DETAILED ACTION
Response to Amendment
This Action is responsive to Applicant’s response filed on 10/13/2025. All claims are still pending
in the present application. This Action is made FINAL.
Response to Arguments
During prosecution, claim scope not solely on the basis of claim language, but also on giving claims their broadest reasonable construction in light of the specification as it would be interpreted by one of ordinary skill in the art. In re Am. Acad. of Sci. Tech. Ctr., 367 F.3d 1359, 1364 (Fed. Cir. 2004). See also Superguide Corp. v. DirecTV Enterprises, Inc., 358 F.3d 870, 875 (Fed. Cir. 2004) (“Though understanding the claim language may be aided by explanations contained in the written description, it is important not to import into a claim limitations that are not part of the claim.”). Additionally, “[t]hough understanding the claim language may be aided by the explanations contained in the written description, it is important not to import into a claim limitations that are not a part of the claim. For example, a particular embodiment appearing in the written description may not be read into a claim when the claim language is broader than the embodiment.” Superguide Corp. v. DirecTV Enterprises, Inc., 358 F.3d 870, 875 (Fed. Cir. 2004).
In response to Argument 1, Applicant’s arguments, see Remarks, filed 10/13/2025, with respect to the rejection(s) of claim(s) 7-8 under 35 U.S.C. 112(a) and 112(b) have been fully considered and are persuasive. Therefore, the rejection has been withdrawn.
In regards to Argument(s) 2, Applicant(s) state(s) that, Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1) does not disclose/teach/suggest on “the distance thresholds are set based on the optical constraints of the cameras - their limited coverage - as illustrated by the FOV s of the cameras - and not based on distance ambiguities and Xu does not teach or suggest estimating, based on the visual information obtained by a visual sensor, and locations of road-boundary points up to a first distance from the visual sensor of a vehicle; wherein the visual information also comprises road-boundary points beyond to the first distance; wherein a distance ambiguity of visual based location determination of road-boundary points with the first distance range does not exceed an ambiguity threshold; wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds the ambiguity threshold; wherein a distance ambiguity of visual based location determination of a road-boundary point is an uncertainty associated with a determining of a location of the road-boundary point”, therefore, the rejection of 35 U.S.C. 103 should be removed, (Emphasis added, Remarks, page 6-7).
With respect to the rejection of claim(s) 1-3, 5-11, and 13-17 under 35 U.S.C. 103 over Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1), Applicant’s arguments have been considered but they are not persuasive. While Xu may not explicitly use the term “ambiguity,” the reference clearly teaches the functional equivalent of a distance-based uncertainty threshold. Xu’s multi-camera system defines specific detection ranges (e.g., Fig. 2 distance thresholds 231/232) that demarcate where road-boundary location estimates remain reliable versus where visual estimation quality degrades. A person of ordinary skill in the art would readily understand that this degradation of location reliability with increasing distance is precisely an increase in “uncertainty,” which the present claim defines as “distance ambiguity.” Thus, the distinction between high-reliability (low-ambiguity) and low-reliability (high-ambiguity) regions is in Xu’s disclosure (See Paragraph [0029], Paragraph [0032]-[0033], and Paragraph [0037], and where Terazawa discloses in Paragraph [0074] and Paragraph [0081]), and the absence of the precise term “ambiguity” does not negate the fact that Xu teaches the same underlying phenomenon of distance-dependent uncertainty that forms the basis of the claimed ambiguity threshold.
Furthermore, Terazawa explicitly discloses that recognition accuracy for road-boundary detection decreases as distance or visibility deteriorates, and that recognition decisions are made by comparing this accuracy to a threshold (see Figure 6 – 7). Recognition accuracy is directly tied to the certainty with which the location of a boundary point can be determined. When accuracy falls below the threshold, the uncertainty (i.e., ambiguity – exceeds an acceptable level). Therefore, Terazawa’s threshold serves the same functional purpose as the claimed “ambiguity threshold,” regardless of its stated application to environmental judgment (See Paragraph [0113] – [0117], Paragraph [0073] – [0079], and Paragraph [0080] – [0081]). Under a broad but reasonable interpretation, a person of ordinary skill would understand Terazawa’s disclosure to teach a distance and condition dependent uncertainty model fully aligned with the claimed ambiguity concept. As a result, the argued features are written such that they read upon the cited references. Therefore, the previous rejection still applies.
In regards to Argument(s) 3, Applicant(s) state(s) that, Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1) does not disclose/teach/suggest on the amended claim(s) “estimating, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; wherein the angular constraints are based on physical limitations regarding road boundaries”, therefore, the rejection of 35 U.S.C. 103 should be removed, (Emphasis added, Remarks, page 6-7).
However, Applicant’s arguments have been considered but are moot in view of the new ground(s) of rejection in view of Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1), further in view of Parikh et al (US 2022/0196797 A1).
Office Action Summary
Claim(s) 1-3, 5-11, and 13-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1), further in view of Parikh et al (US 2022/0196797 A1).
Claim(s) 4 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1) and Parikh et al (US 2022/0196797 A1), further in view of Gan et al (US 2021/0080267 A1).
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) 1-3, 5-11, and 13-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1), further in view of Parikh et al (US 2022/0196797 A1).
Regarding claim(s) 1 and 9, Xu teaches a non-transitory computer readable medium for detecting a road-boundary of a road based on radar information and visual information (Figure 1; Paragraph [0019]: “Computing device 100 includes one or more processor(s) 102, one or more memory device(s) 104 […] one or more Input/Output (I/O) device(s) 110 […]”; and Paragraph [0022]: “Example I/O device(s) 110 include cursor control devices […] cameras, lenses, radars, CCDs or other image capture devices, and the like”), the non- transitory computer readable medium stores instructions for:
estimating, based on the visual information obtained by a visual sensor, and locations of road-boundary points up to a first distance from the visual sensor of a vehicle (Figure 2; Paragraph [0026]: “Roadway environment 200 includes vehicle 201, such as, for example, a car, a truck, or a bus. Vehicle 201 may or may not contain any occupants, such as, for example, one or more passengers. Roadway environment 200 can include roadway markings (e.g., lane boundaries), pedestrians, bicycles, other vehicles, signs, or any other types of objects. Vehicle 201 can be moving within roadway environment 200, such as, for example, driving on a road”; Paragraph [0029]: “Cameras 211A and 211B can be similar types, or even the same type, of camera. Cameras 211A and 211B have fields-of-view 216A and 216B respectively […] cameras 211A and 211B respectively can sense roadway environment 200 from vehicle 201 out to approximately distance threshold 231”; and Paragraph [0042]: “Objects within fields-of-view 216A and 216B can be clustered and tracked through image information. Sensor data 214A and 214B can indicate objects being tracked within fields-of-view 216A and 216B”);
wherein the visual information also comprises road-boundary points beyond to the first distance (Paragraph [0031]: “Camera 221 has field-of-view 226. Within field-of-view 226, camera 221 can sense roadway environment 200 from vehicle 201 to beyond distance threshold 232”; Paragraph [0044]: “camera 221 operates in LIDAR mode to sense sensor data 224 from an area beyond distance threshold 232 within field-of-view 226. Beyond distance threshold 232, objects can be tracked based on three-dimensional (3D) point clouds”; and Paragraph [0036]: “[…] Perception algorithm 202 can process camera sensor data to identify objects of interest within roadway environment 200. Perception algorithm 202 can also classify objects of interest within roadway environment 200”);
determining the shape and position of the road-boundary based on the locations of the road-boundary points within the first range distance (Paragraph [0036] – Paragraph [0037]: “perception algorithm 202 is configured to fuse sensor data from different cameras (and possibly other sensors) into a view of roadway environment 200. Perception algorithm 202 can process camera sensor data to identify objects of interest within roadway environment 200. Perception algorithm 202 can also classify objects of interest within roadway environment 200 [...] Perception algorithm 202 can also determine the location of an object within roadway environment 200, such as, for example, between vehicle 201 and distance threshold 231, between distance threshold 231 and distance threshold 232, or beyond distance threshold 232. If an object is moving, perception algorithm 202 can also determine a likely path of the object”).
Xu fails to teach wherein a distance ambiguity of visual based location determination of road-boundary points with the first distance range does not exceed an ambiguity threshold; wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds the ambiguity threshold; wherein a distance ambiguity of visual based location determination of a road-boundary point is an uncertainty associated with a determining of a location of the road-boundary point; estimating, based at least on (i) the radar information, and (ii) angular- constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; wherein the angular constraints are based on physical limitations regarding road boundaries.
However, Terazawa teaches wherein a distance ambiguity of visual based location determination of road-boundary points with the first distance range does not exceed an ambiguity threshold (Paragraph [0080] – Paragraph [0081]: “The adverse environment determination unit F6 is configured to determine whether the surrounding environment of the subject vehicle corresponds to an environment that may reduce the performance or accuracy of the object recognition […] the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold […]”; Examiner’s Note: comparing an accuracy related value to a threshold to classify environments, where reduced recognition accuracy beyond a certain distance effectively corresponds to ambiguity exceeding a threshold, while within that distance ambiguity does not exceed the threshold);
wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds the ambiguity threshold (Paragraph [0081]: “the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold”);
wherein a distance ambiguity of visual based location determination of a road-boundary point is an uncertainty associated with a determining of a location of the road-boundary point (Paragraph [0116] – Paragraph [0117]: “the process may determine whether the estimation error is within a predetermined allowable range. That is, the estimation error may also be included in the evaluation value of recognition accuracy […] An upper limit of allowable range set for the estimation error (hereinafter referred to as error threshold Pth) may be set to 0.5 meters or 1 meter as an example”);
Therefore, it would have been obvious to one of ordinary skill in the art to combine Xu and Terazawa before the effective filing date of the claimed invention. The motivation for this combination of references would have been to improve reliability assessment of Xu’s visual boundary determination by explicitly quantifying ambiguity/uncertainty and applying a threshold, with a reasonable expectation of success, since Terazawa teaches exactly such uncertainty quantification for visual recognition systems. This motivation for the combination of Xu and Terazawa is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Xu and Terazawa fails to teach estimating, based at least on (i) the radar information, and (ii) angular- constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; wherein the angular constraints are based on physical limitations regarding road boundaries.
However, Parikh teaches to estimating, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range (Paragraph [0022]: “vehicle 100 comprises a number of sensors including radar sensors 105, camera sensors 107 […]”; Paragraph [0036] – Paragraph [0037]: “Curve radius 301 may advantageously be calculated utilizing SR data alone […] The estimated widths and orientation of the road can then be compared to known dimensions of regulated road construction to estimate curve radius 301 […] Utilizing the SR data and curve radius 301, vehicle 100 may generate a refined RST 315 that provides a path to traverse road surface 300 through the curved segment of the highway […]”);
wherein the angular constraints are based on physical limitations regarding road boundaries (Paragraph [0003]: “generating a refined RST based upon the sensor data, lane position, curve radius, and a lookup table of road curvature data”; Paragraph [0036]: “the SR data may be utilized to estimate an orientation of each of the estimated widths 309 as well. The estimated widths and orientation of the road can then be compared to known dimensions of regulated road construction to estimate curve radius 301”; and Paragraph [0038]: “a lookup table comprising historical data of successful turns on roads having similar dimensions and configurations […] the lookup table may be populated with RST data derived from previously-captured SR data”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine the visual-based boundary estimation and ambiguity-thresholding of Xu and Terazawa with the radar-based boundary estimation and roadway-geometry constraints taught by Parikh. Xu and Terazawa collectively recognize that visual estimation becomes ambiguous beyond a certain distance threshold, while Parikh teaches radar-based estimation of road boundaries and curve geometry that is robust at longer distances and constrained by the physical limitations of roadway curvature. Therefore, a person of ordinary skill would have been motivated to supplement ambiguous long-range visual boundary estimation in Xu with radar-based estimation and angular/curvature constraints as taught by Parikh, in order to improve accuracy and robustness of boundary detection beyond the visual reliable range, with a reasonable expectation of success. This motivation for the combination of Xu, Terazawa and Parikh is/are supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim(s) 2 and 10, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, where Terazawa teaches wherein the estimating of the locations of the road-boundary points outside the first distance is executed in an iterative manner (Paragraph [0113]: “In S7, the recognition accuracy evaluation unit F5 acquires information on recognition accuracy. For example, the recognition accuracy evaluation unit F5 acquires a reliability of object recognition from the front camera 11, and the process proceeds to S8. In S8, the process determines whether the evaluation value of recognition accuracy of the front camera 11 is within a predetermined allowable range. For example, the process may determine whether the reliability acquired in S7 is equal to or higher than a predetermined threshold. The reliability of object recognition corresponds to the evaluation value of recognition accuracy. When the reliability is equal to or higher than the predetermined threshold, the recognition accuracy is considered to be within the allowable range, and the process proceeds to S9. When the reliability is less than the predetermined threshold, the recognition accuracy is considered to be out of the allowable range, and the processes returns to S3 and repeats S3 and the subsequent process”).
Regarding claim(s) 3 and 11, Xu as modified by Terazawa and Parikh teaches the method according to claim 2, where Terazawa teaches wherein the iterative manner starts from the first distance (Claim(s) 2; Paragraph [0113]; and Paragraph [0139]: “After the lane change to the traveling lane is completed, the process proceeds to S104. Completion of movement to the traveling lane can be determined based on the recognition result of the front camera 11, for example, when the ego lane ID is changed to 1 or the like. In S104, the process outputs a deceleration request signal to the driving assist ECU 30, and the process is ended. The deceleration request signal may be output repeatedly until the recognition accuracy reaches an allowable level”).
Regarding claim(s) 5 and 13, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, where Xu teaches wherein the first distance does not exceed few tens of meters (Paragraph [0034]: “In one aspect, distance threshold 231 is approximately 20 meters from vehicle 201 and distance threshold 232 is approximately 100 meters from vehicle 201. However, other distances for distance thresholds 231 and 232 are also possible. For example, distance threshold 231 can range from 0-20 meters and distance threshold 232 can range from 20-200 meters”).
Regarding claim(s) 6 and 14, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, where Terazawa teaches wherein the estimating of the locations of road-boundary points outside the first distance range is also based on visual information about locations of road-boundary points outside the first distance range (Figure 2; Figure 12; Figure 13; Paragraph [0037]: “[…] The landmark may include a streetlight, a mirror, a utility pole, a commercial advertisement signboard, a signboard indicating a store name, an iconic building such as a historic building, or the like. The pole may include a streetlight or a utility pole. The landmark may include an uneven portion or a cave-in portion of a road, a manhole, a joint portion, or the like. An end point or a branch point of the lane boundary line may be used as the landmark [...]”; and Paragraph [0167]: “The driving assist system 1 may include multiple camera elements having different view angles as the front camera 11 [...] The middle range camera 11a has a view angle of about 50 degrees, and includes a lens capable of capturing an image up to a distance of, for example, 150 meters. The telephoto camera 11b has a relatively narrow view angle so as to be able to capture an image of a farther distance than the middle range camera 11a. For example, the telephoto camera 11b has a view angle within a range of 30 degrees to 40 degrees, and is capable of capturing an image up to a distance of 250 meters or farther. The wide angle camera 11c captures images within a wide area around the vehicle. The wide angle camera 11c has a view angle within a range of, for example, 120 degrees to 150 degrees, and is capable of capturing an image within 50 meters ahead of the vehicle”).
Regarding claim(s) 7 and 15, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, comprising responding to the determining of the shape and position of the road-boundary (Paragraph [0036] – Paragraph [0037]: “perception algorithm 202 is configured to fuse sensor data from different cameras (and possibly other sensors) into a view of roadway environment 200. Perception algorithm 202 can process camera sensor data to identify objects of interest within roadway environment 200. Perception algorithm 202 can also classify objects of interest within roadway environment 200 [...] Perception algorithm 202 can also determine the location of an object within roadway environment 200, such as, for example, between vehicle 201 and distance threshold 231, between distance threshold 231 and distance threshold 232, or beyond distance threshold 232. If an object is moving, perception algorithm 202 can also determine a likely path of the object”).
Regarding claim(s) 8 and 16, Xu as modified by Terazawa and Parikh teaches the method according to claim 7, where Terazawa teaches wherein the responding comprises validating road-boundary information about the determining the shape and position of the road-boundary based on a map of an environment of the vehicle (Paragraph [0052]: “The high accuracy map data corresponds to map data indicating a road structure, a position coordinate of a planimetric feature disposed along the road and the like with an accuracy that can be used in the autonomous driving. For example, the high accuracy map data includes three-dimensional shape data of the road, lane data, or planimetric feature data. For example, the above-described three-dimensional shape data of the road may include node data related to a point (hereinafter, referred to as node) at which multiple roads intersect, merge, or branch, and link data related to a road connecting the points (hereinafter, referred to as link)”).
Regarding claim(s) 17, Xu teaches a system that comprises a processor (Figure 1; Paragraph [0019]; and Paragraph [0022]) that is configured to:
estimate, based on the visual information obtained by a visual sensor of a vehicle, locations of road-boundary points up to a first distance from the visual sensor Figure 2; Paragraph [0026]: “Roadway environment 200 includes vehicle 201, such as, for example, a car, a truck, or a bus. Vehicle 201 may or may not contain any occupants, such as, for example, one or more passengers. Roadway environment 200 can include roadway markings (e.g., lane boundaries), pedestrians, bicycles, other vehicles, signs, or any other types of objects. Vehicle 201 can be moving within roadway environment 200, such as, for example, driving on a road”; Paragraph [0029]: “Cameras 211A and 211B can be similar types, or even the same type, of camera. Cameras 211A and 211B have fields-of-view 216A and 216B respectively […] cameras 211A and 211B respectively can sense roadway environment 200 from vehicle 201 out to approximately distance threshold 231”; and Paragraph [0042]: “Objects within fields-of-view 216A and 216B can be clustered and tracked through image information. Sensor data 214A and 214B can indicate objects being tracked within fields-of-view 216A and 216B”);
determine the shape and position of the road-boundary of a road based on the locations of the road-boundary points within the first range distance (Paragraph [0036] – Paragraph [0037]: “perception algorithm 202 is configured to fuse sensor data from different cameras (and possibly other sensors) into a view of roadway environment 200. Perception algorithm 202 can process camera sensor data to identify objects of interest within roadway environment 200. Perception algorithm 202 can also classify objects of interest within roadway environment 200 [...] Perception algorithm 202 can also determine the location of an object within roadway environment 200, such as, for example, between vehicle 201 and distance threshold 231, between distance threshold 231 and distance threshold 232, or beyond distance threshold 232. If an object is moving, perception algorithm 202 can also determine a likely path of the object”).
Xu fails to teach wherein a distance ambiguity of visual based location determination of road- boundary points with the first distance range does not exceed ambiguity threshold; wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds ambiguity threshold; wherein a distance ambiguity of visual based location determination of a road-boundary point is an uncertainty associated with a determining of a location of the road-boundary point; dynamically determining the ambiguity threshold thereby dynamically determining the first distance; estimate, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; wherein the angular constraints are based on physical limitations regarding road boundaries; dynamically determine the ambiguity threshold thereby dynamically determining the first distance.
However, Terazawa teaches wherein a distance ambiguity of visual based location determination of road-boundary points with the first distance range does not exceed ambiguity threshold (Paragraph [0080] – Paragraph [0081]: “The adverse environment determination unit F6 is configured to determine whether the surrounding environment of the subject vehicle corresponds to an environment that may reduce the performance or accuracy of the object recognition […] the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold […]”; Examiner’s Note: comparing an accuracy related value to a threshold to classify environments, where reduced recognition accuracy beyond a certain distance effectively corresponds to ambiguity exceeding a threshold, while within that distance ambiguity does not exceed the threshold);
wherein a distance ambiguity of visual based location determination of road-boundary points outside the first distance exceeds ambiguity threshold (Paragraph [0081]: “the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold”);
wherein a distance ambiguity of visual based location determination of a road-boundary point is an uncertainty associated with a determining of a location of the road-boundary point (Paragraph [0116] – Paragraph [0117]: “the process may determine whether the estimation error is within a predetermined allowable range. That is, the estimation error may also be included in the evaluation value of recognition accuracy […] An upper limit of allowable range set for the estimation error (hereinafter referred to as error threshold Pth) may be set to 0.5 meters or 1 meter as an example”);
dynamically determining the ambiguity threshold thereby dynamically determining the first distance (Paragraph [0074]: “The effective recognition distance is a parameter that varies due to external factors such as fog, rainfall, or afternoon sun […]”; Paragraph [0075] – Paragraph [0076]: “The recognition accuracy evaluation unit F5 may calculate the effective recognition distance based on the farthest recognition distance […] an average value, a maximum value, or a second largest value of the multiple farthest recognition distances may be set as the effective recognition distance […]”; Paragraph [0081]: “[…] determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold”; and Paragraph [0089] – Paragraph [0090]: “the adverse environment level determination unit F62 may evaluate a level of the adverse environment, in other words, a level of deterioration in object recognition performance executed based on the image frame […] The first distance may be the same value (25 meters) as the distance threshold described above. The second distance is set shorter than the first distance […]”);
Therefore, it would have been obvious to one of ordinary skill in the art to combine Xu and Terazawa before the effective filing date of the claimed invention. The motivation for this combination of references would have been to improve reliability assessment of Xu’s visual boundary determination by explicitly quantifying ambiguity/uncertainty and applying a threshold, with a reasonable expectation of success, since Terazawa teaches exactly such uncertainty quantification for visual recognition systems. Furthermore, Xu’s system to include dynamically determining the ambiguity (or distance) threshold based on recognition performance or environmental conditions as taught by Terazawa, and thereby dynamically determine the first distance. Doing so would merely constitute the predictable use of prior art techniques to improve Xu’s system by adaptively setting threshold distance in view of changing sensing accuracy and environmental conditions, in order to enhance robustness and reliability of boundary detection. This motivation for the combination of Xu and Terazawa is supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Xu and Terazawa fails to teach to estimate, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range; wherein the angular constraints are based on physical limitations regarding road boundaries.
However, Parikh teaches to estimate, based at least on (i) the radar information, and (ii) angular-constrains regarding angular relationships between adjacent road-boundary points, locations of road-boundary points outside the first distance range (Paragraph [0022]: “vehicle 100 comprises a number of sensors including radar sensors 105, camera sensors 107 […]”; Paragraph [0036] – Paragraph [0037]: “Curve radius 301 may advantageously be calculated utilizing SR data alone […] The estimated widths and orientation of the road can then be compared to known dimensions of regulated road construction to estimate curve radius 301 […] Utilizing the SR data and curve radius 301, vehicle 100 may generate a refined RST 315 that provides a path to traverse road surface 300 through the curved segment of the highway […]”);
wherein the angular constraints are based on physical limitations regarding road boundaries (Paragraph [0003]: “generating a refined RST based upon the sensor data, lane position, curve radius, and a lookup table of road curvature data”; Paragraph [0036]: “the SR data may be utilized to estimate an orientation of each of the estimated widths 309 as well. The estimated widths and orientation of the road can then be compared to known dimensions of regulated road construction to estimate curve radius 301”; and Paragraph [0038]: “a lookup table comprising historical data of successful turns on roads having similar dimensions and configurations […] the lookup table may be populated with RST data derived from previously-captured SR data”).
Therefore, it would have been obvious to one of ordinary skill in the art to combine the visual-based boundary estimation and ambiguity-thresholding of Xu and Terazawa with the radar-based boundary estimation and roadway-geometry constraints taught by Parikh. Xu and Terazawa collectively recognize that visual estimation becomes ambiguous beyond a certain distance threshold, while Parikh teaches radar-based estimation of road boundaries and curve geometry that is robust at longer distances and constrained by the physical limitations of roadway curvature. Therefore, a person of ordinary skill would have been motivated to supplement ambiguous long-range visual boundary estimation in Xu with radar-based estimation and angular/curvature constraints as taught by Parikh, in order to improve accuracy and robustness of boundary detection beyond the visual reliable range, with a reasonable expectation of success. This motivation for the combination of Xu, Terazawa and Parikh is/are supported by KSR exemplary rationale (G) Some teaching, suggestion, or motivation in the prior art that would have led one of ordinary skill to modify the prior art reference or to combine prior art reference teachings to arrive at the claimed invention. MPEP 2141 (III).
Regarding claim(s) 18, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, where Terazawa teaches comprising dynamically determining the ambiguity threshold thereby dynamically determining the first distance (Paragraph [0074]: “The effective recognition distance is a parameter that varies due to external factors such as fog, rainfall, or afternoon sun […]”; Paragraph [0075] – Paragraph [0076]: “The recognition accuracy evaluation unit F5 may calculate the effective recognition distance based on the farthest recognition distance […] an average value, a maximum value, or a second largest value of the multiple farthest recognition distances may be set as the effective recognition distance […]”; Paragraph [0081]: “[…] determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold”; and Paragraph [0089] – Paragraph [0090]: “the adverse environment level determination unit F62 may evaluate a level of the adverse environment, in other words, a level of deterioration in object recognition performance executed based on the image frame […] The first distance may be the same value (25 meters) as the distance threshold described above. The second distance is set shorter than the first distance […]”).
Regarding claim(s) 19, Xu as modified by Terazawa and Parikh teaches method according to claim 18, where Terazawa teaches wherein the dynamically determining of the ambiguity threshold is based on a current visibility of an environment of the vehicle (Paragraph [0074] – Paragraph [0076]: “The effective recognition distance is a parameter that varies due to external factors such as fog, rainfall, or afternoon sun, unlike a designed recognition limit distance[…]”; and Paragraph [0080] – Paragraph [0081]: “The adverse environment determination unit F6 is configured to determine whether the surrounding environment of the subject vehicle corresponds to an environment that may reduce the performance or accuracy of the object recognition […] the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold […]”).
Regarding claim(s) 20, Xu as modified by Terazawa and Parikh teaches the method according to claim 18, where Terazawa teaches wherein the dynamically determining of the ambiguity threshold is based on an angle of an optical axis of the visual sensor to the road (Paragraph [0034]: “The front camera 11 captures images of a front area of vehicle at a predetermined angle of view […] disposed, for example, at an upper end portion of a front windshield in a vehicle compartment, a front grille, or a roof top […]”; Paragraph [0074] – Paragraph [0076]: “The effective recognition distance is a parameter that varies due to external factors such as fog, rainfall, or afternoon sun, unlike a designed recognition limit distance[…]”; and Paragraph [0080] – Paragraph [0081]: “The adverse environment determination unit F6 is configured to determine whether the surrounding environment of the subject vehicle corresponds to an environment that may reduce the performance or accuracy of the object recognition […] the adverse environment determination unit F6 may determine that the environment is adverse when the effective recognition distance is smaller than a predetermined threshold […]”).
Claim(s) 4 and 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over Xu et al (US 2018/0067487 A1) in view of Terazawa (US 2023/0147535 A1) and Parikh et al (US 2022/0196797 A1), further in view of Gan et al (US 2021/0080267 A1).
Regarding claim(s) 4 and 12, Xu as modified by Terazawa and Parikh teaches the method according to claim 1, but do not specifically teach comprising obtaining a location of a current road-boundary segment; estimating a search region for searching for the next road-boundary segment, based at least in part on the angular-constrains; and searching the next road-boundary segment within the search region.
However, Gan teaches comprising obtaining a location of a current road-boundary segment (Paragraph [0037]: “In an embodiment, it is possible to automatically determine a current location of the present vehicle without the manual input of a user”);
estimating a search region for searching for the next road-boundary segment, based at least in part on the angular-constrains (Paragraph [0037]: “detect a current heading of the vehicle (i.e., a current driving direction). Then, the endpoints included in each road section and the endpoints included in each connecting passage are searched based on the high-precision map, and a road segment of an endpoint which is located within a range where an angle with the current heading is smaller than a preset angle and is closest to the current location of the vehicle is determined as the road segment where the origin is located of the path”); and
searching the next road-boundary segment within the search region (Paragraph [0037]: “detect a current heading of the vehicle (i.e., a current driving direction). Then, the endpoints included in each road section and the endpoints included in each connecting passage are searched based on the high-precision map, and a road segment of an endpoint which is located within a range where an angle with the current heading is smaller than a preset angle and is closest to the current location of the vehicle is determined as the road segment where the origin is located of the path”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date to modify an obtaining a location of a current road-boundary segment, searching for the next road-boundary segment, based at least in part on the angular-constrains and searching the next road-boundary segment within the search region section of Xu, Terazawa, and Parikh to incorporate the use of an obtaining a location of a current road-boundary segment, searching for the next road-boundary segment, based at least in part on the angular-constrains and searching the next road-boundary segment within the search region of Gan and one of ordinary skill in the art would have recognized that the results of the combination were predictable. One could look to Gan to include an obtaining a location of a current road-boundary segment, searching for the next road-boundary segment, based at least in part on the angular-constrains and searching the next road-boundary segment within the search region. According to the above path planning method and device for an unmanned vehicle, an exit endpoint of a previous road section of each connecting passage of a final planned path is an exit endpoint of a lane of which the attribute category is matched with the attribute category of the connecting passage in the road section. It can be seen that when an unmanned vehicle drives in the final generated path, the unmanned vehicle can be driven from a road section to a connecting passage connected thereto through a lane obeying traffic rules. Therefore, the unmanned vehicle is enabled to obey traffic rules and can be driven safely.
Relevant Prior Art Directed to State of Art
Takamatsu et al (US 2016/0090084 A1) are relevant prior art not applied in the rejection(s) above. Takamatsu discloses a method of assisting a driver of a vehicle in driving a road, the method comprising: determining a location of a road boundary relative to the vehicle using a sensor; selecting, via a controller, a parameter to assist a driver of the vehicle at the location of the road boundary; updating the parameter based on a previous operation of the vehicle; determining, via the controller, whether the vehicle is approaching the road boundary based on a vehicle trajectory and the location of a road boundary; and providing a feedback operation to assist the driver in avoiding the road boundary, the feedback operation based on the selected parameter.
Ishimaru et al (US 2023/0122011 A1) are relevant prior art not applied in the rejection(s) above. Ishimaru discloses a vehicle position estimation device comprising: a road edge information acquisition unit acquiring a distance from a subject vehicle to a road edge using at least one of an imaging device or a distance measuring sensor, the imaging device capturing images of a predetermined range around the subject vehicle, the distance measuring sensor detecting an object existing in a predetermined direction relative to the subject vehicle by transmitting a probe wave or a laser beam; a map acquisition unit acquiring map information including a lane quantity of a traveling road of the subject vehicle from a map storage disposed inside or outside of the subject vehicle; a boundary line information acquisition unit acquiring position information of lane boundary lines detected by analyzing the images captured by the imaging device; a roadside area width calculation unit calculating, as a roadside area width, a lateral direction distance between an outermost detection line, which is an outermost boundary line among the detected boundary lines, and the road edge; and a traveling lane specification unit specifying a traveling lane of the subject vehicle, in which the subject vehicle is traveling, based on (i) the distance from the subject vehicle to the road edge, (ii) the roadside area width, and (iii) the lane quantity included in the map information acquired by the map acquisition unit.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 JONGBONG NAH whose telephone number is (571)272-1361. The examiner can normally be reached M - F: 7:30am - 4:30pm.
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, Edward Urban can be reached on 571-272-7899. 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.
/JONGBONG NAH/Examiner, Art Unit 2674
/ONEAL R MISTRY/Supervisory Patent Examiner, Art Unit 2674