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 .
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.
Status of Claims
This Office Action is in response to the Applicant’s amendments and remarks filed 26 November 2025. The Applicant has amended claims 1-8, 11, 17-18 and 22. Claims 1-22 are presently pending and are presented for examination.
Reply to Applicant’s Remarks
Applicant’s remarks filed 26 November 2025 have been fully considered and are addressed as follows:
Claim Rejections under 35 U.S.C. 101:
Applicant’s amendment to the claims filed 26 November 2025 have overcome the 35 U.S.C. 101 rejections previously set forth.
Claims Rejections under 35 U.S.C. 102/103:
Applicant’s arguments, see Arguments/Remarks, filed 26 November 2025, with regard to the rejections of claims 1-22 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
Regarding the applicant’s argument that “Nothing in the recited portions of Varadarajan…teaches or suggests generating…that are predicted to avoid collisions with one or more other agents”, the examiner respectfully disagrees.
Varadarajan teaches the trajectory prediction outputs 152 may contain a prediction that a particular surrounding agent is likely to cut in front of the vehicle 102 at a particular future time point, potentially causing a collision…the planning system 160 can generate a new planned vehicle path that avoids the potential collision and cause the vehicle 102 to follow the new planned path, e.g., by autonomously controlling the steering of the vehicle, and avoid the potential collision (see at least Varadarajan, para 0040-0041). Therefore, the prior art discloses the claim limitations as recited and the prior art and rejections have been maintained.
Regarding the applicant’s argument that “Nothing in the recited portions of Varadarajan…teaches or suggests selecting a trajectory…”, the examiner respectfully disagrees.
Varadarajan teaches …the trajectory prediction output includes, for each anchor trajectory, data characterizing, for each waypoint spatial location of the anchor trajectory, a probability distribution dependent on the waypoint spatial location…the probability distribution represents the space of predicted possible deviations from the anchor trajectory of the agent's actual future trajectory…the trajectory prediction output includes K probabilities or other similarity scores, one for each of the K anchor trajectories and when the anchor trajectories are learned, the system can generate the final trajectory…, i.e., select a trajectory… (see at least Varadarajan, para 0091-0094, also see para 0034-0035, para 0097-0108, para 0125-0126). Therefore, the prior art discloses the claim limitations as recited and the prior art and rejections have been maintained.
Regarding the applicant’s argument that “Nothing in the asserted combination of Hendy…teaches or suggests “…control movement of the at least one agent…”, the examiner respectfully disagrees.
Wang teaches …optimize the trajectories of the actors to increase the risk of an autonomy system failure… as the perturbation modifies the trajectories of the actors, the sensor data can be adjusted to accurately reflect the new state (e.g., velocity, location) of the actors (para 0044), i.e., controlling the at least one agent within the simulation environment and generating sensor data…generate perturbed trajectory for an actor that is indicative of one or more states of the actor… the updated trajectory for the subject vehicle can be indicative of one or more states … (para 0087 and para 0090-0091, Fig. 4-6), i.e., movement being controlled based on the updated trajectory. Therefore, the prior art discloses the claim limitations as recited and the prior art and rejections have been maintained.
Regarding the applicant’s argument that “Nothing in the recited portions of Wang…teaches or suggests generating sensor data corresponding to one or more sensors of the system under test based at least on the movement of the agent within the simulation environment…”, the examiner respectfully disagrees.
Wang… determines the interaction of the subject vehicle (e.g., vehicle 205 of FIG. 2) to the simulated sensor data (e.g., simulated sensor data 422 of FIG. 4) based on the new scene configuration… the computing system can update the sensor data (e.g., sensor data 255, simulated sensor data 422 of FIG. 4) that the subject vehicle (e.g., vehicle 205 of FIG. 2) observes…the computing system can evaluate the autonomy system based on the updated sensor data… Given a modified scene configuration, the testing system can use the LiDAR simulator to render a simulated point cloud (e.g., simulated sensor data 422), and then update the real LiDAR sweep with the modified regions (Wang, para 0097-0099, para 0113). Therefore, the prior art discloses the claim limitations as recited and the prior art and rejections have been maintained.
Claims 17 and 22 recite similar languages as (or a subset of) claim 1 and are rejected for similar reasons above.
With respect to the dependent claims 2-16 and 18-21, the Applicant provides no additional arguments other than their dependency from the independent claims 1 and 17. Because independent claims 1 and 17 are not allowable, dependent claims 2-16 and 18-21are not allowable.
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.
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.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claims 1, 5-7, 12-17, 19 and 21-22 are rejected under 35 U.S.C. 103 as being unpatentable over Hendy (US11912301, hereinafter Hendy) in view of Varadarajan (US20220297728, hereinafter Varadarajan) and further in view of Wang (US20250121852, hereinafter Wang).
As to claims 1, 17 and 22, Hendy teaches One or more processors, a system and a method comprising (see at least Hendy Fig. 9 and related text):
one or more circuits to (see at least Hendy Fig. 9 and related text):
generate a simulation environment for testing at least one of hardware or software of a system under test, the simulation environment corresponding to a scene including at least one path for vehicle traffic and one or more agents and a representation of the system under test (see at least Hendy col 2, lines 25-47: A scenario may refer to a real or virtual environment in which an autonomous vehicle may operate over a period of time. Within driving simulation systems, scenarios may be represented as virtual environments in which the software based systems and features of autonomous vehicles may be tested and validated; col 3, lines 22-44: A representation of the environment from a top-down perspective or other perspective can be generated based at least in part on the sensor data, also see Fig. 1, Fig. 3-5);
execute one or more time-steps of a simulation (see at least Hendy Fig. 2, Fig. 3 and related text);
for at least one agent of the one or more agents (see at least Hendy col 6 lines 1-10: predict probabilities associated with possible location and predicted trajectories of various objects or agents in the scenario to control operation of the autonomous vehicle):
Hendy further teaches one or more circuits to execute operations (see at least Hendy Fig. 9 and related text), a machine learning model (see at least Hendy col 3 lines 22-43, Fig. 4, Fig. 8) and predicting probabilities associated with predicted trajectories of various objects or agents in the scenario, models configured to can be generated based on the prediction probabilities and output to a planning system to control an operation of the autonomous vehicle, models configured to predict interactions or collisions between the vehicle 114 and other objects or agents, models to predict a future state of one or more objects in the environment (see at least Hendy col 6, lines 1-10).
Hendy does not teach generating navigation probability distributions for the at least one agent, individual navigation probability distributions of the navigation probability distributions defining a candidate trajectory for the at least one agent to follow with respect to the at least one path that is predicted to avoid collisions with one or more other agents; selecting a trajectory for the at least one agent corresponding to a selected navigation probability distribution of the navigation probability distributions for the at least one agent, control movement of the at least one agent within the simulation environment during execution of the one or more time-steps of the simulation based at least on the selected trajectory for the at least one agent, generate sensor data corresponding to one or more sensors of the system under test based at least on the movement of the at least one agent within the simulation environment; output the sensor data to the system under test; receive one or more signals from the system under test; and update a state of the representation of the system under test within the simulation environment based at least on the one or more signals received from the system under test, wherein the one or more signals are generated by the system under test based at least on the sensor data.
Varadarajan is directed to method for agent trajectory prediction. Varadarajan teaches each anchor trajectory characterize a possible future trajectory of the agent (see at least Varadarajan para 0086), the trajectory prediction output includes, for each anchor trajectory, data characterizing, for each waypoint spatial location of the anchor trajectory, a probability distribution dependent on the waypoint spatial location…the probability distribution represents the space of predicted possible deviations from the anchor trajectory of the agent's actual future trajectory…the trajectory prediction output includes K probabilities or other similarity scores, one for each of the K anchor trajectories and when the anchor trajectories are learned, the system can generate the final trajectory prediction out (see at least Varadarajan, para 0091-0094, also see para 0034-0035, para 0097-0108, para 0125-0126) Varadarajan further teaches the trajectory prediction outputs 152 may contain a prediction that a particular surrounding agent is likely to cut in front of the vehicle 102 at a particular future time point, potentially causing a collision. In this example, the planning system 160 can generate a new planned vehicle path that avoids the potential collision and cause the vehicle 102 to follow the new planned path, e.g., by autonomously controlling the steering of the vehicle, and avoid the potential collision (see at least Varadarajan, para 0040-0041).
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 Hendy so as to include generating navigation probability distributions, individual navigation probability distributions of the navigation probability distributions defining a candidate trajectory for the agent to follow with respect to the at least one path that is predicted to avoid collisions with one or more other agents and selecting a trajectory for the at least one agent corresponding to a selected navigation probability distribution of the navigation probability distributions for the at least one agent in view of Varadarajan et al. with a reasonable expectation of success. Those having ordinary skill in the art would understand that the method to determine a final trajectory using probability distribution of the trajectories of Varadarajan can be used in Hendy, as required by the claim. One of ordinary skill would have been motivated to combine Hendy and Varadarajan because this would have achieved the desirable result of providing an improved method for predicting the future behavior of road users by considering possible interactions among the input that may affect the future trajectories of agents in the scene (see at least Varadarajan para 0007).
Wang is directed to techniques for generating testing data for autonomous systems. Wang teaches …optimize the trajectories of the actors to increase the risk of an autonomy system failure. Additionally, as the perturbation modifies the trajectories of the actors, the sensor data can be adjusted to accurately reflect the new state (e.g., velocity, location) of the actors (i.e., controlling the at least one agent within the simulation environment and generating sensor data …). The testing system can use a high fidelity LiDAR simulator that modifies the sensor data accordingly, while also taking into account occlusions. After running the black-box autonomy system with modified sensor data as input, the testing system generates the planned trajectory based on the modified sensor data… (i.e., outputting the sensor data to the system under test; and updating a state of the representation of the system…) , …generate perturbed trajectory for an actor that is indicative of one or more states of the actor…as represented by a bounding shape, object highlighting… the updated trajectory for the subject vehicle can be indicative of one or more states…as represented by a bounding shape, object highlighting… (see at least Wang, para 0044, para 0087 and para 0090-0091; also see para 0046, para 0083-0086, 0092-0095, Fig. 4-6). Wang further teaches… determines the interaction of the subject vehicle (e.g., vehicle 205 of FIG. 2) to the simulated sensor data (e.g., simulated sensor data 422 of FIG. 4) based on the new scene configuration… the computing system can update the sensor data (e.g., sensor data 255, simulated sensor data 422 of FIG. 4) that the subject vehicle (e.g., vehicle 205 of FIG. 2) observes…the computing system can evaluate the autonomy system based on the updated sensor data… Given a modified scene configuration, the testing system can use the LiDAR simulator to render a simulated point cloud (e.g., simulated sensor data 422), and then update the real LiDAR sweep with the modified regions. (Wang, para 0097-0099, para 0113).
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 Hendy so as to include controlling the movement of the at least one agent within the simulation environment during execution of the one or more time-steps of the simulation based at least on the selected trajectory for the at least one agent, generate sensor data corresponding to one or more sensors of the system under test based at least on the movement of the at least one agent within the simulation environment; outputting the sensor data to the system under test; receive one or more signals from the system under test; and updating a state of the representation of the system under test within the simulation environment based at least on one or more signals received from the system under test, wherein the one or more signals are generated by the system under test based at least on the sensor data in view of Wang et al. with a reasonable expectation of success. Those having ordinary skill in the art would understand that the method to control actors in the simulation scenarios and generating sensor data related to the actors being controlled and updating the trajectory of the autonomous vehicle under test of Wang can be used in Hendy, as required by the claim. One of ordinary skill would have been motivated to combine Hendy and Wang because this would have achieved the desirable result of providing an improved method for the testing system to generate traffic scenarios in training and further improve the performance of autonomy systems (Wang para 0044).
As to claim 5, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Hendy further teaches wherein the one or more circuits are further to compute the navigation probability distributions for the at least one agent based at least on a rasterized map that includes a two-dimensional (2D) top-down view of the scene (see at least Hendy col 4, lines 26-49: a top-down representation of the scenario, also see Fig. 1, Fig. 5).
As to claim 6, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Varadarajan further teaches wherein individual navigation probability distributions of the navigation probability distributions are generated based at least on a Gaussian distribution, and the one or more circuits are further to compute, for the individual navigation probability distributions for the at least one agent, the candidate trajectory using a mean vector of the Gaussian distribution (see at least Varadarajan para 0126 for normal distribution having a mean at different time assigned to waypoint spatial location; also see para 0009 for Gaussian mixture model).
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 Hendy so as to include wherein individual navigation probability distributions of the navigation probability distributions are generated based at least on a Gaussian distribution, and the one or more circuits are further to compute, for the individual navigation probability distributions, the candidate trajectory using a mean vector of the Gaussian distribution in view of Varadarajan et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Varadarajan because this would have achieved the desirable result of providing an improved method for predicting the future behavior of road users by considering possible interactions among the input that may affect the future trajectories of agents in the scene (see at least Varadarajan para 0007).
As to claims 7 and 19, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1 and the system of claim 17.
Varadarajan further teaches wherein the selected navigation probability distribution for the at least one agent is randomly selected from the navigation probability distributions for the at least one agent (see at least Varadarajan para 0120-0121 for an optimizer being used for training the model to generate accurate trajectory prediction outputs; para 0086 for each anchor trajectory characterizes a possible future trajectory of the agent and includes data specifying a sequence of multiple waypoint spatial locations in the environment that each correspond to a possible position of the agent at a respective future time point. That is, each anchor trajectory defines a different possible future path through the environment that could be traversed by the agent after the current time point).
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 Hendy so as to include wherein the selected navigation probability distribution is randomly selected from the navigation probability distributions in view of Varadarajan et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Varadarajan because this would have achieved the desirable result of providing a method for predicting the future behavior of road users by considering possible interactions among the input that may affect the future trajectories of agents in the scene (see at least Varadarajan para 0007).
As to claim 12, Hendy in view of Varadarajan and Wang teaches the processor of claim 1.
Varadarajan further teaches wherein the one or more agents include a plurality of agents, and the one or more circuits are further to:
search across a plurality of time-steps to determine a number of collisions impacting the plurality of agents (see at least Varadarajan para 0040-0041 for predicting a particular agent is likely to cause a collision); and
compute at least a collision statistic based at least on the search (see at least Varadarajan para 0040-0041 for predicting a particular agent is likely to cause a collision).
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 Hendy so as to include searching across a plurality of time-steps to determine a number of collisions impacting the plurality of agents and computing at least a collision statistic based at least on the search in view of Varadarajan et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Varadarajan because this would have achieved the desirable result of providing a method for predicting the future behavior of road users by considering possible interactions among the input that may affect the future trajectories of agents in the scene (see at least Varadarajan para 0007).
As to claim 13, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Hendy further teaches wherein the one or more circuits are further to search across a plurality of time-steps for at least one sequence of candidate trajectories that does not involve a collision between the one or more agents over a duration of the simulation (see at least Hendy col 5, line 43-col 6, line 23: multi-dimensional vector associated with the scenario may be determined by providing the top-down representation of the scenario ( or plurality of top-down representations corresponding to different points in time) as input to a trained model comprising a neural network…output vehicle control action to be taken by an autonomous vehicle).
As to claim 14, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Hendy further teaches wherein the one or more circuits are further to:
execute a plurality of simulation in parallel (see at least Hendy col 6 lines 24-29 for generating a plurality of channels, col 5, lines 42-63 for neural network); and
search across a plurality of time-steps for individual simulation rollouts of the plurality of simulation to determine a number of collisions between the one or more agents (see at least Hendy see at least Hendy col 5, line 43-col 6, line 23: models configured to predict interactions or collisions between the vehicle 114 and other objects or agents, models to predict a future state of one or more 10 objects in the environment, also see col 5, lines 42-63 for neural network).
As to claim 15, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Hendy further teaches wherein the one or more circuits are further to cause display of at least one of:
one or more simulation metrics based at least on a number of collisions between the one or more agents (see at least Hendy col 5, line 43-col 6, line 23: models configured to predict interactions or collisions between the vehicle 114 and other objects or agents, models to predict a future state of one or more 10 objects in the environment); or
a graphical rendering that illustrates a motion of the one or more agents within the scene (see at least Hendy Fig. 1, Fig. 5 and related text).
As to claims 16 and 21, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1 and the system of claim 17.
Hendy further teaches wherein the processor is comprised in at least one of:
a control system for an autonomous or semi-autonomous machine;
a perception system for an autonomous or semi-autonomous machine;
a system for performing simulation operations;
a system for performing digital twin operations;
a system for performing light transport simulation;
a system for performing collaborative content creation for 3D assets;
a system for performing deep learning operations;
a system for performing real-time streaming;
a system for presenting one or more of augmented reality content, virtual reality content, or mixed reality content;
a system implemented using an edge device;
a system implemented using a robot; a system for performing conversational Al operations;
a system for generating synthetic data;
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 at least Hendy Fig. 9 and related text for processors for the vehicle and computing devices and col 3, lines 52-67, col 19, line 51-col 20, line 32).
Claims 2-4, 8-11, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Hendy in view of Varadarajan and Wang as applied to claim 1 above, and further in view of Houston (US11354913, hereinafter Houston).
As to claim 2, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Varadarajan further teaches wherein the one or more circuits are further to compute the navigation probability distributions for the at least one agent based at least on an image of the scene (see at least Varadarajan para 0026-0028 and para 0033-0034).
Hendy modified by Varadarajan and Wang does not explicitly teach the image is a rasterized image.
However, in the same field of endeavor, Houston teaches trained CNNs can be used to make predictions based on rasterized images of the vehicle environment. The rasterized images may be top-down images generated from camera images captured by the vehicle's cameras (see at least Houston col 2, lines 49-58, Fig. 2).
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 Hendy so as to include generating rasterized images of vehicle environment from camera images in view of Houston et al. with a reasonable expectation of success. Those having ordinary skill in the art would understand that image-based prediction systems for making predictions about predicted trajectories of obstacles of Houston can be used in Hendy, as required by the claim. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claims 3 and 18, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1 and the system of claim 17.
Varadarajan further teaches wherein the one or more circuits are further to compute the navigation probability distributions based at least on an image of the scene (see at least Varadarajan para 0026-0028 and para 0033-0034).
Houston further teaches wherein the one or more circuits are further to compute the navigation probability distributions based at least on one or more of:
a rasterized map of the at least one path, the rasterized map being generated with respect to a coordinate frame referenced to a position of the at least one agent; or
a rasterized representation of a location of one or more other agents of the one or more agents, the rasterized representation being generated with respect to the coordinate frame referenced to the position of the at least one agent (see at least Houston col 2, lines 49-58 for imaged based prediction systems based on rasterized images, also see col 8, lines 41-53, Fig. 2).
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 Hendy so as to include wherein the one or more circuits are further to compute the navigation probability distributions based at least on at least one of: a rasterized map of the at least one path, the rasterized map being generated with respect to a coordinate frame referenced to a position of the agent; or a rasterized representation of a location of one or more other agents of the one or more agents, the rasterized representation being generated with respect to the coordinate frame referenced to the position of the agent in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claim 4, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Varadarajan further teaches wherein the one or more circuits are further to compute the navigation probability distributions for the at least one agent based at least on an image of the scene (see at least Varadarajan para 0026-0028 and para 0033-0034).
Houston further teaches wherein the one or more circuits are further to compute the navigation probability distributions based at least on a rasterized target destination of the agent, the rasterized target destination generated with respect to a coordinate frame referenced to a position of the agent (see at least Houston col 2, lines 49-58 for imaged based prediction systems based on rasterized images; col 6, lines 4-45 for map data, target destinations for navigation of the vehicle; also see col 8, lines 41-53, Fig. 2).
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 Hendy so as to include wherein the one or more circuits are further to compute the navigation probability distributions based at least on a rasterized target destination of the agent, the rasterized target destination generated with respect to a coordinate frame referenced to a position of the agent in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claims 8 and 20, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1 and the system of claim 17.
Varadarajan further teaches wherein the one or more circuits are further to compute the navigation probability distributions for the at least one agent based at least on an image of the scene (see at least Varadarajan para 0026-0028 and para 0033-0034).
Houston further teaches wherein the one or more circuits are further to execute a motion prediction model to compute the navigation probability distributions based at least on a rasterized image of the scene (see at least Houston Fig. 2 and related text).
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 Hendy so as to include wherein the one or more circuits are further to execute a motion prediction model to compute the navigation probability distributions based at least on a rasterized image of the scene in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claim 9, Hendy in view of Varadarajan, Wang and Houston teaches the one or more processors of claim 8.
Houston further teaches wherein the motion prediction model includes at least one of a machine learning model or a rules-based policy model (see at least Houston col 5 line 31-col 6 line 3; also see Fig. 2 and related text).
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 Hendy so as to include wherein the motion prediction model includes at least one of a machine learning model or a rules-based policy model in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claim 10, Hendy in view of Varadarajan, Wang and Houston teaches the one or more processors of claim 8.
Houston further teaches wherein the motion prediction model comprises a machine learning model trained to compute outputs corresponding to human driving decisions as represented using a training dataset derived using recorded video of live traffic scenarios (see at least Houston col 5 line 31-col 6 line 3; also see Fig. 2 and related text).
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 Hendy so as to include wherein the motion prediction model comprises a machine learning model trained to compute outputs corresponding to human driving decisions as represented using a training dataset derived using recorded video of live traffic scenarios in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
As to claim 11, Hendy in view of Varadarajan and Wang teaches the one or more processors of claim 1.
Houston further teaches wherein the one or more time-steps of the simulation comprises a plurality of time-steps, individual time-steps of the plurality of time-steps including a re-planning operation, further wherein the one or more circuits are further to compute, during the re-planning operation, the navigation probability distributions for the at least one agent and to determine the trajectory (see at least Houston col 5 line 31-col 6 line 3 for a sequence of sensor data at times t0 and ti… update the configuration parameters of the machine learning model…the machine learning model may be trained iteratively…; also see Fig. 2 and related text).
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 Hendy so as to include wherein the one or more circuits are further to execute a simulation rollout comprising a plurality of time-steps, individual time-steps of the plurality of time-steps including a re-planning operation, further wherein the one or more circuits are further to compute, during the re-planning operation, the navigation probability distributions and to select the trajectory in view of Houston et al. with a reasonable expectation of success. One of ordinary skill would have been motivated to combine Hendy and Houston because this is merely combining prior art elements according to known methods to yield predictable results (KSR International Co. v. Teleflex Inc., 550 U.S. 398, 82 USPQ2d 1385 (2007)).
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 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.
Examiner’s Notes
Examiner has cited particular columns/paragraph and line numbers in the references applied to the claims above for the convenience of the applicant. Although the specified citations are representative of the teachings of the art and are applied to specific limitations within the individual claim, other passages and figures may apply as well. It is respectfully requested from the applicant in preparing responses, to fully consider the references in entirety as potentially teaching all or part of the claimed invention, as well as the context of the passage as taught by the prior art or disclosed by the examiner.
In the case of amending the claimed invention, Applicant is respectfully requested to indicate the portion(s) of the specification which dictate(s) the structure relied on for proper interpretation and also to verify and ascertain the metes and bounds of the claimed invention. This will assist in expediting compact prosecution. MPEP 714.02 recites: “Applicant should also specifically point out the support for any amendments made to the disclosure. See MPEP §2163.06. An amendment which does not comply with the provisions of 37 CFR 1.121(b), (c), (d), and (h) may be held not fully responsive. See MPEP § 714.” Amendments not pointing to specific support in the disclosure may be deemed as not complying with provisions of 37 C.F.R. 1.131(b), (c), (d), and (h) and therefore held not fully responsive. Generic statements such as "Applicants believe no new matter has been introduced" may be deemed insufficient.
Inquiry
Any inquiry concerning this communication or earlier communications from the examiner should be directed to HONGYE LIANG whose telephone number is (571)272-5410. The examiner can normally be reached on Monday-Friday 9:00am-5:00pm.
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, Rachid Bendidi can be reached on 571-272-4896. 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.
/HONGYE LIANG/Primary Examiner, Art Unit 3664