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 .
Information Disclosure Statement
The references listed on the IDS filed 7/25/2024 have been considered by the Examiner.
Claim Rejections - 35 USC § 102
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.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claims 1, 3, 10-11, 13 and 20 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Hu et al. (US 20240420344 A1).
Regarding claim 1, Hu teaches: A system, comprising a computer including a processor and a memory, the memory storing instructions executable by the processor (See Hu [0013] for processor, memory and instructions) to:
obtain a portion of an occupancy grid map for an area, wherein the occupancy grid map is generated based on collected data of a host object in the area and collected data of respective target objects in the area; (See Hu Figs 1-4 and [0035]-[0080] for generation of occupancy map based on collected data regarding host and surrounding vehicles)
generate a predicted portion of the occupancy grid map based on predicted data of the host object and predicted data of the respective target objects; (See Hu [0057] for predicted occupancy map based on prediction of target objects)
determine an action based on inputting the portion and the predicted portion of the occupancy grid map to a deep reinforcement learning neural network; and (See Hu [0032]-[0034] for processing via neural network for determination of optimal trajectory based on predictions. See Figs 9-11 and [0106]-[0139] for iterative training of the neural network model, a form of reinforcement learning)
operate the host object based on the action. (See Hu Fig. 5, [0033], [0081], [0105] for post-processing motion planner used to determine an optimal trajectory for the ego vehicle to ensure the safety of the autonomous vehicle. While the operation of the vehicle based on the predicted trajectory is not explicitly described, it is clearly implied by the nature of an autonomous vehicle.)
Regarding claim 3, Hu teaches: The system of claim 1, wherein the instructions further include instructions to determine the collected data of the host object based on host object sensor data. (See Hu [0039] for ego vehicle traveling data and environmental data acquired by sensors in the vehicle)
Regarding claim 10, Hu teaches: The system of claim 1, wherein the occupancy grid map is generated based additionally on at least one of signal phase and timing (SPaT) data for traffic signals in the area and map data for the area. (See Hu [0038], [0091] where environmental data includes map data and static object data. See also Mueller et al. (US 20250368231 A1), used in the rejection of claim 5, for SPaT data.)
Regarding claims 11, 13 and 20, the claims are directed to a method for operating the system of claims 1, 3 and 10 and are rejected under the same rationale.
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 2 and 12 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 20240420344 A1) in view of Somayazulu et al. (US 20220240168 A1).
Regarding claim 2, Hu teaches: The system of claim 1,
Hu does not explicitly teach: wherein the instructions further include instructions to receive the collected data of the respective target objects from an infrastructure element in the area.
However, the use of data generated by infrastructure-based sensors is well known in the art.
For example, Somayazulu teaches a method of occupancy grid map computation, and teaches the communication of vehicles with infrastructure systems for data and sensor sharing between vehicles, other vehicles, and infrastructure (See [0024]-[0027]) including roadside units (RSUs) as a source of sensor data (See Fig. 16).
It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the application, to modify the system of Hu to incorporate environmental data collected or provided by local infrastructure, as taught in Somayazulu, in order to improve the available data provided to the neural network.
Regarding claim 12, the claim is directed to a method for operating the system of claim 2 and is rejected under the same rationale.
Claims 4 and 14 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 20240420344 A1) in view of Ramamoorthy et al. (US 20210370980 A1).
Regarding claim 4, Hu teaches: The system of claim 1, wherein the deep reinforcement learning neural network is trained based on a reward function, (See Hu [0098]-[0106] for cost function, considered comparable to a reward function, and training based on the described functions)
Hu does not explicitly teach: a reward for the reward function being determined based on comparing the action to a virtual scenario.
However, Ramamoorthy teaches a method of autonomous vehicle path planning based on predicted occupancy grid (See [0003], [0023], [0209]), the model being trained based on a reward function (See [0438]), by comparing different virtual scenarios (See [0139] for comparison of reward function scores generated for different simulated paths. Examiner considers the different paths to be comparable to the virtual scenarios.)
It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the application, to modify the system of Hu to incorporate the multiple scored simulations of Ramamoorthy in order to provide more effective iterative training of the neural network model.
Regarding claim 14, the claim is directed to a method for operating the system of claim 4 and is rejected under the same rationale.
Claims 5 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 20240420344 A1) in view of Ramamoorthy et al. (US 20210370980 A1) and Mueller et al. (US 20250368231 A1).
Regarding claim 5, Hu in view of Ramamoorthy teaches: The system of claim 4, wherein the virtual scenario includes virtual target vehicles operating in a virtual area, …and map data for the virtual area. (Each of the simulations of Ramamoorthy [0139] would include the relevant information)
Hu in view of Ramamoorthy does not explicitly teach: …simulated signal phase and timing (SPaT) data for virtual traffic signals in the virtual area,…
However, Mueller teaches a method of determining an occupancy grid map for a vehicle environment (See [0006]) which incorporates signal phase and timing data (See [0046] for information about traffic lights and their state. While the specific SPaT terminology is not used, Examiner considers these to be comparable.)
It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the application, to modify the system of Hu in view of Ramamoorthy to incorporate traffic signal state and timing information, as taught in Mueller, in order to more accurately predict the upcoming behavior of surrounding vehicles.
Regarding claim 15, the claim is directed to a method for operating the system of claim 5 and is rejected under the same rationale.
Claims 6-9 and 16-19 are rejected under 35 U.S.C. 103 as being unpatentable over Hu et al. (US 20240420344 A1) in view of Kurbiel et al. (US 20230048926 A1), Ramamoorthy et al. (US 20210370980 A1), and Wan et al. (Wan, E. A., & Van Der Merwe, R. (2000, October). The unscented Kalman filter for nonlinear estimation. In Proceedings of the IEEE 2000 adaptive systems for signal processing, communications, and control symposium (Cat. No. 00EX373) (pp. 153-158). Ieee.)
Examiner’s Note: Claims 6, 8, 16 and 18 reference an Immediate Multiple Model, as do paragraphs [0020, [0022], [0030], and [0032] of the specification. However, these paragraphs do not include a description of the Immediate Multiple Model. Paragraph [0087], however, introduces the Interactive Multiple Model (IMM) 425, which appears to perform the described function of the Immediate Multiple Model. Examiner will be using the description of IMM 425 from paragraphs and afterward to examine these claims. Specifically, it is described as using a Markov Model to determine a future state based on a present state.
Regarding claim 6, Hu teaches: The system of claim 1, wherein the instructions further include instructions to:
…
determine, in the predicted occupancy grid map, a predicted occupancy of the host object based on the predicted host object position and a host object size. (See Hu [0006]-[0008] for generation of occupancy map based on data including ego-vehicle size, sample trajectory vectors and the generation of predicted trajectory vectors.)
Hu does not explicitly teach the use of an Immediate Unscented Kalman Filter as part of the initial data analysis, or a Markov Model (the basis of the IMM) as the method of predicting future states.
Kurbiel teaches a method for determining the surroundings of a vehicle (Abstract) including the generation of an occupancy grid (See [0035]) and using a Kalman filter for radar and image data analysis and object tracking (See [0007]). Kurbiel does not go into detail regarding which form of the Kalman filter to employ.
Wan teaches the benefits of an Unscented Kalman Filter over alternatives such as the Extended Kalman Filter. (See Wan, abstract and throughout). Regarding the Immediate UKF and the Immediate Multiple Model, based on the specification and an online search regarding the terms, Examiner is assuming the “Immediate” modifier to refer to the feedback loop described in paragraph [0076]. Wan teaches the UKF as being applied to control applications requiring full-state feedback (See Applications and Results).
Ramamoorthy teaches a method of autonomous vehicle path planning based on predicted occupancy grid (See [0003], [0023], [0209]), incorporating a spatial Markov model (See [0023], [0209], and elsewhere).
It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the application, to modify the system of Hu to incorporate the Kalman filter of Kurbiel and the Markov Model of Ramamoorthy in order to improve the accuracy of the data analysis and occupancy map predictions. It would have further been obvious to specifically use an Unscented Kalman Filter, as described in Wan, to improve the performance and reliability of the filter.
Regarding claim 7, modified Hu teaches: The system of claim 6, wherein the instructions further include instructions to, upon determining a predicted heading angle of the host object based on the predicted host object position, determine the predicted occupancy of the host object additionally based on the predicted heading angle. (See Hu [0008] for generation of occupancy map based on data including sample trajectory vectors and the generation of predicted trajectory vectors.)
Regarding claim 8, Hu teaches: The system of claim 1, wherein the instructions further include instructions to:
…
determine, in the predicted occupancy grid map, respective predicted occupancies of the respective target objects based on the respective predicted target object positions… (See Hu [0007]-[0011] for prediction of object positions and trajectories)
Hu does not explicitly teach the use of an Immediate Unscented Kalman Filter as part of the initial data analysis, or a Markov Model (the basis of the IMM) as the method of predicting future states.
Hu also does not explicitly teach the occupancy prediction being based on the respective target object’s size. Examiner considers this an obvious part of predicting the occupancy of a target object, as a truck and a pedestrian (See Hu [0041] for examples of target objects) will clearly occupy different spaces.
Kurbiel teaches a method for determining the surroundings of a vehicle (Abstract) including the generation of an occupancy grid (See [0035]) and using a Kalman filter for radar and image data analysis and object tracking (See [0007]). Kurbiel does not go into detail regarding which form of the Kalman filter to employ.
Wan teaches the benefits of an Unscented Kalman Filter over alternatives such as the Extended Kalman Filter. (See Wan, abstract and throughout). Regarding the Immediate UKF and the Immediate Multiple Model, based on the specification and an online search regarding the terms, Examiner is assuming the “Immediate” modifier to refer to the feedback loop described in paragraph [0076]. Wan teaches the UKF as being applied to control applications requiring full-state feedback (See Applications and Results).
Ramamoorthy teaches a method of autonomous vehicle path planning based on predicted occupancy grid (See [0003], [0023], [0209]), incorporating a spatial Markov model (See [0023], [0209], and elsewhere). Ramamoorthy also teaches detecting the size of objects within the environment (See [0123]).
It would have been obvious to one of ordinary skill in the art, prior to the effective filing date of the application, to modify the system of Hu to incorporate the Kalman filter of Kurbiel and the Markov Model of Ramamoorthy in order to improve the accuracy of the data analysis and occupancy map predictions. It would have further been obvious to specifically use an Unscented Kalman Filter, as described in Wan, to improve the performance and reliability of the filter.
Regarding claim 9, Hu teaches: The system of claim 8, wherein the instructions further include instructions to, upon determining respective predicted heading angles for each of the respective target objects based on the respective predicted target object positions, predicted occupancy of the respective target objects additionally based on the respective predicted heading angles. (See Hu [0008] for generation of occupancy map based on data including sample trajectory vectors and the generation of predicted trajectory vectors.)
Regarding claims 16-19, the claims are directed to a method for operating the system of claims 6-9 and are rejected under the same rationale.
Art Cited but not Used
Of the art cited on the attached form PTO-892, Examiner specifically recommends reviewing the following as teaching or nearly teaching the limitations of at least claim 1:
Philbin et al. (US 20210103285 A1)
Ramamoorthy et al. (US 20210370980 A1)
Mueller et al. (US 20250368231 A1)
Kurbiel et al. (US 20230048926 A1)
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JACOB KENT BESTEMAN-STREET whose telephone number is (571)272-2501. The examiner can normally be reached M-TH 8:00-5:00. 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, Peter Nolan can be reached on 571-270-7016. 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.
/JACOB KENT BESTEMAN-STREET/
Examiner, Art Unit 3661
/PETER D NOLAN/Supervisory Patent Examiner, Art Unit 3661