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 .
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 1-4, 6-14, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over US20210300413 by Turlej et al. (hereinafter “Turlej”), further in view of US20200211394 by King et al. (hereinafter “King”).
Regarding claim 1, Turlej teaches A method comprising: evaluating safety procedure trajectories initiated from respective future positions of a machine on a trajectory with respect to at least one objective corresponding to the safety procedure trajectories; see for example paragraphs [0011] or [0039], where the system evaluates two, three, or more abort trajectories diverging from a nominal trajectory.
based at least on the evaluating, assigning respective scores to the safety procedure trajectories, the respective scores indicating levels of safety associated with the safety procedure trajectories; see again paragraph [0011] or paragraphs [0040]-[[0043], where a cost is associated with each abort trajectory.
computing, using the scores, an aggregate score for the trajectory; see paragraphs [0015]-[0016] and [0040]-[0043], where the abort trajectory scores are incorporated into the overall trajectory score.
based at least on the aggregate score, initiating the trajectory . See paragraphs [0044]-[0048], where the vehicle initiates the nominal trajectory computed.
Turlej does not explicitly teach initiating…a different trajectory for the machine. Although Turlej implies that the overall trajectory is optimized (selecting the best trajectory over other possible trajectories), Turlej does not explicitly teach that the machine could initiate a different trajectory.
However, King teaches a vehicle system that initiat[es] the trajectory or a different trajectory for the machine. See for example paragraph [0058], where the system executes a cost-based search to identify different trajectories, such as a primary and a secondary trajectory. See also paragraphs [0083]-[0085], where the system evaluates multiple trajectories and selects one to execute.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the nominal and abort trajectory generation system of Turlej with the multiple candidate trajectories of King with a reasonable expectation of success. Doing so allows the system to examine and compare the costs of multiple trajectories, each with their own abort trajectories, in order to select the safest and most comfortable trajectory.
Claims 11 and 17 have similar limitations to claim 1 above, and are therefore rejected based on a similar rationale.
Regarding claim 2, Turlej teaches wherein a score of the respective scores for a safety procedure trajectory of the safety procedure trajectories is based at least on one or more of: a distance between a current position of the machine and one or more positions corresponding to the safety procedure trajectory; or an elapsed time for the machine to reach the one or more positions from the current position. See for example paragraph [0043], where the abort trajectories have decreasing weights over time/distance, reading on both a distance and an elapsed time for the machine to reach the one or more positions from the current position.
Claims 12 and 18 have similar limitations to claim 2 above, and are therefore rejected based on a similar rationale.
Regarding claim 3, Turlej teaches wherein the score increases as one or more of the distance or the elapsed time increases. The cost weights of the abort trajectories decrease in space/time in paragraph [0043], so that the trajectory optimizer allows for more extreme abort maneuvers at later abort trajectories. See also Fig. 2, describing this relationship. That is, Turlej has a minimizing (rather than maximizing) cost function, making the trajectory better as its cost decreases. See ¶¶ {0040]-[0043], Fig. 2. Thus, the decreasing weights for more distant abort trajectories described in paragraph [0043] correspond to a better “score” compared to other trajectories, reading on wherein the score increases as one or more of the distance or the elapsed time increases.
Claims 13 and 19 have similar limitations to claim 3 above, and are therefore rejected based on a similar rationale.
Regarding claim 4, Turlej teaches wherein one or more of the distance or the elapsed time is used as a soft constraint on the trajectory based at least on the one or more of the distance or the elapsed time being greater than one or more thresholds. See for example paragraphs [0017], [0043], and [0049], where abort trajectories are weighted according to their distance from the current vehicle position, with a first high-discomfort abort trajectory reflecting more negatively on the nominal trajectory than a subsequent, more distant abort trajectory with the same high discomfort level.
Claim 14 has similar limitations to claim 4 above, and is therefore rejected based on a similar rationale.
Regarding claim 6, Turlej teaches wherein the aggregate score is based at least on a first weighting corresponding to the levels of safety, and one or more second weightings corresponding to at least one of comfort, progress, rule or convention following, or lane following associated with the trajectory. See for example paragraph [0039], where the nominal trajectory is required to be safe. See also paragraph [0043], where the abort trajectories (as part of the overall trajectory optimization formula) are weighted based on their comfort levels, such as jerk.
Regarding claim 7, Turlej teaches wherein a safety procedure trajectory of the safety procedure trajectories indicates a conflict with the at least one objective, and the initiating is of the trajectory based at least on one or more of: a distance between a current position of the machine and one or more positions corresponding to the safety procedure trajectory being greater than one or more thresholds; or an elapsed time for the machine to reach the one or more positions from the current position being greater than the one or more thresholds. See for example paragraphs [0004]-[0005] and [0039]-[0043], where the system has an objective of avoiding collisions. Moreover, the abort trajectories have decreasing weights over time/distance and are accordingly used in computing the overall trajectory, which is later initiated.
Regarding claim 8, Turlej teaches wherein the at least one objective comprises the machine stopping prior to a collision. See for example paragraphs [0004]-[0005] and [0039]-[0043], where the system has an objective of avoiding collisions.
Regarding claim 9, Turlej teaches wherein the aggregate score corresponds to a first ranking score assigned to the trajectory, and the initiating is of the trajectory based at least on the first ranking score being greater than a second ranking score . See paragraphs [0015]-[0016] and [0040]-[0043], where the abort trajectory scores are incorporated into the overall trajectory score. See also paragraphs [0044]-[0048], where the vehicle initiates the nominal trajectory computed based on its score being the best.
Turlej does not explicitly teach the initiating is of the trajectory based at least on the first ranking score being greater than a second ranking score assigned to the different trajectory. Although Turlej implies that the overall trajectory is optimized (selecting the best trajectory over other possible trajectories), Turlej does not explicitly teach that the machine could initiate a different trajectory.
However, King teaches initiating a trajectory based at least on the first ranking score being greater than a second ranking score assigned to the different trajectory. See for example paragraph [0058], where the system executes a cost-based search to identify different trajectories, such as a primary and a secondary trajectory. See also paragraphs [0083]-[0085], where the system evaluates multiple trajectories and selects one to execute.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the nominal and abort trajectory generation system of Turlej with the multiple candidate trajectories of King with a reasonable expectation of success. Doing so allows the system to examine and compare the costs of multiple trajectories, each with their own abort trajectories, in order to select the safest and most comfortable trajectory.
Claims 11 and 17 have similar limitations to claim 1 above, and are therefore rejected based on a similar rationale.
Regarding claim 10, Turlej teaches wherein at least one safety procedure trajectory of the safety procedure trajectories indicates a conflict with the at least one objective, the initiating is of the trajectory, and the method further includes one or more of re-planning the trajectory or switching to another trajectory prior to the machine reaching the at least one safety procedure trajectory along the trajectory. See for example paragraphs [0004]-[0005] and [0039]-[0043], where the system has an objective of avoiding collisions. See also paragraph [0048], where the nominal trajectory is executed until steps 54-55, where if the nominal trajectory turns out to be unsafe mid-execution, the first abort trajectory is executed before reaching the second (or third) abort trajectory location, reading on switching to another trajectory prior to the machine reaching the at least one safety procedure trajectory along the trajectory.
Regarding claim 16, Turlej teaches wherein the at least one processor is comprised in at least one of: a control system for a fully or semi-autonomous machine; a perception system for a fully or semi-autonomous machine; a system for performing simulation operations; a system for performing deep learning operations; a system implemented using an edge device; a system implemented using a robot; a system incorporating one or more virtual machines (VMs); a system implemented at least partially in a data center; or a system implemented at least partially using cloud computing resources. See for example paragraphs [0035]-[0036], where the process is implemented on an autonomous vehicle’s control system.
Claim 20 has similar limitations to claim 16 above, and is therefore rejected using a similar rationale.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Turlej in view of King as applied to claims 1 and 11 above, and further in view of US11460848 by Russell et al. (hereinafter “Russell”).
Regarding claim 5, Turlej does not explicitly teach, but Russell teaches wherein the aggregate score corresponds to an estimated time for the machine to reach a destination, and the respective scores are incorporated into the estimated time as time penalties. See for example column 10 line 15 through column 11 line 8, where the candidate trajectories are broken up into segments, and the vehicle prioritizes the trajectory having the lowest traversal time.
It would have been prima facie obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the nominal and abort trajectory generation system of Turlej, modified by the multiple candidate trajectories of King, with the time-based calculation of Russell with a reasonable expectation of success. Doing so allows the system to compare trajectory costs based on traversal time, reducing the time it takes a vehicle to reach the destination while remaining safe.
Claim 15 has similar limitations to claim 5 above, and is therefore rejected based on a similar rationale.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
US20210146956 by Fujita et al. teaching trajectory generation, including generation of risk avoidance trajectories.
US20210339741 by Rezvan Behbahani et al. teaching trajectory generation and modification based on risk.
US20210107517 by Watanabe et al. teaching generation of primary and secondary trajectories.
US20220227391 by Wang et al. teaching generation and scoring of candidate trajectories.
The publication "Fail- Safe Motion Planning of Autonomous Vehicles" by Magdici et al. teaching generation of a fail-safe route along a vehicle trajectory.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JORDAN THOMAS SMITH whose telephone number is (571)272-0522. The examiner can normally be reached Monday - Friday, 9am - 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, Anne Antonucci can be reached at (313) 446-6519. 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.
/JORDAN T SMITH/ Examiner, Art Unit 3666
Prosecution Insights