: control the host vehicle to travel based on the second driving route when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section taught in Tateishi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20230071612 A1 ("Takeuchi") in further view of KR 20230073832 A ("Kim Sang") in further view of US 20240400095 A1 ("Lee").
Regarding claim 12, Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: generate the final driving route based on the first driving route (Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 15 lines 1-7, “In step S106, the driving support controller 2 determines whether the first prediction path PT1 has higher reliability than the second prediction path PT2. If it is determined that the first prediction path PT1 has higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S107 to select the first prediction path PT1 as the travel path.”. The cited passages clearly teach that the final driving route is generated based on the route information corresponding to the first predicted route.).
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and
generate the final driving route based on the first driving route, when the similarity value meets a specified criterion.
Lee, in the same field of endeavor, teaches determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generate the final driving route based on the first driving route, when the similarity value meets a specified criterion (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: generate the final driving route based on the first driving route. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and generate the final driving route based on the first driving route, when the similarity value meets a specified criterion. Lee teaches determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and generate the final driving route based on the first driving route, when the similarity value meets a specified criterion. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang with determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and generate the final driving route based on the first driving route, when the similarity value meets a specified criterion taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang could then be easily modified to determine the similarity value between each trajectory and determining if this similarity meets a specified criterion using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and generate the final driving route based on the first driving route, when the similarity value meets a specified criterion.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang with determine the similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section; and generate the final driving route based on the first driving route, when the similarity value meets a specified criterion taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 2021/0009161 A1 ("Kim") in further view of US 20240400095 A1 ("Lee").
Regarding claim 15, Kokido in view of Kurakami in further view of Kim teaches when a difference between the first curvature and the second curvature is less than a reference curvature difference (Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane. The left deviation amount may be calculated by using positional information of the left edge l00EL of the subject vehicle 100A or by using information about the center position of the subject vehicle 100A in the vehicle width direction.”, Column 17 lines 22-29, “Referring back to the flowchart in FIG. 14, the driving support controller 2 determines in step S302 whether the left deviation amount is larger than a first threshold value (e.g., 1 m). If it is determined that the left deviation amount is larger than the first threshold value (1 m), the driving support controller 2 sets a left deviation flag to the ON mode in step S303 and ends the left deviation determination process since the left deviation amount is large.”, Column 17 lines 30-40, “In contrast, if it is determined that the left deviation amount is smaller than or equal to the first threshold value (1 m), the driving support controller 2 proceeds to step S304 to determine whether the left deviation amount is larger than a second threshold value (e.g., 20 cm). If the left deviation amount is larger than the second threshold value (20 cm), that is, if the left deviation amount is larger than the second threshold value (20 cm) and smaller than or equal to the first threshold value (1 m), the driving support controller 2 determines in step S305 whether an ON time variable is larger than 0.5 seconds.”. The cited passages show that the divergence (i.e. similarity) between the two predicted paths can be determined based on the curvature of the paths. Additionally, the cited passages teach that the difference is compared to a threshold to check if it is less than said threshold. One of ordinary skill in the art would recognize that because the deviation can be determined based on any of the metrics listed, the threshold the deviation is compared to would change accordingly.)
and when a difference between the first heading and the second heading is less than a reference heading difference (Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane. The left deviation amount may be calculated by using positional information of the left edge l00EL of the subject vehicle 100A or by using information about the center position of the subject vehicle 100A in the vehicle width direction.”, Column 17 lines 22-29, “Referring back to the flowchart in FIG. 14, the driving support controller 2 determines in step S302 whether the left deviation amount is larger than a first threshold value (e.g., 1 m). If it is determined that the left deviation amount is larger than the first threshold value (1 m), the driving support controller 2 sets a left deviation flag to the ON mode in step S303 and ends the left deviation determination process since the left deviation amount is large.”, Column 17 lines 30-40, “In contrast, if it is determined that the left deviation amount is smaller than or equal to the first threshold value (1 m), the driving support controller 2 proceeds to step S304 to determine whether the left deviation amount is larger than a second threshold value (e.g., 20 cm). If the left deviation amount is larger than the second threshold value (20 cm), that is, if the left deviation amount is larger than the second threshold value (20 cm) and smaller than or equal to the first threshold value (1 m), the driving support controller 2 determines in step S305 whether an ON time variable is larger than 0.5 seconds.”. The cited passages show that the divergence (i.e. similarity) between the two predicted paths can be determined based on the heading of the vehicle. Additionally, the cited passages teach that the difference is compared to a threshold to check if it is less than said threshold. One of ordinary skill in the art would recognize that because the deviation can be determined based on any of the metrics listed, the threshold the deviation is compared to would change accordingly.).
Kokido in view of Kurakami in further view of Kim does not teach wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value,
Lee, in the same field of endeavor, teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths.).
Kokido in view of Kurakami in further view of Kim teaches an autonomous vehicle control apparatus wherein the similarity is determined when a difference between the first curvature and the second curvature is less than a reference curvature difference and when a difference between the first heading and the second heading is less than a reference heading difference. Kokido in view of Kurakami in further view of Kim does not teach wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value. Lee teaches wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the apparatus taught in Kokido in view of Kurakami in further view of Kim with wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value taught in Lee. Furthermore, the apparatus taught in Kokido in view of Kurakami in further view of Kim already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Additionally, Kokido in view of Kurakami in further view of Kim teaches determining the divergence based on whether the divergence is less than a threshold, wherein the divergence can be determined based on the curvature of the paths or the heading of the vehicle. Kokido in view of Kurakami in further view of Kim could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is greater than or equal to reference similarity value using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control apparatus comprising: wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control apparatus taught in Kokido in view of Kurakami in further view of Kim with wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine that the similarity value between the first driving route and the second driving route is greater than or equal to reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 18 and 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of KR 20230073832 A ("Kim Sang") in further view of US 20240400095 A1 ("Lee") in further view of US 20230071612 A1 ("Takeuchi").
Regarding claim 18, Kokido in view of Kurakami in further view of Kim Sang teaches wherein the determining of the first reliability value and the second reliability value comprises determining, by the controller, the first reliability value and the second reliability value, when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”, Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in an opposite direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the right lane is detected in the periphery driving lane detection or vice versa.), and wherein the method further comprises:
determining, by the controller, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”);
generating, by the controller, the final driving route including information about the first line and the second line (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
Kokido in view of Kurakami in further view of Kim Sang does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Lee, in the same field of endeavor, teaches determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
generating, by the controller, the final driving route including information about the first line and the second line, when the similarity value is less than the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami in further of Kim Sang teaches wherein the determining of the first reliability value and the second reliability value comprises determining, by the controller, the first reliability value and the second reliability value, when a first line included in the first lane detection result corresponds to a line in an opposite direction to a second line included in the second lane detection result;, and the method further comprises: determining, by the controller, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line. Kokido in view of Kurakami does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Lee teaches determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Kim Sang with determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee. Furthermore, the method taught in Kokido in view of Kurakami in view of Kim Sang already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold as well as the reliability of the trajectories. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is less than a threshold using the methods taught in Lee. Furthermore, the method taught in Kokido in view of Kurakami in further view of Kim Sang already teaches determining a reliability value for each path, comparing the reliability of each path to each other. a person of ordinary skill in the art would have easily been able to modify the method to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method comprising: determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami with determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Kim Sang in further view of Lee does not teach generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Takeuchi, in the same field of endeavor, teaches generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value (Takeuchi: ¶ 0043, “For example, the first travel path information which the first travel path generation part 60 outputs and the second travel path information, which the second travel path generation part 70 outputs, are equivalent of determining each of the coefficients for a lateral position deviation, an angle deviation, a path curvature, and a path curvature deviation, with respect to a host vehicle and an approximated curve. It is worth noticing that, henceforth, the first travel path information and the second travel path information are abbreviated as the first travel path and the second travel path, respectively.”, ¶ 0044, “From the information of the first travel path generation part 60, the host vehicle position and azimuth detection part 10, the road map data 20, the second travel path generation part 70, the front camera sensor 30, and the vehicle sensor 40, the travel path weight setting part 90 sets a weight, which denotes the certainty between the first travel path of the first travel path generation part 60 and the second travel path of the second travel path generation part 70, that is, the ratio of possibility. The integrated travel path generation part 100 outputs an integrated travel path which is the one integrated to a single path, on the basis of the information of the first travel path generation part 60, the second travel path generation part 70, and the travel path weight setting part 90.”, ¶ 0054, “After that, in the integrated travel path generation part 100, an integrated travel path Path_total, on which a host vehicle should travel, is computed by the Equation 4, from the paths computed in Step SlO0 and Step S200 and the weights to the respective paths computed in Step S400 (Step S500).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. One of ordinary skill in the art would see from the cited passages that the system is configured to determine the curvature of the two potential paths of the vehicle, thew weights associated with the curvature of each path, and determine an integrated path using the two potential paths and their weights. This integrated driving path will be used to control the vehicle. As can be seen in Figure 19, the integrated path will fall roughly in the middle of the two potential paths and will have a lower curvature than at least one of the potential paths. This clearly teaches generating a final driving path based on path with a low curvature between the first and second driving paths.).
Kokido in view of Kurakami in further view of Kim Sang in further view of Lee teaches an autonomous vehicle control method further comprising: generating, by the controller, the final driving route including information about the first line and the second line when the similarity value is less than the reference similarity value. Kokido in view of Kurakami in further view of Kim Sang in further view of Lee does not teach generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Takeuchi teaches generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee with generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Takeuchi. Furthermore, the method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee is already configured to determine multiple potential driving paths, the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and a final driving path based on the first and second driving paths. The method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee could be modified to determine the final driving route based on a driving route with a low curvature between the first and second driving routes as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee with generating, by the controller, the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value, when the similarity value is less than the reference similarity value taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Regarding claim 19, Kokido in view of Kurakami teaches wherein the determining of the first reliability value and the second reliability value comprises determining, by the controller, the first reliability value and the second reliability value, when a first line included in the first lane detection result corresponds to a line in the same direction to a second line included in the second lane detection result (Kokido: Column 7 lines 22-31, “Then the frontward driving lane detection unit performs image recognition on the vehicle frontward image acquired from the frontward detection camera unit 1, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle frontward lane shape, and calculates the reliability of the detected division line result as the frontward lane detection reliability (step Sl-5). The calculated base vehicle frontward lane shape and the frontward lane detection reliability are notified to the base 30 vehicle driving lane determination unit 5.”, Column 7 lines 32-41, “Then the periphery driving lane detection unit 4 performs image recognition on the vehicle periphery image acquired from the periphery detection camera unit 2, and detects the left and right division lines of the lane where the base vehicle is driving, as the base vehicle periphery lane shape, and calculates the reliability of the detected division line result as the periphery lane detection reliability (step Sl-6). The calculated base vehicle periphery lane shape and the periphery lane detection reliability are notified to the base vehicle driving lane determination unit 5.”, Kurakami: Column 10 lines 22-26, “The reliability determination process may involve calculating the reliability of each of the first prediction path PT1 and the second prediction path PT2 in a plurality of levels (e.g., 0 to 100), or calculating the levels of reliability in the form of flags (0 and 1).”. The cited passages clearly teach determining the reliability of each path.. Kokido clearly teaches both lane lines are detected in both the forward and periphery lane detection. One of ordinary skill in the art would clearly see that this teaches detecting a first line in the first lane detection that is in the same direction to a second line in the second lane detection because the left lane is detected in the forward driving lane detection and the left lane is detected in the periphery driving lane detection or vice versa.), and wherein the method further comprises:
generating, by the controller, the final driving route including information about the first line and the second line (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
determining, by the controller, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”);
generating, by the controller, the final driving route including information about the first line and the second line (Kurakami: Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”, Column 14 lines 54-56, “In step S103, the driving support controller 2 generates the third prediction path PT3 (see FIG. 3) based on the first prediction path PT1 and the second prediction path PT2.”, Column 14 lines 57-59, “Then, in step S104, the driving support controller 2 selects the third prediction path PT3 as the travel path of the subject vehicle 100A.”).
Kokido in view of Kurakami in further view of Kim Sang does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and
generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Lee, in the same field of endeavor, teaches determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined.); and
Generating the final driving route including information about the first line and the second line, when the similarity value is less than the reference similarity value (Lee: ¶ 0090, “Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami in further of Kim Sang teaches wherein the determining of the first reliability value and the second reliability value comprises determining, by the controller, the first reliability value and the second reliability value, when a first line included in the first lane detection result corresponds to a line in an same direction to a second line included in the second lane detection result;, and the method further comprises: determining, by the controller, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line. Kokido in view of Kurakami does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Lee teaches determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Kim Sang with determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee. Furthermore, the method taught in Kokido in view of Kurakami in view of Kim Sang already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold as well as the reliability of the trajectories. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami could then be easily modified to determine the similarity value between each trajectory and determining if this similarity is less than a threshold using the methods taught in Lee. Furthermore, the method taught in Kokido in view of Kurakami in further view of Kim Sang already teaches determining a reliability value for each path, comparing the reliability of each path to each other. a person of ordinary skill in the art would have easily been able to modify the method to compare the reliability values of the paths to a predetermined threshold and determine the similarity the driving paths based on this comparison as taught in Kim Sang. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method comprising: determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami with determining, by the controller, a similarity value between the first driving route and the second driving route, when the first reliability value and the second reliability value are greater than or equal to reference reliability value; and generating, by the controller, the final driving route including information about the first line and the second line based on the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Kim Sang in further view of Lee does not teach generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Takeuchi, in the same field of endeavor, teaches generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value (Takeuchi: ¶ 0043, “For example, the first travel path information which the first travel path generation part 60 outputs and the second travel path information, which the second travel path generation part 70 outputs, are equivalent of determining each of the coefficients for a lateral position deviation, an angle deviation, a path curvature, and a path curvature deviation, with respect to a host vehicle and an approximated curve. It is worth noticing that, henceforth, the first travel path information and the second travel path information are abbreviated as the first travel path and the second travel path, respectively.”, ¶ 0044, “From the information of the first travel path generation part 60, the host vehicle position and azimuth detection part 10, the road map data 20, the second travel path generation part 70, the front camera sensor 30, and the vehicle sensor 40, the travel path weight setting part 90 sets a weight, which denotes the certainty between the first travel path of the first travel path generation part 60 and the second travel path of the second travel path generation part 70, that is, the ratio of possibility. The integrated travel path generation part 100 outputs an integrated travel path which is the one integrated to a single path, on the basis of the information of the first travel path generation part 60, the second travel path generation part 70, and the travel path weight setting part 90.”, ¶ 0054, “After that, in the integrated travel path generation part 100, an integrated travel path Path_total, on which a host vehicle should travel, is computed by the Equation 4, from the paths computed in Step SlO0 and Step S200 and the weights to the respective paths computed in Step S400 (Step S500).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. One of ordinary skill in the art would see from the cited passages that the system is configured to determine the curvature of the two potential paths of the vehicle, thew weights associated with the curvature of each path, and determine an integrated path using the two potential paths and their weights. This integrated driving path will be used to control the vehicle. As can be seen in Figure 19, the integrated path will fall roughly in the middle of the two potential paths and will have a lower curvature than at least one of the potential paths. This clearly teaches generating a final driving path based on path with a low curvature between the first and second driving paths.).
Kokido in view of Kurakami in further view of Kim Sang in further view of Lee teaches an autonomous vehicle control method further comprising: generating, by the controller, the final driving route including information about the first line and the second line when the similarity value is less than the reference similarity value. Kokido in view of Kurakami in further view of Kim Sang in further view of Lee does not teach generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. Takeuchi teaches generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee with generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value taught in Takeuchi. Furthermore, the method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee is already configured to determine multiple potential driving paths, the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and a final driving path based on the first and second driving paths. The method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee could be modified to determine the final driving route based on a driving route with a low curvature between the first and second driving routes as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami in further view of Kim Sang in further view of Lee with generating the final driving route including information about the first line and the second line based on a driving route with a low curvature between the first driving route and the second driving route, when the similarity value is less than the reference similarity value, when the similarity value is less than the reference similarity value taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Claim(s) 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 10821975 B2 ("Kokido") in view of US 12221100 B2 ("Kurakami") in further view of US 20230071612 A1 ("Takeuchi") in further view of KR 20230073832 A ("Kim Sang") in further view of US 10030969 B2 ("Tateishi") in further view of US 20240400095 A1 ("Lee").
Regarding claim 20, Kokido in view of Kurakami teaches further comprising: when determining, by the controller, that the host vehicle is expected to enter a section with a deviation of a specified value or more (Kurakami: Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”. The cited passages show that the vehicle is configured to determine when the vehicle will enter a section in which the predicted paths have a divergence greater than a threshold. One of ordinary skill in the art would recognize that this is a method of determining when the vehicle is expected to enter the section in which the divergence begins.):
controlling, by the controller, the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters the section (Kurakami: Column 4 lines 27-34, “The stereo camera 18 may be replaced with a camera device equipped with a single imaging unit having a distance measurable imaging element. In addition to the stereo camera 18 that captures an image in front of the vehicle 100, the external environment recognizer may include an imaging unit that captures an image behind the vehicle 100 and an imaging unit that captures images at the lateral sides”, Column 4 lines 44-55, “The image processor 19 executes various kinds of image processing based on each piece of captured image data obtained by stereo imaging so as to recognize forward information, such as three-dimensional-object data and boundary lines (such as a center line and lane boundary lines) in front of the subject vehicle, and can estimate the road and the lane (i.e., subject-vehicle travel lane) on which the subject vehicle is traveling based on the recognized information.”, Column 9 line 63 – Colum 10 line 5, “In other words, it is determined that there is a divergence between the two prediction paths if the subject vehicle 100A traveling along either one of the prediction paths deviates from the other prediction path by a predetermined amount or more. This determination result can be regarded as a result obtained in a case where the divergence is to increase after a predetermined time period (e.g., after 2.5 seconds) even if there is no divergence between the first prediction path PT1 and the second prediction path PT2 at the current location of the subject vehicle l00A.”, Column 13 line 58 – Colum 14 line 4, “FIG. 9 illustrates a first example where it may be determined that there is a divergence in the divergence determination process. FIG. 9 schematically illustrates an area surrounding an exit of a highway. As illustrated in FIG. 9, if the driving support controller 2 selects the first prediction path PT1 based on information from the map locator 4 as the travel path, the subject vehicle 100A continues to travel on the main line of the highway. In contrast, if the travel path of the subject vehicle 100A is selected based on the left lane line WLL serving as a lane line to the left of the subject vehicle 100A, the second prediction path PT2 is selected. In this case, it is determined that there is a divergence of a predetermined amount or more between the first prediction path PT1 and the second prediction path PT2.”, Column 15 lines 8-12, “In contrast, if it is determined that the first prediction path PT1 does not have higher reliability than the second prediction path PT2, the driving support controller 2 proceeds to step S108 to select the second prediction path PT2 as the travel path.”. The cited passages clearly teach that the system is configured to control the vehicle based on the first driving route identified using the first sensor. Furthermore, the cited passages show that the vehicle is configured to determine when the vehicle will enter a section in which the predicted paths have a divergence greater than a threshold.).
Kokido in view of Kurakami does not teach when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more,
and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle;
controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section; and
determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion.
Takeuchi, in the same field of endeavor, teaches when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more (Takeuchi: ¶ 0049, “First, in the first travel path generation part 60, a target point sequence (a point sequence arranged fundamentally in the lane center) of a lane on which a host vehicle is traveling presently and the state of the host vehicle are computed as an approximate expression on a host vehicle reference coordinate system, from the information of the host vehicle position and azimuth detection part 10 and the road map data 20. The expression is represented as the Equation 1 (Step Sl00).”, ¶ 0051, “Next, in the second travel path generation part 70, the travel path on which a host vehicle should travel is computed from the information of a division line which is detected with the front camera sensor 30, where the division line is ahead of a host vehicle. The expression is represented as the Equation 2 (Step S200).”, ¶ 0066, “First, the weight of the bird's-eye view detection travel path weight W bird_l_cX (X=O, 1, 2, 3) for the first travel path is set to be a maximum value of 1 (Step S411) Next, it is judged whether the magnitude of the coefficient of a curvature element of an approximated curve is larger than a threshold value C2_threshold, namely, it is judged whether a road curvature is larger than the threshold value C2_threshold (Step S412), where the approximated curve shows the relation between a host vehicle and a target path, and is computed in the first travel path generation part 60. When it is judged that the path curvature is larger in Step S412, the bird's-eye view detection travel path weight W bird_2_cX to the second travel path is set as a value which is smaller than the bird's-eye view detection travel path weight W bird_l_cX to the first travel path (Step S413).”. The cited passages show that the system is configured to generate a trajectory of a vehicle in advance and is further configured to determine the curvature of a road is greater than a series of thresholds.),
Kokido in view of Kurakami teaches an autonomous vehicle control method further comprising: generating, by the controller, a first driving route based on a first lane detection result identified using the first sensor and generating, by the controller, a second driving route based on a second lane detection result identified using the second sensor; and when determining, by the controller, that the host vehicle is expected to enter a section with a deviation of a specified value or more: controlling, by the controller, the host vehicle to travel based on the first driving route identified using the first sensor, before the host vehicle enters the section. Kokido in view of Kurakami does not teach when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more. Takeuchi teaches when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami with when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more taught in Takeuchi. Furthermore, the method taught in Kokido in view of Kurakami is already configured to determine multiple potential driving paths and the curvature of the driving paths (Kokido: Column 4 lines 47-52, “To calculate the shape of the division line, the offset distance between the base vehicle and the division line and the inclination of the division line are determined based on the edge feature points of the side camera image, and the curve components of the division line are determined based on the edge feature points of the front camera image.” Kurakami: Column 17 lines 4-15, “The left deviation amount can be calculated from, for example, the vehicle width of the subject vehicle 100A, the position of the subject vehicle l00A in the lane width direction, the lane width of the travel lane, the curvature of the travel lane, the speed and acceleration of the subject vehicle 100A, and the yaw angle of the subject vehicle l00A relative to the travel lane.”), and when the vehicle is expected to enter a section with a divergence greater than a threshold.. The method taught in Kokido in view of Kurakami could be modified to determine when the vehicle is expected to enter a section of the road with a curvature greater than a threshold as taught in Takeuchi. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami with when determining, by the controller, that the host vehicle is expected to enter a section with a curvature of a specified value or more taught in Takeuchi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Takeuchi does not teach and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle;
controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section; and
determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion.
Kim Sang, in the same field of endeavor, teaches and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle (Kim Sang: Abstract, “The present invention provides a method and a device for searching routes in units of lanes in consideration of the operational design domain (ODD) of an autonomous vehicle. The method comprises, in a state where global path information is being transmitted from a control server to the autonomous vehicle, the steps of: (a) when specific global path information is transmitted, performing at least part of a first process (i), a second process (ii), and a third process (iii); (b) searching for a plurality of local routes located within a predetermined driving distance from the autonomous vehicle and calculating a reliability score for each of the plurality of local routes; and (c) selecting a specific local route with a specific reliability score, which is the highest reliability score among predetermined reliability scores equal to or greater than a preset reliability threshold, as the optimal driving route for the autonomous vehicle, and performing or assisting traveling of the autonomous vehicle along the specific local route.”, ¶ 0008, “In addition, the present invention compares each reliability score with a preset reliability threshold and selects a specific regional path having the highest reliability score among the reliability scores that are equal to or greater than the preset reliability threshold as the optimal driving route for an autonomous vehicle. Another purpose is to enable autonomous vehicles to operate along the optimal driving path.”, ¶ 0112, “Next, the path search apparatus 100 compares each reliability score with a preset reliability threshold value to determine whether each reliability score is equal to or greater than the preset reliability threshold value, and determines whether or not each reliability score is equal to or greater than the preset reliability threshold value. By selecting a specific regional route having a specific reliability score, which is the highest reliability score among the scores, as an optimal driving route for the autonomous vehicle, the autonomous vehicle can be operated or supported to operate along the specific regional route (S240).”).
Kokido in view of Kurakami in further view of Takeuchi teaches an autonomous vehicle control method further comprising: determining whether the first path reliability is greater than the second path reliability or vice versa. Kokido in view of Kurakami in further view of Takeuchi does not teach and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle. Kim Sang teaches and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Takeuchi with and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle taught in Kim Sang. Furthermore, because the method taught in Kokido in view of Kurakami in further view of Takeuchi already teaches determining a reliability value for each path, comparing the reliability of each path to each other, and determining the final driving path based on these comparisons, a person of ordinary skill in the art would have easily been able to modify the method to compare the reliability values of the paths to a predetermined threshold and determine the final driving path based on this comparison as taught in Kim Sang. The modification would consist of the simple addition of a comparison to a threshold using the methods taught in Kim Sang. Such a modification would be well within the technological capabilities of one of ordinary skill in the art. This modification would not have changed or introduced new functionality to either. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami in further view of Takeuchi with and that the first reliability value and the second reliability value are greater than or equal to reference reliability value, based on an expected driving route of the host vehicle taught in Kim Sang with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section; and
determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion.
Tateishi, in the same field of endeavor teaches controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section (Tateishi: Column 4 lines 34-44, “The map data 15 further contains road gradient information. The road gradient information corresponds to each road section stored in the map data 15. In the map data 15, the road gradient information of each road section represents a direction and magnitude of its road gradient.”, Column 10 lines 46-50, “FIG. 5 is a view showing a flow chart of the curvature detection process performed by the white line recognition device 20 in the in-vehicle system 1 as the road curvature detection device according to the exemplary embodiment shown in FIG. 1.”, Column 11 lines 7-13, “The control section 21 determines the lane boundary line candidate to be a lane boundary line when the lane boundary line candidate reaches a predetermined likelihood threshold value. The control section 21 specifies a lane boundary line which extends in the forward direction of the own vehicle as a calculation target for calculating a curvature of the lane boundary line. The operation flow progress to step S215.”, Column 11 lines 19-33, “At this time, the control unit 11 specifies a gradient accuracy of the obtained gradient information for the specified current road section. In other words, the control unit 11 detects a density of the gradient information for the specified current road section obtained from the map data 15. The control unit 11 determines the gradient accuracy of the gradient information for the specified current road section on the basis of the detection result. As previously described, the gradient information and the current road sections are stored in one-to-on correspondence in the map data 15. The control unit 11 calculates an average value A of lengths of the current road sections corresponding to the gradient information stored in the map data 15. When the average value A is gradually reduced, the control unit 11 recognizes that the gradient information has a high degree.”, Column 11 lines 34-37, “Specifically, the control unit 11 determines that the gradient accuracy of the gradient information is high when the average value A is smaller than a first predetermined value A1 (A<A1).”, Column 11 lines 38-44, “The control unit 11 determines that the gradient accuracy of the gradient information is medium when the first predetermined value A1 is not more than the average value A and the average value A is not more than a second predetermined value A2 (A1<=A<=A2), where The first predetermined value A1 is smaller than the second predetermined value A2 (A1<A2).”, Column 11 lines 45-48, “The control unit 11 determines that the gradient accuracy of the gradient information is low when the second predetermined value A2 is smaller than the average value A (A2<A).”. The cited passages teach a method of determining the curvature of a section of road using the accuracy of the gradient information of the road section. The cited passages further teach that this gradient accuracy is checked against various thresholds. One of ordinary skill in the art would recognize that the gradient of a section of road represents how curved that section of road is.).
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang teaches an autonomous vehicle control method. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang does not teach controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section. Tateishi teaches controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in with controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section taught in Tateishi. Furthermore, the method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang is already configured to select the second predicted driving path as the final driving path when the reliability of the second driving path is greater than the first driving path (i.e. when the reliability of the first driving path is low). Additionally, the method is already configured to determine the curvature of the predicted paths. A person of ordinary skill in the art would be able to modify the method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang to determine if the accuracy of the curvature information is less than a threshold and select the second travel path as the final travel path using the methods taught in Tateishi, as the accuracy of the curvature information detected by a sensor would clearly have an effect on the reliability of the path determined using this information. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang with controlling, by the controller, the host vehicle to travel based on the second driving route, when accuracy of curvature information included in the first lane detection result is less than reference accuracy, while the host vehicle enters the section taught in Tateishi with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion.
Lee, in the same field of endeavor, teaches determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion (Lee: Figure 6 operations 612 and 616, ¶ 0090, “At operation 612, the ML system may determine whether the first or second candidate trajectories satisfy a condition. The ML system may send candidate trajectories to be included in a tree search (e.g., tree structure) based on such candidate trajectories satisfying the condition. The condition may be a threshold for the probability of the candidate trajectory to meet or exceed. As such, the ML system may determine whether the first candidate trajectory and the second candidate trajectory satisfy the condition by determining whether the probability of the first candidate trajectory and the probability of the second candidate trajectory meet or exceed a threshold value. Filtering candidate trajectories based on probabilities may reduce the number of low-quality candidate trajectories in the tree structure while increasing the quality of trajectories in the tree structure, thereby reducing the computational expenses. If the ML system determines that the first or second candidate trajectory does not satisfy the condition (612: No), the ML system may exclude the candidate trajectory from the tree search. At operation 614, the ML system may determine to exclude the candidate trajectory from the tree structure based on the candidate trajectory failing to satisfy the condition. Further, the ML system may also exclude the learned candidate trajectory based on determining that the candidate trajectory is within a threshold level of similarity to an already generated candidate trajectory (learned or heuristic-based candidate trajectory).”, ¶ 0091, “In contrast, if the first or second candidate trajectories satisfy the condition (612: Yes), the ML system may send such candidate trajectories to be included in the tree structure. At operation 616, the ML system may determine a control trajectory based on generating a tree structure that includes the first and the second candidate trajectories.”. The cited passage clearly teaches that the system is configured to determine if the first or second trajectories satisfy a condition, one of which is a similarity between the two paths. One of ordinary skill in the art would see that in order to determine if the similarity between is within a threshold, the value representing the similarity of the two trajectories must first be determined. Additionally, the cited passages clearly show that a final driving path is determined based on the first and second candidate paths when a condition is satisfied. As can be seen, this condition can be when the similarity between the two candidate trajectories is greater than a threshold. The cited figure shows that the system is configured to perform a different action when the condition is not satisfied.).
Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi teaches an autonomous driving control method further comprising: generating the final driving route based on the first driving route. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi does not teach determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion. Lee teaches determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion. A person of ordinary skill in the art would have had the technological capabilities required to have modified the method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion taught in Lee. Furthermore, the method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi already teaches determining how much the two vehicle trajectories diverge and if this divergence is above a threshold. Determining the divergence between two trajectories is clearly a method of determining how similar the two trajectories are. Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi could then be easily modified to determine the similarity value between each trajectory and determining if this similarity meets a specified criterion using the methods taught in Lee. Such a modification would not have changed or introduced new functionality. No inventive effort would have been required. The combination would have yielded the predictable result of an autonomous vehicle control method further comprising: determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion.
Therefore, it would have been obvious to one of ordinary skill in the art, before the effective filling date of the claimed invention, to have combine the autonomous vehicle control method taught in Kokido in view of Kurakami in further view of Takeuchi in further view of Kim Sang in further view of Tateishi with determining, by the controller, a similarity value between the first driving route and the second driving route, after the host vehicle completes entering the section, and generating, by the controller, the final driving route based on the first driving route, when the similarity value meets specified criterion taught in Lee with a reasonable expectation of success. One of ordinary skill in the art would have been motivated to make this modification because the combination would have yielded predictable results.
Response to Arguments
Applicant’s arguments, see Page 13, filed February 13th, 2026, with respect to the 35 U.S.C. § 101 rejection of claims 1-9 and 13-19 have been fully considered and are persuasive. The independent claims 1 and 16 have been amended to recite the limitation “control the host vehicle to travel based on the generated final driving route”. The limitation is an active control step of the system using the information determined from the abstract idea. Such a limitation clearly shows integration into a practical application. Therefore, the 35 U.S.C. § 101 rejection of claims 1-9 and 13-19 have been withdrawn.
Applicant's arguments filed February 13th, 2026 have been fully considered but they are not persuasive.
Regarding Applicant’s arguments on Pages 13-16 applicant argues that the prior art on record does not teach the limitations of the amended independent claims 1 and 16 and the new independent claim 22.
Specifically on Pages 15-16, Applicant argues that the secondary reference Kurakami fails to teach the limitations “wherein each of the first sensor and the second sensor is configured to capture an image of lane markings of a road on which a host vehicle is traveling”, “determine a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor”, and “generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result”. The Examiner respectfully disagrees. In response to applicant's arguments against the references individually, one cannot show nonobviousness by attacking references individually where the rejections are based on combinations of references. See In re Keller, 642 F.2d 413, 208 USPQ 871 (CCPA 1981); In re Merck & Co., 800 F.2d 1091, 231 USPQ 375 (Fed. Cir. 1986). As stated in the Non-Final Office Action mailed November 13th, 2026, and in the 35 U.S.C. § 103 rejection section above, the primary reference Kokido teaches an autonomous driving control apparatus, comprising (Kokido: Figure 1, Column 3 lines 35-45): a sensor device including a first sensor and a second sensor different from the first sensor (Kokido: Column 3 lines 35-45, Column 3 lines 53-57, Column 3 lines 58-63); wherein each of the first sensor and the second sensor is configured to capture an image of lane markings of a road on which a host vehicle is traveling (Kokido: Column 3 lines 35-45, “In FIG. 1, the driving assist apparatus includes a frontward detection camera unit 1, a periphery detection camera unit 2, a frontward driving lane detection unit 3, a periphery driving lane detection unit 4, a base vehicle driving lane determination unit 5,…”, Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”. The cited passages clearly shows that the first and second sensors are configured to capture images of the lane markings of the road.); a memory storing at least one instruction (Kokido: Column 3 lines 46-52); and a controller operatively connected with the sensor device and the memory (Kokido: Column 3 lines 46-52, Column 3 lines 53-57, Column 3 lines 58-63), wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine at least one lane detection result regarding a lane in which a host vehicle is traveling, using at least one of the first sensor or the second sensor, or any combination thereof (Kokido: Column 3 line 64 – Column 4 line 9, Column 4 lines 28-36); wherein the at least one instruction is configured to, when executed by the controller, cause the autonomous driving control apparatus to: determine a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor (Kokido: Column 3 lines 53-57, “The frontward detection camera unit 1 acquires an image ahead of the vehicle where the vehicle moves using a monocular camera or a plurality of optical cameras installed in the vehicle, and notifies the image to the frontward driving lane detection unit 3.”, Column 3 lines 58-63, “The periphery detection camera unit 2 acquires an image of the periphery of the vehicle using one or a plurality of optical cameras, installed outside the vehicle, such as a front camera, a back camera, a side camera and a side mirror camera, and notifies the image to the periphery driving lane detection unit 4.”, Column 3 line 64 – Column 4 line 9, “The frontward driving lane detection unit 3 performs image recognition on the image ahead of the vehicle acquired from the frontward detection camera unit 1, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle frontward lane shape (frontward division line shape), and calculates the reliability of the detected division line result as the frontward lane detection reliability (first reliability).”, Column 4 lines 28-36, “The periphery driving lane detection unit 4 performs image recognition on the image of the periphery of the vehicle acquired from the periphery detection camera unit 2, and detects the division lines on the left and right of the lane where the base vehicle is driving, as the base vehicle periphery lane shape (periphery division line shape), and calculates the reliability of the detected division line result as the periphery lane detection reliability (second reliability).”). As can clearly be seen from the cited passages, Kokido teaches a first sensor that is a camera configured to capture an image of a forward direction of the vehicle and a second sensor that is different from the first sensor that is a camera configured to capture an image of a periphery of the vehicle. The system is further configured to use the capture images to determine a lane detection result for the image captured by the first and second sensor respectively. The secondary reference Kurakami teaches generate at least one driving route, based on the at least one lane detection result (Kurakami: Column 9 lines 13-20); and determine a final driving route for autonomous driving of the host vehicle, based on the at least one driving route (Kurakami: Figure 8, Column 15 lines 1-7, Column 15 lines 8-12); generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result (Kurakami: Column 9 lines 7-12, “The first prediction path generator generates a prediction path of the subject vehicle 100A based on positional information of the subject vehicle l00A and map information acquired from the map locator 4. The prediction path generated by the first prediction path generator 32 will be referred to as "first prediction path PT1".”, Column 9 lines 13-20, “The second prediction path generator generates a prediction path of the subject vehicle 100A based on vehicle-exterior environment information acquired from the stereo camera 18 and other sensors. In detail, the prediction path is generated based on a lane line (i.e., boundary line) recognized by the stereo camera 18. The prediction path generated by the second prediction path generator will be referred to as "second prediction path PT2".”, Column 9 lines 21-27, “The third prediction path generator 34 generates a third prediction path PT3 from the first prediction path PT1 and the second prediction path PT2. For example, as illustrated in FIG. 3, the third prediction path generator 34 generates a path extending through an intermediate point between the first prediction path PT1 and the second prediction path PT2 as the third prediction path PT3.”); generate the final driving route based on at least one of a similarity value between the first driving route and the second driving route, first reliability value for the first driving route, or second reliability value for the second driving route, or any combination thereof (Kurakami: Column 15 lines 1-7, Column 9 line 63 – Colum 10 line 5); and control the host vehicle to travel based on the generated final driving route (Kurakami: Column 4 lines 27-34, Column 4 lines 44-55, Column 9 line 63 – Colum 10 line 5, Column 13 line 58 – Colum 14 line 4, Column 15 lines 8-12). The cited passages clearly teaches that the system of Kurakami is configured to determine three paths based on lane detection results. The first path is based on a lane detection result from map information, the second path is based on lane detection results from a camera system, and the third path is based on the first two paths. One of ordinary skill in the art would recognize that because the third path is determined based on, in part, the second path, the third lane is also based on the lane detection result from the camera images. Furthermore, the apparatus taught in Kokido is already configured to detect a lane in which the vehicle is travelling using a first and second sensor respectfully, and uses these lane detection results in the control of the vehicle. As such, modifying the apparatus to generate and determine a driving route based on the lane detection of each sensor would only require the addition of the trajectory planning using the methods taught in Kurakami. Therefore, the combination of Kokido in view of Kurakami clearly teach the limitations “wherein each of the first sensor and the second sensor is configured to capture an image of lane markings of a road on which a host vehicle is traveling”, “determine a first lane detection result of the at least one lane detection result using the first sensor and determine a second lane detection result of the at least one lane detection result using the second sensor”, and “generate a first driving route and a second driving route, based respectively on the first lane detection result and the second lane detection result”.
Therefore, for the reasons stated herein and in the 35 U.S.C. § 103 rejection section above, the 35 U.S.C. § 103 rejection of the independent claims 1, 16, and 22 are maintained.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Noah W Stiebritz whose telephone number is (571)272-3414. The examiner can normally be reached Monday thru Friday 7-5 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Ramon Mercado can be reached at (571) 270-5744. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/N.W.S./ Examiner, Art Unit 3658
/Ramon A. Mercado/Supervisory Patent Examiner, Art Unit 3658
Prosecution Insights