DETAILED ACTION
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 .
Status of Claims
Claims 1-20 of U.S. Application No. 18/520138 filed on 01/02/2026 have been examined.
Office Action is in response to the Applicant's amendments and remarks filed01/02/2026. Claims 1, 4, 11, & 14 are presently amended. Claims 1-20 are presently pending and are presented for examination.
Response to Arguments
In regards to the previous rejection under 35 U.S.C. § 102: Applicants amendments overcome the previous rejection under 35 U.S.C. § 102. Therefore the previous rejection under 35 U.S.C. § 102 is withdrawn.
In regards to the previous rejection under 35 U.S.C. § 103: Applicant argues that the prior art does not disclose the limitation “based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determine a reliability value associated with information on the object”. Applicant further argues on pages. 7-9, “First, Taylor fails to disclose "based on the object not belonging to any pre-classified type ... determine a reliability value associated with information on the object" of claim 1. The Office Action alleges that the "confidence level" as described in Taylor corresponds to the "reliability value" of claim 1 (Office Action, pp. 3-4). In particular, Taylor states the following regarding its "confidence level"…However, Taylor is silent about its "confidence level" being "based on the object not belonging to any pre-classified type" as claim 1 requires. Even though Taylor describes that "various autonomous driving systems perform object and/or hazard detection by consuming sensor input to classify an object" (Taylor, paragraph [0076]), and that "issues may arise when objects are present that are not within one of the preprogrammed classification categories" (Taylor, id), Taylor fails to disclose that the determination of its "confidence level" is "based on the object not belonging to any pre-classified type."… However, Alazem's "RCS values" and "RCS variance metrics" are distinct from Taylor's "confidence level associated with a likelihood that a hazard exists within the bounding area." Further, even if combined, Alazem fails to cure the deficiencies of Taylor discussed above. Thus, the alleged combination fails to disclose or suggest at least "based on the object not belonging to any pre- classified type and based on whether the object is in contact with a road surface, determine a reliability value associated with information on the object," as recited in present claim 1. Further, Warshauer-Baker, Djuric, Prediger, and Jiang, either alone or in combination, fail to cure the deficient disclosure of Taylor and Alazem. In particular, Alazem explains that "the RCS classifier 102 may classify the object 110 into one of two broad categories, corresponding to road surface features (e.g., objects with no height or a minimal height profile) that can be safely driven over by the vehicle 108, and non-road surface features ( e.g., objects with non-trivial height) that cannot be safely driven over by the vehicle 108" (Alazem, paragraph [0031 ]). While Alazem' s categorization relies on the "height" of each object ( e.g., "no height," "minimal height," "nontrivial height," etc.), Alazem is silent about "based on whether the object is in contact with a road surface, determin[ing] a reliability value" as present claim 1 recites. For example, Alazem cites "manhole cover, storm drain, road expansion joint, road safety feature, pothole, etc." as its first category of objects (i.e., "road surface features") and cites "pedestrian, sign, traffic cone, road debris, etc." as its second category of objects (i.e., "non-road surface features"), but the both categories include objects that are presumably in contact with a road surface, at least including, for example, manhole cover, storm drain, road expansion joint, road safety feature, pothole, pedestrian, traffic cone, road debris, etc ..”. Examiner respectfully disagrees. Applicant is reminded claims must be given their broadest reasonable interpretation. The prior art Taylor is incorporated to disclose the idea of detecting unclassified hazards for a driver assistance system of a vehicle. So Taylor is strictly for detecting unclassified hazards if it is not able to classify the hazard as some type of object (see at least Taylor, para. [0076]). Further while detecting the objects and obstacles on the road, Taylor is able to determine a confidence associated with a likelihood that a hazard exists within the bounding area (See at least Taylor, para. [0071]). The bounding area is adjusted to specify or hone in on the object in order to further increase and/or decrease the confidence the hazard actually exists or not. Therefore the confidence is associated with the hazard and the vehicle acts accordingly to the confidence level (see at least Taylor, para. [0072-0074]). Further Alazem is further incorporated to teach the idea of using radar cross section data to classify objects in driving environments. Alazem is able to classify objects based on the objects profile and is able to recognize if the vehicle is able to drive over the object or not based on the classification if the object is a road-surface object or non-road surface object (see at least Alazem, para. [0031]). Further the objects that are included in a non-road surface object include a traffic signs which also include traffic signs (that include low hanging traffic lights), animals (that include birds that fly low), road debris (includes hanging electric lines and/or hanging branches), and all these non-road surface objects are objects that are able to be detected and not contact the surface of the road and still would force a vehicle to shift its path to avoid collision or downtime (see at least Alazem, para. [0074-0075]). In view of the arguments above, the 103 rejection is maintained.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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, 11-12, & 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2024/0409125A1 (“Taylor”), in view of US 2023/0242149A1 (“Alazem”).
As per claim 1 Taylor discloses
An apparatus for controlling an autonomous vehicle (see at least Taylor, para. [0036]: In autonomous vehicle control system 100 determines a plan for autonomously operating a vehicle 10 along a route in a manner that accounts for unclassified objects or obstacles detected by onboard sensors 28, 40, as described in greater detail below.), the apparatus comprising:
a sensor configured to detect an object (see at least Taylor, para. [0036]: In this regard, a control module onboard the vehicle 10 calibrates different types of onboard sensors 28, 40 with respect to one another and/or the vehicle 10, thereby allowing data from those different types of onboard sensors 28, 40 to be spatially associated or otherwise with one another based on the calibration for purposes of object detection…);
a processor; and memory storing instructions that, when executed by the processor, cause the apparatus to (see at least Taylor, para. [0043]: The controller 34 includes at least one processor 44, a communication bus 45, and a computer readable storage device or media 46. …):
determine whether the object belongs to any pre-classified type (see at least Taylor, para. [0076]:For example, various autonomous driving systems perform object and/or hazard detection by consuming sensor input to classify an object. While useful in many situations, classifying objects may require specific sensors and/or may require significant computational resources. Furthermore, issues may arise when objects are present that are not within one of the preprogrammed classification categories.);
based on the object not belonging to any pre-classified type, determine a reliability value associated with information on the object (see at least Taylor, para. [0060]: In various embodiments, the hazard detection module 214 receives as input the bounding area data 226 generated by the bounding area module 212. The hazard detection module 214 dynamically determines a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. & para. [0071]: At 322, the method 300 may include determining a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. Depending on the quantity of the radar objects within the bounding area and/or a grouping of the radar objects within the bounding area, the confidence level may be increased or decreased dynamically.); and
control, based on the reliability value being greater than a threshold reliability value, a vehicle to avoid the object (see at least Taylor, para. [0072-0074]: In various embodiments, the lane score may increase exponentially. For example, the lane score may increase at an increasing rate in response to, for example, a persistence of the confidence level. In various embodiments, the lane score may decrease or decay at a predetermined rate over time in response to, for example, a decrease in the persistence of the confidence level, rather than decreasing in a sharp drop or a step change manner….At 330, the lane score may be compared to a preprogramed lane score threshold. At 332, the method 300 may include suspending or preventing a lane change maneuver in response to the lane score exceeding the lane score threshold. At 334, the method 300 may include enabling or allowing a lane change maneuver in response to the lane score being less than the lane score threshold. The method 300 may end at 336. [Examiner Note: the control avoids the adjacent lane by suspending the lane change because the confidence score is high and meaning there is an unknown hazard in the adjacent lane.]).
However Taylor does not explicitly disclose
based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determine a reliability value associated with information on the object.
Alazem teaches
based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determine a reliability value associated with information on the object (see at least Alazem, para. [0074-0075]: In some instances, and in general, the perception component 522 can include functionality to perform object detection, segmentation, and/or classification. In some examples, the perception component 522 can provide processed sensor data that indicates a presence of an object that is proximate to the vehicle 502 and/or a classification of the object as an object type (e.g., car, pedestrian, cyclist, animal, building, tree, road surface, curb, sidewalk, stoplight, stop sign, unknown, etc.)…The RCS classifier(s) 524, which may be implemented within the perception component 522,may include any of the components described herein configured to perform one or more object detection and/or classification functionalities. In some examples, the RCS classifier(s) 524 may be similar or identical to the RCS classifier 302 described above. For example, RCS classifier(s) 524 may include one or more of an RCS variance analyzer 304, an object classifier 306, and/or object profiles data store 322. These components may be used in combination to analyze the received radar data associated with an object, determine the variance of the RCS data associated with the object, and classify the object as an object as a road surface feature or a non-road surface feature object.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determine a reliability value associated with information on the object of Alazem, with a reasonable expectation of success, in order to classify objects more efficiently and accurately while navigating a driving environment (see at least Alazem, para. [0010]).
As per claim 11 Taylor discloses
A method for controlling an autonomous vehicle (see at least Taylor, para. [0005]), the method comprising:
determining whether an object acquired by a sensor of a vehicle belongs to any pre-classified type (see at least Taylor, para. [0036]: In this regard, a control module onboard the vehicle 10 calibrates different types of onboard sensors 28, 40 with respect to one another and/or the vehicle 10, thereby allowing data from those different types of onboard sensors 28, 40 to be spatially associated or otherwise with one another based on the calibration for purposes of object detection…para. [0076]:For example, various autonomous driving systems perform object and/or hazard detection by consuming sensor input to classify an object. While useful in many situations, classifying objects may require specific sensors and/or may require significant computational resources. Furthermore, issues may arise when objects are present that are not within one of the preprogrammed classification categories.);
based on the object not belonging to any pre-classified type, determining a reliability value associated with information on the object (see at least Taylor, para. [0060]: In various embodiments, the hazard detection module 214 receives as input the bounding area data 226 generated by the bounding area module 212. The hazard detection module 214 dynamically determines a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. & para. [0071]: At 322, the method 300 may include determining a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. Depending on the quantity of the radar objects within the bounding area and/or a grouping of the radar objects within the bounding area, the confidence level may be increased or decreased dynamically.); and
controlling, based on the reliability value being greater than a threshold reliability value, the vehicle to avoid the object (see at least Taylor, para. [0072-0074]: In various embodiments, the lane score may increase exponentially. For example, the lane score may increase at an increasing rate in response to, for example, a persistence of the confidence level. In various embodiments, the lane score may decrease or decay at a predetermined rate over time in response to, for example, a decrease in the persistence of the confidence level, rather than decreasing in a sharp drop or a step change manner….At 330, the lane score may be compared to a preprogramed lane score threshold. At 332, the method 300 may include suspending or preventing a lane change maneuver in response to the lane score exceeding the lane score threshold. At 334, the method 300 may include enabling or allowing a lane change maneuver in response to the lane score being less than the lane score threshold. The method 300 may end at 336. [Examiner Note: the control avoids the adjacent lane by suspending the lane change because the confidence score is high and meaning there is an unknown hazard in the adjacent lane.]).
However Taylor does not explicitly disclose
based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determining a reliability value associated with information on the object.
Alazem teaches
based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determining a reliability value associated with information on the object (see at least Alazem, para. [0074-0075]: In some instances, and in general, the perception component 522 can include functionality to perform object detection, segmentation, and/or classification. In some examples, the perception component 522 can provide processed sensor data that indicates a presence of an object that is proximate to the vehicle 502 and/or a classification of the object as an object type (e.g., car, pedestrian, cyclist, animal, building, tree, road surface, curb, sidewalk, stoplight, stop sign, unknown, etc.)…The RCS classifier(s) 524, which may be implemented within the perception component 522,may include any of the components described herein configured to perform one or more object detection and/or classification functionalities. In some examples, the RCS classifier(s) 524 may be similar or identical to the RCS classifier 302 described above. For example, RCS classifier(s) 524 may include one or more of an RCS variance analyzer 304, an object classifier 306, and/or object profiles data store 322. These components may be used in combination to analyze the received radar data associated with an object, determine the variance of the RCS data associated with the object, and classify the object as an object as a road surface feature or a non-road surface feature object.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of based on the object not belonging to any pre-classified type and based on whether the object is in contact with a road surface, determining a reliability value associated with information on the object of Alazem, with a reasonable expectation of success, in order to classify objects more efficiently and accurately while navigating a driving environment (see at least Alazem, para. [0010]).
As per claim 12 Taylor discloses
further comprising: determining the reliability value based on at least one of: a first reliability value determined based on an image acquired by a camera of the sensor, a second reliability value determined based on data acquired by a lidar of the sensor, or a third reliability value determined based on a reflected radio wave received by a radar of the sensor (see at least Taylor, para. [0060]: In various embodiments, the hazard detection module 214 receives as input the bounding area data 226 generated by the bounding area module 212. The hazard detection module 214 dynamically determines a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time.).
As per claim 14 Taylor does not explicitly disclose
wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar.
Alazem teaches
wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar (see at least Alazem, para. [0029]: Conversely, if the determined RCS variance is below the variance threshold, the RCS data may indicate an absence of multipath fading, further indicating that the object 110 does not have a significant height. para. [0031]: In some examples, the RCS classifier 102 may classify the object 110 into one of two broad categories, corresponding to road surface features (e.g., objects with no height or a minimal height profile) that can be safely driven over by the vehicle 108, and non-road surface features (e.g., objects with non-trivial height) that cannot be safely driven over by the vehicle 108. In other examples, the RCS classifier 102 may determine more a specific object classification representing the type of the road surface feature (e.g., manhole cover, storm drain, road expansion joint, road safety feature, pothole, etc.), and/or the type of the none road surface feature (e.g., pedestrian, sign, traffic cone, road debris, etc.).& para. [0051]: In some examples, determining an object classification may be based on the variance of the RCS radar data associated with the object, using the various techniques described herein, in conjunction with object classification based on other types of sensor data (e.g., lidar data, image data, sonar data, etc.) and/or map data. For instance, an object classification determined by the object classifier 306 based on RCS variance data from the RCS variance analyzer 304 may be used to verify a separate object classification performed by a separate perception subcomponent, or vice versa, to increase the accuracy and confidence levels associated with the object classification.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar of Alazem, with a reasonable expectation of success, in order to classify objects more efficiently and accurately while navigating a driving environment (see at least Alazem, para. [0010]).
Claim(s) 2, 4, 9-10, & 19-20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of US 2020/0034634A1 (“Baker”).
As per claim 2 Taylor discloses
wherein the sensor comprises at least one of a camera, a lidar, or a radar (see at least Taylor, para. [0041]: The sensing devices 40a-40n can include, but are not limited to, radars, lidars, global positioning systems, optical cameras, thermal cameras, ultrasonic sensors, and/or other sensors.).
However Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to determine the reliability value based on at least two of: a first reliability value determined based on an image acquired by the camera, a second reliability value determined based on data acquired by the lidar, or a third reliability value determined based on a reflected radio wave received by the radar.
Baker teaches
wherein the sensor comprises at least one of a camera, a lidar, or a radar, wherein the instructions, when executed by the processor, further cause the apparatus to determine the reliability value based on at least two of: a first reliability value determined based on an image acquired by the camera, a second reliability value determined based on data acquired by the lidar, or a third reliability value determined based on a reflected radio wave received by the radar (see at least Baker, para. [0052-0054]: At 606, using a first object classifier module, first confidence score data is generated by providing the first object classifier module with a first type of the training data (e.g., image data rather than radar scans or lidar scans)…At 608, using a second object classifier module, second confidence score data is generated based upon a second type of the training data (e.g. lidar scans rather than image data or radar scans)…At 610, a Bayesian object classifier system is learned based upon the labeled training data, the first confidence score data, and the second confidence score data, such that the Bayesian object classifier system is fit to the labeled training data and the confidence score data output by the first and second object classifier modules. The methodology 600 completes at 612.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the sensor comprises at least one of a camera, a lidar, or a radar, wherein the instructions, when executed by the processor, further cause the apparatus to determine the reliability value based on at least two of: a first reliability value determined based on an image acquired by the camera, a second reliability value determined based on data acquired by the lidar, or a third reliability value determined based on a reflected radio wave received by the radar of Baker, with a reasonable expectation of success, in order for reducing errors with respect to object type classification (see at least Baker, para. [0003]).
As per claim 4 Taylor does not explicitly disclose
wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar.
Alazem teaches
wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar (see at least Alazem, para. [0029]: Conversely, if the determined RCS variance is below the variance threshold, the RCS data may indicate an absence of multipath fading, further indicating that the object 110 does not have a significant height. para. [0031]: In some examples, the RCS classifier 102 may classify the object 110 into one of two broad categories, corresponding to road surface features (e.g., objects with no height or a minimal height profile) that can be safely driven over by the vehicle 108, and non-road surface features (e.g., objects with non-trivial height) that cannot be safely driven over by the vehicle 108. In other examples, the RCS classifier 102 may determine more a specific object classification representing the type of the road surface feature (e.g., manhole cover, storm drain, road expansion joint, road safety feature, pothole, etc.), and/or the type of the none road surface feature (e.g., pedestrian, sign, traffic cone, road debris, etc.).& para. [0051]: In some examples, determining an object classification may be based on the variance of the RCS radar data associated with the object, using the various techniques described herein, in conjunction with object classification based on other types of sensor data (e.g., lidar data, image data, sonar data, etc.) and/or map data. For instance, an object classification determined by the object classifier 306 based on RCS variance data from the RCS variance analyzer 304 may be used to verify a separate object classification performed by a separate perception subcomponent, or vice versa, to increase the accuracy and confidence levels associated with the object classification.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the second reliability value has a positive correlation with at least one of a height or a width, of the object, determined by the lidar of Alazem, with a reasonable expectation of success, in order to classify objects more efficiently and accurately while navigating a driving environment (see at least Alazem, para. [0010]).
As per claim 9 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, cause the apparatus to control the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction.
Baker teaches
wherein the instructions, when executed by the processor, cause the apparatus to control the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction (see at least Baker, para. [0051]: Further, for instance, when the label indicates that the object isa car and the car is approaching relatively quickly from the left-hand side of the vehicle, the steering system and the braking system can be controlled to slow the autonomous vehicle and veer to the right to ensure that the autonomous vehicle avoids a collision with the car.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, cause the apparatus to control the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction of Baker, with a reasonable expectation of success, in order for reducing errors with respect to object type classification (see at least Baker, para. [0003]).
As per claim 10 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, cause the apparatus to, based on a determination that the object is unavoidable in a lateral direction, decelerate the vehicle based on the reliability value.
Baker teaches
wherein the instructions, when executed by the processor, cause the apparatus to, based on a determination that the object is unavoidable in a lateral direction, decelerate the vehicle based on the reliability value (see at least Baker, para. [0051]: In an example, the Bayesian object classifier system can generate a confidence score distribution over several possible types of objects, and can further assign the label to the type that has the highest confidence score assigned thereto. At 516, a mechanical system of the autonomous vehicle is controlled based upon the label assigned to the object by the Bayesian object classifier system. For example, the mechanical system may be one of an engine, a braking system, or a steering system. Further, for instance, when the label indicates that the object isa car and the car is approaching relatively quickly from the left-hand side of the vehicle, the steering system and the braking system can be controlled to slow the autonomous vehicle and veer to the right to ensure that the autonomous vehicle avoids a collision with the car.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, cause the apparatus to, based on a determination that the object is unavoidable in a lateral direction, decelerate the vehicle based on the reliability value of Baker, with a reasonable expectation of success, in order for reducing errors with respect to object type classification (see at least Baker, para. [0003]).
As per claim 19 Taylor does not explicitly disclose
wherein the controlling of the vehicle comprises: controlling the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction.
Baker teaches
wherein the controlling of the vehicle comprises: controlling the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction (see at least Baker, para. [0051]: Further, for instance, when the label indicates that the object isa car and the car is approaching relatively quickly from the left-hand side of the vehicle, the steering system and the braking system can be controlled to slow the autonomous vehicle and veer to the right to ensure that the autonomous vehicle avoids a collision with the car.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the controlling of the vehicle comprises: controlling the vehicle to avoid the object in a lateral direction based on a determination that the object is avoidable in the lateral direction of Baker, with a reasonable expectation of success, in order for reducing errors with respect to object type classification (see at least Baker, para. [0003]).
As per claim 20 Taylor does not explicitly disclose
further comprising: causing the vehicle to decelerate based on the reliability value.
Baker teaches
further comprising: causing the vehicle to decelerate based on the reliability value (see at least Baker, para. [0051]: Further, for instance, when the label indicates that the object isa car and the car is approaching relatively quickly from the left-hand side of the vehicle, the steering system and the braking system can be controlled to slow the autonomous vehicle and veer to the right to ensure that the autonomous vehicle avoids a collision with the car.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of further comprising: causing the vehicle to decelerate based on the reliability value of Baker, with a reasonable expectation of success, in order for reducing errors with respect to object type classification (see at least Baker, para. [0003]).
Claim(s) 3 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Baker, in view of US 2024/0103522A1 (“Djurie”).
As per claim 3 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to determine the first reliability value further based on a height, of the object, determined by the camera.
Djurie teaches
wherein the instructions, when executed by the processor, further cause the apparatus to determine the first reliability value further based on a height, of the object, determined by the camera (see at least Djurie, para. [0057]: For example, state(s) can describe (e.g., for a given time, time period, etc.) an estimate of an object's current or past location (also referred to as position)…classification (e.g., pedestrian class vs. vehicle class vs. bicycle class, etc.); the uncertainty scores associated therewith; or other state information….In some implementations, state(s) for one or more identified or unidentified objects can be maintained and updated over time as the autonomous platform continues to perceive or interact with the objects (e.g., maneuver with or around, yield to, etc.). & para. [0084]: The feature maps can be stacked together and processed by the perception model 410 to produce high quality three-dimensional detections. The detections include properties of the object such as velocity, width, height, length, category, and uncertainty scores on position for each detection.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to determine the first reliability value further based on a height, of the object, determined by the camera of Djurie, with a reasonable expectation of success, in order to provide an improved understanding of the environment context, which can lead to improved accuracy in object detection in addition to improved accuracy of future velocity predictions (see at least Djurie, para. [0033]).
Claim(s) 5-6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Baker, in view of US 2024/0190422A1 (“Prediger”).
As per claim 5 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a height of the object detected by the lidar.
Prediger teaches
wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a height of the object detected by the lidar (see at least Prediger, para. [0057-0059]: Based on the sensor data, the characteristics including the dimensions (size, height, shape, etc.) of the perceived obstacle may be indicative of one or more of a type of the obstacle…a height of the obstacle,…for identifying the perceived obstacle based on the sensor data….Based on the sensor data, data from a data storage is retrieved, which is associated with the perceived obstacle (S102). The data is referring to the geographical location of the perceived obstacle and comprises a confidence score. The confidence score may indicate a probability whether the perceived obstacle is actually over drivable or not.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a height of the object detected by the lidar of Prediger, with a reasonable expectation of success, in order to provide an improved method for determining the drivable path for a vehicle during a ride (see at least Prediger, para. [0008]).
As per claim 6 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a width of the object detected by the lidar.
Prediger teaches
wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a width of the object detected by the lidar (see at least Prediger, para. [0057-0059]: Based on the sensor data, the characteristics including the dimensions (size, height, shape, etc.) of the perceived obstacle may be indicative of one or more of a type of the obstacle…a height of the obstacle,…for identifying the perceived obstacle based on the sensor data….Based on the sensor data, data from a data storage is retrieved, which is associated with the perceived obstacle (S102). The data is referring to the geographical location of the perceived obstacle and comprises a confidence score. The confidence score may indicate a probability whether the perceived obstacle is actually over drivable or not.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a height of the object detected by the lidar of Prediger, with a reasonable expectation of success, in order to provide an improved method for determining the drivable path for a vehicle during a ride (see at least Prediger, para. [0008]).
Claim(s) 7-8 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Baker, in view of US 2024/0326787A1 (“Jiang”).
As per claim 7 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to determine the third reliability value further based on a power of the reflected radio wave received by the radar.
Jiang teaches
wherein the instructions, when executed by the processor, further cause the apparatus to determine the third reliability value further based on a power of the reflected radio wave received by the radar (see at least Jiang, para. [0078]: In some embodiments, the computer processor 10 may be comprised of a radar confidence processing module 128, and the sensors 100 may be comprised of a radar sensor configured to illuminate a scene with waves of a known wavelength (e.g., 76.5 GHZ) and to generate radar image data (e.g., a video stream) and radar confidence data from reflected waves, which have the known wavelength and which have been reflected from the scene, and to output a radar confidence map 130 to the encoder module 112.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to determine the third reliability value further based on a power of the reflected radio wave received by the radar of Jiang, with a reasonable expectation of success, in order to increase passenger safety by enabling driver assistance systems to determine whether a particular sensor is partially or wholly malfunctioning (e.g., partially or wholly covered by debris). (see at least Jiang, para. [0078]).
As per claim 8 Taylor does not explicitly disclose
wherein the instructions, when executed by the processor, further cause the apparatus to control the vehicle to ignore the object and maintain a current course of the vehicle based on the reliability value being less than a threshold value
Jiang teaches
wherein the instructions, when executed by the processor, further cause the apparatus to control the vehicle to ignore the object and maintain a current course of the vehicle based on the reliability value being less than a threshold value (see at least Jiang, para. [0088]: That is, in some embodiments, because the confidence values for the lower left region are below a reliability threshold and therefore computed depth values for the lower left region may be invalid, the computer processor 10 may be controlled not to use data from the cameras 100pertaining to the lower left region to detect objects in the scene of the captured image, to avoid false readings and consequently to avoid erroneous control of the car (e.g., to prevent the car from being controlled to perform an evasive maneuver to avoid an object that is not actually in the scene).).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to control the vehicle to ignore the object and maintain a current course of the vehicle based on the reliability value being less than a threshold value of Jiang, with a reasonable expectation of success, in order to increase passenger safety by enabling driver assistance systems to determine whether a particular sensor is partially or wholly malfunctioning (e.g., partially or wholly covered by debris). (see at least Jiang, para. [0078]).
Claim(s) 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Djurie.
As per claim 13 Taylor does not explicitly disclose
further comprising: determining the first reliability value further based on a height of the object determined by the camera.
Djurie teaches
further comprising: determining the first reliability value further based on a height of the object determined by the camera (see at least Djurie, para. [0057]: For example, state(s) can describe (e.g., for a given time, time period, etc.) an estimate of an object's current or past location (also referred to as position)…classification (e.g., pedestrian class vs. vehicle class vs. bicycle class, etc.); the uncertainty scores associated therewith; or other state information….In some implementations, state(s) for one or more identified or unidentified objects can be maintained and updated over time as the autonomous platform continues to perceive or interact with the objects (e.g., maneuver with or around, yield to, etc.). & para. [0084]: The feature maps can be stacked together and processed by the perception model 410 to produce high quality three-dimensional detections. The detections include properties of the object such as velocity, width, height, length, category, and uncertainty scores on position for each detection.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of further comprising: determining the first reliability value further based on a height of the object determined by the camera of Djurie, with a reasonable expectation of success, in order to provide an improved understanding of the environment context, which can lead to improved accuracy in object detection in addition to improved accuracy of future velocity predictions (see at least Djurie, para. [0033]).
Claim(s) 15-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Prediger.
As per claim 15 Taylor does not explicitly disclose
further comprising: determining the second reliability value further based on a height of the object detected by the lidar
Prediger teaches
further comprising: determining the second reliability value further based on a height of the object detected by the lidar (see at least Prediger, para. [0057-0059]: Based on the sensor data, the characteristics including the dimensions (size, height, shape, etc.) of the perceived obstacle may be indicative of one or more of a type of the obstacle…a height of the obstacle,…for identifying the perceived obstacle based on the sensor data….Based on the sensor data, data from a data storage is retrieved, which is associated with the perceived obstacle (S102). The data is referring to the geographical location of the perceived obstacle and comprises a confidence score. The confidence score may indicate a probability whether the perceived obstacle is actually over drivable or not.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of wherein the instructions, when executed by the processor, further cause the apparatus to determine the second reliability value further based on a height of the object detected by the lidar of Prediger, with a reasonable expectation of success, in order to provide an improved method for determining the drivable path for a vehicle during a ride (see at least Prediger, para. [0008]).
As per claim 16 Taylor does not explicitly disclose
further comprising: determining the second reliability value further based on a width of the object detected by the lidar.
Prediger teaches
further comprising: determining the second reliability value further based on a width of the object detected by the lidar (see at least Prediger, para. [0057-0059]: Based on the sensor data, the characteristics including the dimensions (size, height, shape, etc.) of the perceived obstacle may be indicative of one or more of a type of the obstacle…a height of the obstacle,…for identifying the perceived obstacle based on the sensor data….Based on the sensor data, data from a data storage is retrieved, which is associated with the perceived obstacle (S102). The data is referring to the geographical location of the perceived obstacle and comprises a confidence score. The confidence score may indicate a probability whether the perceived obstacle is actually over drivable or not.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of further comprising: determining the second reliability value further based on a width of the object detected by the lidar of Prediger, with a reasonable expectation of success, in order to provide an improved method for determining the drivable path for a vehicle during a ride (see at least Prediger, para. [0008]).
Claim(s) 17-18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Taylor, in view of Alazem, in view of Jiang.
As per claim 17 Taylor does not explicitly disclose
further comprising: determining the third reliability value further based on a power of the reflected radio wave received by the radar.
Jiang teaches
further comprising: determining the third reliability value further based on a power of the reflected radio wave received by the radar (see at least Jiang, para. [0078]: In some embodiments, the computer processor 10 may be comprised of a radar confidence processing module 128, and the sensors 100 may be comprised of a radar sensor configured to illuminate a scene with waves of a known wavelength (e.g., 76.5 GHZ) and to generate radar image data (e.g., a video stream) and radar confidence data from reflected waves, which have the known wavelength and which have been reflected from the scene, and to output a radar confidence map 130 to the encoder module 112.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of further comprising: determining the third reliability value further based on a power of the reflected radio wave received by the radar of Jiang, with a reasonable expectation of success, in order to increase passenger safety by enabling driver assistance systems to determine whether a particular sensor is partially or wholly malfunctioning (e.g., partially or wholly covered by debris). (see at least Jiang, para. [0078]).
As per claim 18 Taylor discloses
further comprising:
determining whether a second object acquired by the sensor belongs to any pre-classified type (see at least Taylor, para. [0076]:For example, various autonomous driving systems perform object and/or hazard detection by consuming sensor input to classify an object. While useful in many situations, classifying objects may require specific sensors and/or may require significant computational resources. Furthermore, issues may arise when objects are present that are not within one of the preprogrammed classification categories.);
based on the second object not belonging to any pre-classified type, determining a second reliability value associated with information on the second object (see at least Taylor, para. [0060]: In various embodiments, the hazard detection module 214 receives as input the bounding area data 226 generated by the bounding area module 212. The hazard detection module 214 dynamically determines a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. & para. [0071]: At 322, the method 300 may include determining a confidence level associated with a likelihood that a hazard exists within the bounding area based, at least in part, on the quantity of the radar objects located within the bounding area at a given time. Depending on the quantity of the radar objects within the bounding area and/or a grouping of the radar objects within the bounding area, the confidence level may be increased or decreased dynamically.).
However Taylor does not explicitly disclose
controlling, based on the second reliability value being smaller than a threshold value, the vehicle to ignore the second object and maintain a current course of the vehicle.
Jiang teaches
controlling, based on the second reliability value being smaller than a threshold value, the vehicle to ignore the second object and maintain a current course of the vehicle (see at least Jiang, para. [0088]: That is, in some embodiments, because the confidence values for the lower left region are below a reliability threshold and therefore computed depth values for the lower left region may be invalid, the computer processor 10 may be controlled not to use data from the cameras 100pertaining to the lower left region to detect objects in the scene of the captured image, to avoid false readings and consequently to avoid erroneous control of the car (e.g., to prevent the car from being controlled to perform an evasive maneuver to avoid an object that is not actually in the scene).).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified Taylor to incorporate the teaching of controlling, based on the second reliability value being smaller than a threshold value, the vehicle to ignore the second object and maintain a current course of the vehicle of Jiang, with a reasonable expectation of success, in order to increase passenger safety by enabling driver assistance systems to determine whether a particular sensor is partially or wholly malfunctioning (e.g., partially or wholly covered by debris). (see at least Jiang, para. [0078]).
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 MOHAMED ABDO ALGEHAIM whose telephone number is (571)272-3628. The examiner can normally be reached Monday-Friday 8-5PM 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, Fadey Jabr can be reached at 571-272-1516. 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.
/MOHAMED ABDO ALGEHAIM/Primary Examiner, Art Unit 3668
Prosecution Insights