DETAILED ACTION
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 12/23/2025 has been entered.
Claims 1-7, 10-17 and 20-22 are currently pending and examined below. Claims 1, 10-11 and 20 have been amended. Claims 21-22 have been added.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendment
Applicant’s arguments with respect to claim(s) 1-20 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Claim Objections
Claim 11 is objected to because of the following informalities:
In claim 11, the Office recommends amending “determine that a first candidate trajectory, from among the plurality of candidate trajectories, has a score that is greater than a threshold accept the first candidate trajectory as a target trajectory” to “determine that a first candidate trajectory, from among the plurality of candidate trajectories, has a score that is greater than a threshold, accept the first candidate trajectory as a target trajectory”.
Appropriate corrections are required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-7, 10-17 and 20-22 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
In claims 1 and 11, the recitation “executing the target trajectory to cause the vehicle to move in the candidate trajectory” is unclear. It is unclear which of the each candidate trajectory is “the candidate trajectory” referring to. How is the target trajectory related or different from the candidate trajectory and how executing the target trajectory would lead to moving in the candidate trajectory . The scope of the invention is thus indefinite.
Claims 2-7, 10, 12-17 and 20-22 are rejected as they depend upon rejected claims 1 and 11.
Appropriate corrections are required.
Claim Rejections - 35 USC § 102
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 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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1-4, 10-14 and 20-22 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Nister et al. (US 20210253128 A1; hereinafter Nister).
Regarding claim 1, Nister discloses:
A method (Fig. 1) comprising:
obtaining, as output from a kinematic vehicle model ([0056] “the behavior planner 140 to monitor and implement yielding and determine actual kinematic feasibility or any dangers”) executed by one or more processors ([0028] processor) associated with an autonomous vehicle ([0020] autonomous vehicle 800), i) a plurality of candidate trajectories ([0029] multiple trajectories) simulating ([0020] simulation environments) motion of the vehicle travelling a forward path (see Fig. 2), ii) one or more constraints ([0053]-[0055], [0058], [0071], [0074] constraints), and iii) one or more objectives ([0074] “Objectives may include, without limitation, maximizing comfort and making progress (get to a destination with minimum expenditure of resources such as time, money, fuel and wear). Another objective may be to maximize collision safety (obstacles), to follow lanes all else being equal (paths), and to operate while following applicable rules and conventions (wait conditions)”), the one or more constraints and the one or more objectives generated based on at least one of sensor data ([0099], [0048] “The higher amount of detail can include objects (e.g., other vehicles, pedestrians) detected by sensors associated with the autonomous vehicle”) or map data ([0048] “use a map showing a high level of detail over a small area”) of the autonomous vehicle, each of the plurality of candidate trajectories defined by forward motion attributes (see Fig. 2) that satisfy the one or more constraints on candidate forward movement of the vehicle ([0053]-[0055], [0058], [0071], [0074] constraints), the one or more objectives indicating objectives of the plurality of candidate trajectories ([0069] The varying choices include path 202, path 204, path 206, path 208, path 210, path 212, path 214, path 216, path 218, path 220, and path 222. Each path can be associated with a speed profile as shown on profile graph 230. As can be seen, paths 218, 220, and 222 come to a full stop within a short distance. In contrast, path 202 will allow a higher speed to be maintained.);
iteratively scoring, by the one or more processors, each candidate trajectory of the plurality of candidate trajectories and updating, by the one or more processors, the each candidate trajectory to increase the respective score thereof ([0086] “an iterative approach to identify an optimal trajectory”) by:
evaluating the each candidate trajectory using a reward function ([0075] sequential time reward/penalty), the reward function including variables representing at least one of penalties or rewards in satisfying the one or more constraints and the one or more objectives ([0075] The sequential time rewards for potential future locations can be used directly in the score and as a starting point, while the other components contributing to the score can add time as a penalty, [0074] “Each hypothetical trajectory can be evaluated by the plan evaluation component 171 to identify the highest quality or optimal trajectory”); and
modifying each candidate trajectory to increase the respective score based on the reward function ([0086] “the initial plurality of hypothetical trajectories may be evaluated with the trajectory having the highest optimization score acting as a seed to generate additional hypothetical trajectories for evaluation. In a second iteration, the second plurality of hypothetical trajectories may be generated by marginally changing various parameters of the seed trajectory”);
determining, by the one or more processors, that a first candidate trajectory, from among the plurality of candidate trajectories, has a score that is greater than a threshold ([0086] “The second plurality of hypothetical trajectories may then be evaluated to determine if one of these trajectories has a higher optimization score than the seed trajectory”);
accepting the first candidate trajectory as a target trajectory ([0086] “The hypothetical trajectory with the best optimization score may be selected for implementation.”); and
executing, by the one or more processors, the target trajectory to cause the vehicle to move in the candidate trajectory ([0087] “The Model Predictive Controller (MPC) 180 takes the chosen trajectory and uses a more refined vehicle model to select instantaneous lateral and longitudinal acceleration control 195”).
Regarding claim 2, Nister discloses:
wherein each of the one or more candidate trajectories is a longitudinal trajectory (see Fig. 2) for a predetermined duration of time ([0025] “the behavior planner may plan a vehicle's movement for the next half second, second, two seconds, three seconds, four seconds, five seconds, ten seconds, twenty seconds, etc.”).
Regarding claim 3, Nister discloses:
wherein the predetermined duration of time is greater than or equal to 10 seconds ([0025] “ten seconds, twenty seconds, etc.”).
Regarding claim 4, Nister discloses:
wherein each of the one or more constraints is one of (1) a distance and time constraint, (2) a velocity and time constraint, or (3) a velocity and distance constraint ([0053] “the longitudinal pre-limiting component 150 may augment a lane/rail with an acceleration limit, speed constraint, or a distance constraint”).
Regarding claim 10, Nister discloses:
wherein scoring the each candidate trajectory based on the reward function comprises applying, using the reward function, different weights to the one or more constraints and to the one or more objectives satisfied by the respective candidate trajectory ([0074] “Different qualities can be weighed differently when calculating a score”).
Regarding claim 11, Nister discloses:
A system (Fig. 1) comprising:
a non-transitory computer readable medium containing instructions ([0028] memory) that are executed by one or more processors ([0028] processor)([0028] “a processor executing instructions stored in memory”) associated with an autonomous vehicle ([0020] autonomous vehicle 800) and configured to:
obtain, as output from a kinematic vehicle model ([0056] “the behavior planner 140 to monitor and implement yielding and determine actual kinematic feasibility or any dangers”) executed by the one or more processors ([0028] processor), i) a plurality of candidate trajectories ([0029] multiple trajectories) simulating motion ([0020] simulation environments) of the vehicle travelling a forward path (see Fig. 2), ii) one or more constraints ([0053]-[0055], [0058], [0071], [0074] constraints), and iii) one or more objectives ([0074] “Objectives may include, without limitation, maximizing comfort and making progress (get to a destination with minimum expenditure of resources such as time, money, fuel and wear). Another objective may be to maximize collision safety (obstacles), to follow lanes all else being equal (paths), and to operate while following applicable rules and conventions (wait conditions)”), the one or more constraints and the one or more objectives generated based on at least one of sensor data ([0099], [0048] “The higher amount of detail can include objects (e.g., other vehicles, pedestrians) detected by sensors associated with the autonomous vehicle”) or map data ([0048] “use a map showing a high level of detail over a small area”) of the autonomous vehicle, each of the plurality of candidate trajectories defined by forward motion attributes (see Fig. 2) that satisfy the one or more constraints on candidate forward movement of the vehicle ([0053]-[0055], [0058], [0071], [0074] constraints), the one or more objectives indicating objectives of the plurality of candidate trajectories ([0069] The varying choices include path 202, path 204, path 206, path 208, path 210, path 212, path 214, path 216, path 218, path 220, and path 222. Each path can be associated with a speed profile as shown on profile graph 230. As can be seen, paths 218, 220, and 222 come to a full stop within a short distance. In contrast, path 202 will allow a higher speed to be maintained.);
iteratively score each candidate trajectory of the plurality of candidate trajectories and update the each candidate trajectory to increase the respective score thereof ([0086] “an iterative approach to identify an optimal trajectory”) by:
evaluating the each candidate trajectory using a reward function ([0075] sequential time reward/penalty), the reward function including variables representing at least one of penalties or rewards in satisfying the one or more constraints and the one or more objectives ([0075] The sequential time rewards for potential future locations can be used directly in the score and as a starting point, while the other components contributing to the score can add time as a penalty, [0074] “Each hypothetical trajectory can be evaluated by the plan evaluation component 171 to identify the highest quality or optimal trajectory”); and
modifying each candidate trajectory to increase the respective score based on the reward function ([0086] “the initial plurality of hypothetical trajectories may be evaluated with the trajectory having the highest optimization score acting as a seed to generate additional hypothetical trajectories for evaluation. In a second iteration, the second plurality of hypothetical trajectories may be generated by marginally changing various parameters of the seed trajectory”);
determine that a first candidate trajectory, from among the plurality of candidate trajectories, has a score that is greater than a threshold ([0086] “The second plurality of hypothetical trajectories may then be evaluated to determine if one of these trajectories has a higher optimization score than the seed trajectory”) accept the first candidate trajectory as a target trajectory ([0086] “The hypothetical trajectory with the best optimization score may be selected for implementation.”); and
execute the target trajectory to cause the vehicle to move in the candidate trajectory ([0087] “The Model Predictive Controller (MPC) 180 takes the chosen trajectory and uses a more refined vehicle model to select instantaneous lateral and longitudinal acceleration control 195”).
Regarding claim 12, Nister discloses:
wherein each of the one or more candidate trajectories is a longitudinal trajectory (see Fig. 2) for a predetermined duration of time ([0025] “the behavior planner may plan a vehicle's movement for the next half second, second, two seconds, three seconds, four seconds, five seconds, ten seconds, twenty seconds, etc.”).
Regarding claim 13, Nister discloses:
wherein the predetermined duration of time is greater than or equal to 10 seconds ([0025] “ten seconds, twenty seconds, etc.”).
Regarding claim 14, Nister discloses:
wherein each of the one or more constraints is one of (1) a distance and time constraint, (2) a velocity and time constraint, or (3) a velocity and distance constraint ([0053] “the longitudinal pre-limiting component 150 may augment a lane/rail with an acceleration limit, speed constraint, or a distance constraint”).
Regarding claim 20, Nister discloses:
wherein in scoring each candidate trajectory based on the reward function, the instructions cause the one or more processors to apply, using the reward function, different weights to the one or more constraints and to the one or more objectives satisfied by the respective candidate trajectory ([0074] “Different qualities can be weighed differently when calculating a score”).
Regarding claim 21, Nister discloses:
wherein the variables of the reward function have different weights ([0074] “Different qualities can be weighed differently when calculating a score”), the method further comprising:
adjusting the reward function by adjusting the different weights of the variables based on importance levels of the one or more constraints and the one or more objectives ([0074] “Different qualities can be weighed differently when calculating a score”); and
iteratively scoring and updating the each candidate trajectory, based on the adjusted reward function ([0075] The sequential time rewards for potential future locations can be used directly in the score and as a starting point, while the other components contributing to the score can add time as a penalty, [0074] “Each hypothetical trajectory can be evaluated by the plan evaluation component 171 to identify the highest quality or optimal trajectory”).
Regarding claim 22, Nister discloses:
wherein the variables of the reward function have different weights ([0074] “Different qualities can be weighed differently when calculating a score”) and the instructions cause the one or more processors to:
adjust the reward function by adjusting the different weights of the variables based on importance levels of the one or more constraints and the one or more objectives ([0074] “Different qualities can be weighed differently when calculating a score”); and
iteratively score and update the each candidate trajectory, based on the adjusted reward function ([0075] The sequential time rewards for potential future locations can be used directly in the score and as a starting point, while the other components contributing to the score can add time as a penalty, [0074] “Each hypothetical trajectory can be evaluated by the plan evaluation component 171 to identify the highest quality or optimal trajectory”).
Claim Rejections - 35 USC § 103
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.
Claims 5-7 and 15-17 are rejected under 35 U.S.C. 103 as being unpatentable over Nister in view of Cao et al. (US 20240017745 A1; hereinafter Cao).
Regarding claim 5, Nister does not specifically disclose:
wherein obtaining the one or more candidate trajectories comprises performing a differentiable simulation on a differential equation of the kinematic vehicle model.
However, Cao discloses:
wherein obtaining the one or more candidate trajectories comprises performing a differentiable simulation on a differential equation of the kinematic vehicle model ([0069] differentiable dynamic model 202 is a kinematic model; [0072] differentiable dynamic model 202 computes a next state, a next state is calculated using a differential method).
Nister and Cao are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectory generation. Therefore, 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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model (Cao’s background, [0001]).
Regarding claim 6, Nister does not specifically disclose:
wherein obtaining the one or more candidate trajectories comprises performing a first order optimization with respect to a differential equation of the kinematic vehicle model.
However, Cao discloses:
wherein obtaining the one or more candidate trajectories comprises performing a first order optimization with respect to a differential equation of the kinematic vehicle model ([0096] optimization is based on optimization methods such as stochastic gradient descent, stochastic gradient descent is first order optimization).
Nister and Cao are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectory generation. Therefore, 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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model (Cao’s background, [0001]).
Regarding claim 7, Nister does not specifically disclose:
wherein the differential equation of the kinematic vehicle model relates to a control of an acceleration of the vehicle.
However, Cao discloses:
wherein the differential equation of the kinematic vehicle model relates to a control of an acceleration of the vehicle ([0069] differentiable dynamic model 202 mathematically represents a vehicle's control and/or motion using various parameters such as…acceleration).
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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model and vehicle control (Cao’s background, [0001], [0060]).
Regarding claim 15, Nister does not specifically disclose:
wherein in obtaining the one or more candidate trajectories, the instructions cause the one or more processors to perform a differentiable simulation on a differential equation of the kinematic vehicle model.
However, Cao discloses:
wherein in obtaining the one or more candidate trajectories, the instructions cause the one or more processors to perform a differentiable simulation on a differential equation of the kinematic vehicle model ([0069] differentiable dynamic model 202 is a kinematic model; [0072] differentiable dynamic model 202 computes a next state, a next state is calculated using a differential method).
Nister and Cao are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectory generation. Therefore, 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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model (Cao’s background, [0001]).
Regarding claim 16, Nister does not specifically disclose:
wherein in obtaining the one or more candidate trajectories, the instructions cause the one or more processors to perform a first order optimization with respect to a differential equation of the kinematic vehicle model.
However, Cao discloses:
wherein in obtaining the one or more candidate trajectories, the instructions cause the one or more processors to perform a first order optimization with respect to a differential equation of the kinematic vehicle model ([0096] optimization is based on optimization methods such as stochastic gradient descent, stochastic gradient descent is first order optimization).
Nister and Cao are considered to be analogous to the claimed invention because they are in the same field of vehicle trajectory generation. Therefore, 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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model (Cao’s background, [0001]).
Regarding claim 17, Nister does not specifically disclose:
wherein the differential equation relates to a control of an acceleration of the vehicle.
However, Cao discloses:
wherein the differential equation relates to a control of an acceleration of the vehicle ([0069] differentiable dynamic model 202 mathematically represents a vehicle's control and/or motion using various parameters such as…acceleration).
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 Nister’s trajectory generation to further incorporate Cao’s trajectory generation for the advantage of generating optimized adversarial trajectories based on a differentiable dynamic model that uses differential equations which results in a better trajectory prediction model and vehicle control (Cao’s background, [0001], [0060]).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to PAYSUN WU whose telephone number is (571)272-1528. The examiner can normally be reached Monday-Friday 8AM-5PM.
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, Hunter Lonsberry can be reached on (571)272-7298. 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.
/PAYSUN WU/Examiner, Art Unit 3665
/DONALD J WALLACE/Primary Examiner, Art Unit 3665