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 § 101
Applicant’s amendments sufficiently integrate the abstract idea into a practical application by actively controlling a vehicle, and thus are considered eligible.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-3, 6-10, 12-16, and 18-20 are rejected under 35 U.S.C. 103 as being unpatentable over Gopalan (US20250021712A1) in view of Philion (“Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs By Implicitly Unprojecting to 3D” 2020).
Regarding claim 14, Gopalan teaches;
A method for navigating a path by an autonomous vehicle in motion without using an external localization device (taught as an autonomous navigation system and method, paragraph 0043), the method comprising:
accessing image data collected on the path by an onboard sensor operably coupled to the autonomous vehicle (taught as collecting data from imaging sensors, paragraph 0055);
passing a slice of collected image data encoded with a first neural network feature extractor to generate encoded image data (taught as perception architecture inputting data from a set of sensors associated with a given mobile robot/vehicle, such as a convolutional neural network [CNN], paragraph 0069);
passing the encoded image data to a Bird’s Eye View (BEV) generation module (taught as planner guided perception architectures to run semantic labeling/queries on data, including a Bird’s Eye View, paragraphs 0075-0076); wherein the BEV generation module is a second neural network that cross-correlates input features with spatial positions around the autonomous vehicle (taught as sending queries to a cross attention transformer to determine representations of information, paragraph 0076, such as a spatial cross-attention transformer, paragraph 0078);
passing the outputted BEV [[costmap]] to a path-planning module operably coupled to the autonomous vehicle, wherein the path-planning module is configured to calculate a plurality of possible paths using a cost model (taught as passing features converted to the bird’s eye view using motion to generate attention information utilized by the autonomous navigation system, paragraph 0079).
However, Gopalan does not explicitly teach;
transforming the encoded image data into a BEV costmap using the BEV generation module;
passing the outputted BEV costmap to a path-planning module operably coupled to the autonomous vehicle, generating, with the path-planning module a plurality of possible paths using a cost model
after receiving the BEV costmap; selecting, with the path-planning module, a lowest cost path from among the plurality of possible paths based on a cost defined for the lowest cost path in the cost model, executing the lowest cost path to control the autonomous vehicle.
Philion teaches; transforming the encoded image data into a BEV costmap using the BEV generation module (taught as converting the Lift-Splat model into an inferred cost map, Section 3.3, pages 6-7, shown in Fig 4);
passing the outputted BEV costmap to a path-planning module operably coupled to the autonomous vehicle (indicated in using the inferred costmap to ‘shoot’ trajectories to act on section 3.3 page 6; essentially the costmap being used for motion planning indicates that the generated information is passed to a planner);
generating, with the path-planning module, a plurality of possible paths using a cost model after receiving the BEV costmap (taught as ‘shooting’ different trajectories to score their cost, Section 3.3, page 6);
selecting, with the path-planning module, a lowest cost path from among the plurality of possible paths based on a cost defined for the lowest cost path in the cost model (taught as acting [essentially choosing] the lowest cost trajectory, Section 3.3, page 6); and
executing the lowest cost path to control the autonomous vehicle (taught as acting [essentially choosing] the lowest cost trajectory, Section 3.3, page 6).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to create and use a cost map as taught by Philion in the system taught by Gopalan in order to better define optimization of trajectories. Philion demonstrates a marked improvement from the base in generalizing scenes from only camera data (see table 1, 2, and 4). Such a system allows for effective scene representation and analysis by only camera data.
Regarding claim 15, Gopalan as modified by Philion teaches;
The method of claim 14 (see claim 14 rejection). Gopalan further teaches; wherein the first neural network is a convolutional neural network (taught as a CNN, paragraph 0069).
Regarding claim 16, Gopalan as modified by Philion teaches;
The method of claim 14 (see claim 14 rejection). Gopalan further teaches; wherein the second neural network is a pre-trained transformer (taught as the machine learning models being trained [i.e. before implementation], paragraph 0037).
Regarding claim 18, Gopalan as modified by Philion teaches;
The method of claim 14 (see claim 14 rejection). Gopalan further teaches; wherein the second neural network is a spatial-cross attention transformer (taught as a spatial cross attention transformer, paragraph 0078).
Regarding claim 19, Gopalan as modified by Philion teaches;
The method of claim 18 (see claim 18 rejection). Gopalan further teaches; wherein the spatial cross-attention transformer is configured to output a BEV feature vector (taught as planning heads involved in spatial cross attention transformer involving vectors, paragraph 0078).
Regarding claim 20, Gopalan as modified by Philion teaches;
The method of claim 19 (see claim 19 rejection). Gopalan further teaches; wherein BEV feature vector is [[converted to a BEV costmap]] and passed to the path-planning controller (taught as using planning heads based on Bird’s Eye View segmentation, paragraph 0080). However, Gopalan does not explicitly teach; wherein BEV feature vector is converted to a BEV costmap and passed to the path-planning controller.
Philion teaches; wherein BEV feature vector is converted to a BEV costmap and passed to the path-planning controller ((indicated in using the inferred costmap to ‘shoot’ trajectories to act on section 3.3 page 6; essentially the costmap being used for motion planning indicates that the generated information is passed to a planner).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to create and use a cost map as taught by Philion in the system taught by Gopalan in order to better define optimization of trajectories. Philion teaches that using such a costmap can determine trajectories of high probability [likelihood of occurrence] (paragraph 0048), and thus better predict features/object motion and behavior; such knowledge is critical in trying to, for example, avoid collisions by predicting behavior of other objects, and thus take appropriate action (paragraph 0083).
Regarding claims 1-3, 6-10, and 12-13, it has been determined that no further limitations exist apart from those previously addressed in claims 14-16 and 19. Therefore, claims 1-3, 6-10, and 12-13 are rejected under the same rational as claims 14-16 and 18-19, wherein;
1-3 and 8-10 correspond to claims 14-16, and
Claims 6-7 and 12-13 correspond to claims 18-19
Claim(s) 4, 11, and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Gopalan (US20250021712A1) in view of Philion (“Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs By Implicitly Unprojecting to 3D” 2020) as applied to claim 14, and further in view of Danielczuk (US20220152826A1).
Regarding claim 17, Gopalan as modified by Philion teaches;
The method of claim 14 (see claim 14 rejection). However, Gopalan does not explicitly teach; wherein the path-planning module is a Model Predictive Path Integral (MPPI) module.
Danielczuk teaches; wherein the path-planning module is a Model Predictive Path Integral (MPPI) module (taught as using an MPPI for collision free trajectory planning, paragraph 0094).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use an MPPI as taught by Danielczuk in the system taught by Gopalan in order to improve trajectory generation. As taught by Danielczuk, using the MPPI policy/algorithm allows for iterative updates toa control sequence to obtain optimal solutions, and thus use a scene collision network [cost map/environment] to determine placements and collision free trajectories (paragraph 0094).
Claim(s) 5 is rejected under 35 U.S.C. 103 as being unpatentable over Gopalan (US20250021712A1) in view of Philion (Lift, Splat, Shoot: Encoding Images from Arbitrary Camera Rigs By Implicitly Unprojecting to 3D” 2020) as applied to claim 14, and further in view of Beaudoin (US20240059319A1).
Regarding claim 5, Gopalan as modified by Philion teaches;
The method of claim 1 (see claim 14 rejection). However, Gopalan does not explicitly teach; wherein selecting the lowest cost path includes applying an optimizer using a Monte Carlo approximation.
Beaudoin teaches; wherein selecting the lowest cost path includes applying an optimizer using a Monte Carlo approximation (taught as performing a Monte Carlo search to select a trajectory, paragraph 0107).
It would be obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to use an optimization/selection based on a Monte Carlo search as taught by Beaudoin in the system taught by Gopalan in order to better select a trajectory. Using Monte Carlo in this fashion allows one to account for different control parameters, actions, at current and previous points in time, as suggested by Beaudoin (paragraph 0107). Such a search additionally allows for clear reward functions in further training, suggested in Beaudoin (paragraph 0109), and thus would improve future iterations of the method.
Response to Arguments
Applicant argues on pages 12-15 of the remarks that the recited prior art does not effectively teach the amended claim material, in particular using the generated BEV costmap to determine trajectories.
The examiner agrees, and withdraws the previous rejection. However, a new rejection in light of Philion, detailing a process of Lift, Splat, Shoot that takes in data from cameras, converts it to BEV, determines costs based on the BEV, and applies the lowest cost trajectory to the vehicle, is presented above [in place of Vernaza].
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
For further birds eye view generation and use in navigation; US20210302992A1 and US20230230385A1
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to GABRIEL ANFINRUD whose telephone number is (571)270-3401. The examiner can normally be reached M-F 9:30-5:30.
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, Jelani Smith can be reached at (571)270-3969. 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.
/GABRIEL ANFINRUD/Examiner, Art Unit 3662
/JELANI A SMITH/Supervisory Patent Examiner, Art Unit 3662
