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 .
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55.
Status of Claims
Claims 1-9 are pending in this application.
Claims 1-4 are amended.
Claims 5-9 are newly added.
Claims 1-9 are presented for examination.
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 2 September 2025 is being considered by the examiner.
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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
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.
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.
Claims 1-4, 6, and 8 are rejected under 35 U.S.C. 103 as being unpatentable over Kurutach et al. (US Publication 2024/0246537 A1) in view of Seegmiller et al. (US Patent 11,697,429 B2).
Regarding claim 1, Kurutach teaches a travel controller that controls travelling of a vehicle, the travel controller comprising: a memory in which is stored one or more undesirable motions of the vehicle that are to be avoided (Kurutach: Para. 21, 41; memory, including instructions that can be executed by the one or more processors; error functions may include, but are not limited to, a measure of kinematic infeasibility of the predicted trajectories such as acceleration or turn rate exceeding set thresholds); and a processor configured to generate a candidate parameter set including one or more parameters for controlling travel of the vehicle (Kurutach: Para. 45, 83; processor configured to: receive road data, wherein the road data represents a real-world environment encountered by an autonomous vehicle; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform) by inputting input data into a classifier that has been trained to output the one or more parameters in response to input of the input data (Kurutach: Para. 61, 65; an input layer can be configured to receive sensor data and/or data relating to an environment surrounding an AV; the neural network is pre-trained to process the features from the data in the input layer), the input data including a surroundings image obtained by a camera configured to take pictures of surroundings of the vehicle (Kurutach: Para. 39, 49; the raw AV data can include HD LiDAR point cloud data, image data, RADAR data, GPS data, and other sensor data that the data center can use for creating or updating AV geospatial data or for creating simulations of situations encountered by AV for future testing or training of various machine learning algorithms; still image cameras).
Kurutach doesn’t explicitly teach predict a future motion of the vehicle controlled to travel with the candidate parameter set, control travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of the one or more undesirable motions stored in the memory, and control travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches predict a future motion of the vehicle controlled to travel with the candidate parameter set (Seegmiller: Col. 13 Line 52 - Col. 14 Line 4, Col. 17 Lines 56-63; “trajectories” may refer to a path with positions of the AV along the path with respect to time; a trajectory may define a path of travel on a roadway for an AV that follows each of the rules associated with the roadway), control travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of the one or more undesirable motions stored in the memory (Seegmiller: Col. 15 Lines 52-59, Col. 16 Lines 1-10; control an autonomous vehicle on a trajectory; trajectory planning can include generating sets of candidate constraints that specify semantic longitudinal and lateral actions), and control travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23; with an unwieldy and intractable number of candidate constraint sets being passed, existing systems may be unable to efficiently compute an optimal trajectory; if the collision cannot be avoided, then vehicle controller may transmit appropriate control instructions to vehicle control system for execution of an emergency maneuver (e.g., brake and/or change direction of travel)).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Regarding claim 2, Kurutach teaches the travel controller according to claim 1, wherein the processor generates a plurality of the candidate parameter sets each including the one or more parameters (Kurutach: Para. 45; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform), and ………. where the future motion of the vehicle predicted for remaining ones of the candidate parameter sets does not correspond to any of the one or more undesirable motions (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit), the processor controls travel of the vehicle with one of the remaining candidate parameter sets (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit).
Kurutach doesn’t explicitly teach in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions.
However Seegmiller, in the same field of endeavor, teaches in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23; with an unwieldy and intractable number of candidate constraint sets being passed, existing systems may be unable to efficiently compute an optimal trajectory; if the collision cannot be avoided, then vehicle controller may transmit appropriate control instructions to vehicle control system for execution of an emergency maneuver (e.g., brake and/or change direction of travel)).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Regarding claim 3, Kurutach teaches a method for controlling travel of a vehicle, the method executed by a travel controller configured to control travel of the vehicle and comprising: generating a candidate parameter set including one or more parameters for controlling travel of the vehicle (Kurutach: Para. 45, 83; processor configured to: receive road data, wherein the road data represents a real-world environment encountered by an autonomous vehicle; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform) by inputting input data into a classifier that has been trained to output the one or more parameters in response to input of the input data (Kurutach: Para. 61, 65; an input layer can be configured to receive sensor data and/or data relating to an environment surrounding an AV; the neural network is pre-trained to process the features from the data in the input layer), the input data including a surroundings image obtained by a camera configured to take pictures of surroundings of the vehicle (Kurutach: Para. 39, 49; the raw AV data can include HD LiDAR point cloud data, image data, RADAR data, GPS data, and other sensor data that the data center can use for creating or updating AV geospatial data or for creating simulations of situations encountered by AV for future testing or training of various machine learning algorithms; still image cameras); ……….. , the undesirable motions being stored in a memory accessed by the travel controller (Kurutach: Para. 21, 41; memory, including instructions that can be executed by the one or more processors; error functions may include, but are not limited to, a measure of kinematic infeasibility of the predicted trajectories such as acceleration or turn rate exceeding set thresholds).
Kurutach doesn’t explicitly teach predicting a future motion of the vehicle controlled to travel with the candidate parameter set; controlling travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of one or more undesirable motions of the vehicle that are to be avoided ………… controlling travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches predicting a future motion of the vehicle controlled to travel with the candidate parameter set (Seegmiller: Col. 13 Line 52 - Col. 14 Line 4, Col. 17 Lines 56-63; “trajectories” may refer to a path with positions of the AV along the path with respect to time; a trajectory may define a path of travel on a roadway for an AV that follows each of the rules associated with the roadway); controlling travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of one or more undesirable motions of the vehicle that are to be avoided (Seegmiller: Col. 15 Lines 52-59, Col. 16 Lines 1-10; control an autonomous vehicle on a trajectory; trajectory planning can include generating sets of candidate constraints that specify semantic longitudinal and lateral actions) ………… controlling travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23; with an unwieldy and intractable number of candidate constraint sets being passed, existing systems may be unable to efficiently compute an optimal trajectory; if the collision cannot be avoided, then vehicle controller may transmit appropriate control instructions to vehicle control system for execution of an emergency maneuver (e.g., brake and/or change direction of travel)).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Regarding claim 4, Kurutach teaches a non-transitory computer-readable medium storing a computer program for controlling travel of a vehicle, the computer program causing a computer mounted on the vehicle to execute a process comprising: generating a candidate parameter set including one or more parameters for controlling travel of the vehicle (Kurutach: Para. 45, 83; processor configured to: receive road data, wherein the road data represents a real-world environment encountered by an autonomous vehicle; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform) by inputting input data into a classifier that has been trained to output the one or more parameters in response to input of the input data (Kurutach: Para. 61, 65; an input layer can be configured to receive sensor data and/or data relating to an environment surrounding an AV; the neural network is pre-trained to process the features from the data in the input layer), the input data including a surroundings image obtained by a camera configured to take pictures of surroundings of the vehicle (Kurutach: Para. 39, 49; the raw AV data can include HD LiDAR point cloud data, image data, RADAR data, GPS data, and other sensor data that the data center can use for creating or updating AV geospatial data or for creating simulations of situations encountered by AV for future testing or training of various machine learning algorithms; still image cameras); ……….. , the undesirable motions being stored in a memory accessed by the computer (Kurutach: Para. 21, 41; memory, including instructions that can be executed by the one or more processors; error functions may include, but are not limited to, a measure of kinematic infeasibility of the predicted trajectories such as acceleration or turn rate exceeding set thresholds).
Kurutach doesn’t explicitly teach predicting a future motion of the vehicle controlled to travel with the candidate parameter set; controlling travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of one or more undesirable motions of the vehicle that are to be avoided …………. controlling travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches predicting a future motion of the vehicle controlled to travel with the candidate parameter set (Seegmiller: Col. 13 Line 52 - Col. 14 Line 4, Col. 17 Lines 56-63; “trajectories” may refer to a path with positions of the AV along the path with respect to time; a trajectory may define a path of travel on a roadway for an AV that follows each of the rules associated with the roadway); controlling travel of the vehicle with the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set does not correspond to any of one or more undesirable motions of the vehicle that are to be avoided (Seegmiller: Col. 15 Lines 52-59, Col. 16 Lines 1-10; control an autonomous vehicle on a trajectory; trajectory planning can include generating sets of candidate constraints that specify semantic longitudinal and lateral actions) …………. controlling travel of the vehicle without the candidate parameter set when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23; with an unwieldy and intractable number of candidate constraint sets being passed, existing systems may be unable to efficiently compute an optimal trajectory; if the collision cannot be avoided, then vehicle controller may transmit appropriate control instructions to vehicle control system for execution of an emergency maneuver (e.g., brake and/or change direction of travel)).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Regarding claim 6, Kurutach teaches the method according to claim 3, further comprising: generating a plurality of the candidate parameter sets each including the one or more parameters (Kurutach: Para. 45, 83; processor configured to: receive road data, wherein the road data represents a real-world environment encountered by an autonomous vehicle; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform), and …… , and where the future motion of the vehicle predicted for remaining ones of the candidate parameter sets does not correspond to any of the one or more undesirable motions (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit), controlling travel of the vehicle with one of the remaining candidate parameter sets (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit).
Kurutach doesn’t explicitly teach wherein in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions.
However Seegmiller, in the same field of endeavor, teaches wherein in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions (Seegmiller: Col. 28 Lines 50-57, Col. 29 Lines 10-23; motion planning system can determine a motion plan for autonomous vehicle that best navigates autonomous vehicle relative to the objects at their future locations; control instructions to vehicle control system for execution of an emergency maneuver e.g., brake and/or change direction of travel).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Regarding claim 8, Kurutach teaches the non-transitory computer-readable medium according to claim 4, wherein the process further comprises: generating a plurality of the candidate parameter sets each including the one or more parameters (Kurutach: Para. 45, 83; processor configured to: receive road data, wherein the road data represents a real-world environment encountered by an autonomous vehicle; planning stack can determine multiple sets of one or more mechanical operations that the AV can perform), and ……… , and where the future motion of the vehicle predicted for remaining ones of the candidate parameter sets does not correspond to any of the one or more undesirable motions (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit), controlling travel of the vehicle with one of the remaining candidate parameter sets (Kurutach: Para. 46; the control stack can implement the final path; turning the routes and decisions from the planning stack into commands for the actuators that control the AV's steering, throttle, brake, and drive unit).
Kurutach doesn’t explicitly teach wherein in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions.
However Seegmiller, in the same field of endeavor, teaches wherein in the case where the future motion of the vehicle predicted for at least one of the generated candidate parameter sets corresponds to at least one of the one or more undesirable motions (Seegmiller: Col. 28 Lines 50-57, Col. 29 Lines 10-23; motion planning system can determine a motion plan for autonomous vehicle that best navigates autonomous vehicle relative to the objects at their future locations; control instructions to vehicle control system for execution of an emergency maneuver e.g., brake and/or change direction of travel).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Claims 5, 7, and 9 are rejected under 35 U.S.C. 103 as being unpatentable over Kurutach et al. (US Publication 2024/0246537 A1) in view of Seegmiller et al. (US Patent 11,697,429 B2) and in further view of Yamaguchi et al. (US Publication 2022/0274585 A1).
Regarding claim 5, Kurutach doesn’t explicitly teach wherein when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches wherein when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 17 Lines 56-63, Col. 25 Lines 49-54; generate multiple candidate constraint sets, each of the candidate constraint sets is used to optimize a candidate trajectory; constraints take into account, with respect to the autonomous vehicle, current velocity, speed limit in the local region, acceleration limit, deceleration limit, prediction data relating to objects in the autonomous vehicle environment).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Kurutach and Seegmiller don’t explicitly teach the processor controls travel of the vehicle using a modification of the candidate parameter set, the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory.
However Yamaguchi, in the same field of endeavor, teaches the processor controls travel of the vehicle using a modification of the candidate parameter set (Yamaguchi: Para. 73 - 74; travel route does not satisfy the regulation for automatic travel of the vehicle, the determination unit sends the regulation with which the travel route is not satisfied to the modification unit), the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory (Yamaguchi: Para. 76; when the speed during teaching travel is greater than or equal to a threshold value, the modification unit modifies the speed to be less than or equal to the threshold value).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) and a parameter modification due to thresholds (Yamaguchi: Para. 73-74, 76) with a reasonable expectation of success because when a generated travel route information does not comply with the regulation for automatic travel, the modification unit can modify one or more parameters achieving regulations and reducing processing load (Yamaguchi: Para. 143-145).
Regarding claim 7, Kurutach doesn’t explicitly teach wherein when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches wherein when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 17 Lines 56-63, Col. 25 Lines 49-54; generate multiple candidate constraint sets, each of the candidate constraint sets is used to optimize a candidate trajectory; constraints take into account, with respect to the autonomous vehicle, current velocity, speed limit in the local region, acceleration limit, deceleration limit, prediction data relating to objects in the autonomous vehicle environment).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Kurutach and Seegmiller don’t explicitly teach controlling travel of the vehicle using a modification of the candidate parameter set, the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory.
However Yamaguchi, in the same field of endeavor, teaches controlling travel of the vehicle using a modification of the candidate parameter set (Yamaguchi: Para. 73 - 74; travel route does not satisfy the regulation for automatic travel of the vehicle, the determination unit sends the regulation with which the travel route is not satisfied to the modification unit), the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory (Yamaguchi: Para. 76; when the speed during teaching travel is greater than or equal to a threshold value, the modification unit modifies the speed to be less than or equal to the threshold value).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) and a parameter modification due to thresholds (Yamaguchi: Para. 73-74, 76) with a reasonable expectation of success because when a generated travel route information does not comply with the regulation for automatic travel, the modification unit can modify one or more parameters achieving regulations and reducing processing load (Yamaguchi: Para. 143-145).
Regarding claim 9, Kurutach doesn’t explicitly teach when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory.
However Seegmiller, in the same field of endeavor, teaches when the future motion of the vehicle predicted for the candidate parameter set corresponds to at least one of the one or more undesirable motions stored in the memory (Seegmiller: Col. 17 Lines 56-63, Col. 25 Lines 49-54; generate multiple candidate constraint sets, each of the candidate constraint sets is used to optimize a candidate trajectory; constraints take into account, with respect to the autonomous vehicle, current velocity, speed limit in the local region, acceleration limit, deceleration limit, prediction data relating to objects in the autonomous vehicle environment).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) with a reasonable expectation of success because when the existing systems is unable to efficiently compute an optimal trajectory with the candidate constraints sets, even when pruning is used to determine potential constraints sets, a collision might not be avoided and the vehicle executes an emergency braking maneuver (Seegmiller: Col. 16 Lines 35-46, Col. 29 Lines 19-23).
Kurutach and Seegmiller don’t explicitly teach controlling travel of the vehicle using a modification of the candidate parameter set, the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory.
However Yamaguchi, in the same field of endeavor, teaches controlling travel of the vehicle using a modification of the candidate parameter set (Yamaguchi: Para. 73 - 74; travel route does not satisfy the regulation for automatic travel of the vehicle, the determination unit sends the regulation with which the travel route is not satisfied to the modification unit), the modification of the candidate parameter set not causing the motion of the vehicle to correspond to any of the one or more undesirable motions stored in the memory (Yamaguchi: Para. 76; when the speed during teaching travel is greater than or equal to a threshold value, the modification unit modifies the speed to be less than or equal to the threshold value).
It would have been obvious to one having ordinary skill in the art to modify the neural network trajectory prediction with error functions (Kurutach: Para. 19, 21) with the emergency maneuver (Seegmiller: Col. 29 Lines 19-23) and a parameter modification due to thresholds (Yamaguchi: Para. 73-74, 76) with a reasonable expectation of success because when a generated travel route information does not comply with the regulation for automatic travel, the modification unit can modify one or more parameters achieving regulations and reducing processing load (Yamaguchi: Para. 143-145).
Response to Arguments
Applicant’s arguments with respect to claims 1-4 under 35 U.S.C. 103, filed on 5 November 2025, have been fully considered, and they are not persuasive .
The applicant attorney argues that Kurutach does not “predict a future motion of the vehicle controlled to travel with the candidate parameter set.”
In response to the argument above, Seegmiller generates a trajectory along a path with respect to time for an AV that follows each of the rules associated with the roadway (Seegmiller: Col. 13 Line 52 – Col. 14 Line 4). The system generates multiple candidate constraint sets, each of the candidate constraint sets is used to optimize a candidate trajectory, and one of the candidate constraint sets may be selected to control the AV by a trajectory scoring subsystem of a vehicle computing system (Seegmiller: Col. 17 Lines 56-63). The candidate trajectories are a predicted future vehicle motions for each parameter set.
The applicant next argues that Kurutach does not determine whether or not to control travel of the vehicle with the candidate parameter set based on a comparison of the future of the vehicle that has been predicted to the one or more undesirable motions stored in the memory.
In response to the argument above, Kurutach is not being used to teach the above limitation.
The applicant next argues that Kurutach does not predict motion of the AV controlled according to the one or more sets of mechanical operations.
In response to the argument above, Kurutach is not being used to teach the above limitation.
The applicant next argues that Seegmiller does not overcome the deficiencies of Kurutach.
In response to the argument above, Seegmiller does overcome the deficiencies of Kurutach as explained above.
The applicant next argues that independent claims 1, 3, and 4, along with their dependent claims, are patentable over Kurutach in view of Seegmiller.
In response to the argument above, the applicant’s arguments for claim 1 have been addressed above and would similarly apply to claims 3 and 4. The dependent claims are rejected at least by their dependencies.
The applicant next argues that newly added claims 5-9 are patentable due to their dependence from claims 1, 3, and 4 and due to the additional features claim in claims 5-9.
In response to the argument above, claims 1 and 3-4 have been rejected. The dependent claims are rejected at least by their dependencies.
The applicant’s arguments have failed to point out the distinguishing characteristics of the amended claim language over the prior art. For the above reasons, Kurutach’s route determination with Seegmiller’s trajectory planning reads on applicant’s travel controller and method for controlling travel. The rejection is maintained.
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 extension fee 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 date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to LAURA E LINHARDT whose telephone number is (571)272-8325. The examiner can normally be reached on M-TR, M-F: 8am-4pm.
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, Angela Ortiz can be reached on (571) 272-1206. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/L.E.L./Examiner, Art Unit 3663
/ANGELA Y ORTIZ/Supervisory Patent Examiner, Art Unit 3663