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 .
DETAILED ACTION
1. 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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 09/26/2025 has been entered.
2. The amendment filed on 09/26/2025 has been received and considered. Claims 1-3, 6-11, 13-18, and 23-28 are presented for examination.
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.
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.
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.
3. Claims 1-3, 6-11, 13-18, 23-24, and 27-28 are rejected under 35 U.S.C. 103 as being unpatentable over Dolben et al. (US 11731652 B2), further in view of Mian et al. (“Modeling of individual differences in driver behavior”).
As per Claim 1, Dolben et al. teaches a system (Figure 2) comprising:
one or more processors (Fig. 7 and the description); and
one or more computer-readable media storing computer-executable instructions that, when executed (Fig. 7 and the description) comprising:
receiving log data associated with operation of a vehicle in a real-world driving environment, wherein the log data indicates a real-world trajectory of an agent different from the vehicle in the real-world driving environment (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles. The mission logs include sensor data collected by sensors of the fleet of vehicles from various sources and geographic locations. Sensor data may be collected by, for example, sensors mounted to the vehicles themselves and/or sensors on computing devices associated with users riding within the fleet of vehicles (e.g., user mobile devices). For example, the simulation module 210 can be configured to communicate and operate with at least one data store 212 that is accessible to the simulation module 210. The data store 220 can be configured to store and maintain various types of data, such as mission logs associated with the fleet of vehicles, sensor data captured by the fleet of vehicles, disengagement information, and the like.”);
determining a driving … of the agent in the real-world driving environment (Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”, “behavior of an agent in a computer simulation can be based on a naïve agent model. A naïve agent model can generate behavior of an agent that does not react to other objects. The behavior of the agent can be based on a trajectory that follows a specified path at a specified speed. The specified path can include a list of points, or a series of positions, for the agent. For example, a naïve agent model can generate a behavior of an agent (e.g., simulated vehicle) that drives along a road.”; Col. 8 lines 32-45 “behavior of an agent in a computer simulation can be based on a heuristic agent model. A heuristic agent model can generate behavior of an agent that reacts to other objects”; Col. 9 lines 27-48 “The machine learning agent model can train the one or more machine learning models based on training data that includes data associated with how objects behave in various scenarios. The various scenarios can include, for example, real-world scenarios encountered by a driver or an autonomous vehicle system. The training data can include sensor data associated with the various scenarios. For example, the training data can be associated with behavior of vehicles at an intersection or behavior of vehicles on a freeway.”), …
executing a driving simulation including a simulated vehicle associated with the vehicle in the real-world driving environment and a simulated agent associated with the agent in the real-world driving environment (Col. 5 lines 20-34, “computer simulation of realistic agent behavior in various virtual environments, such as scenarios. In various embodiments, behavior of an agent (e.g., a simulated dynamic object, a simulated vehicle, etc.) in an environment involving an autonomous vehicle (or ego),” Fig. 4B, Fig. 5A step 510 “
PNG
media_image1.png
157
566
media_image1.png
Greyscale
), wherein executing the driving simulation comprises:
controlling the simulated vehicle using an autonomous vehicle controller in a simulated environment (Fig. 2, Col. 12 lines 58-65 “In FIG. 2, the dynamics simulator 220 can be configured to generate movement information associated with an autonomous vehicle based on control instructions outputted by an autonomous vehicle system of the autonomous vehicle.”);
controlling the simulated agent using a second vehicle controller different from the autonomous vehicle controller (Fig. 2; Col. 7 lines 61-67, Col. 8 lines 1-6, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. The computer simulation can be used, for example, to test an autonomous vehicle system (e.g., ego). An agent model can generate behavior of an agent based on a trajectory. The trajectory can be selected from candidate trajectories generated by the agent model. In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”; Col. 13 lines 35-49 “The example agent controller system 300 can generate behavior of an agent in a computer simulation. In various embodiments, the example agent controller system 300 can be implemented in or with the agent models module 214 and the world simulator module 216 of the example system 200 of FIG. 2. As shown, the example agent controller system 300 can include implied perception 302, contextual information 304, a heuristic agent model 306, a planner 308, a machine learning agent model 310, a naïve agent model 312, a trajectory generator 316, and a drive controller 318.”);
determining, using the second vehicle controller (Fig. 2-3; Col. 7 lines 61-67, Col. 8 lines 1-6, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation”), a simulated agent trajectory for the simulated agent during the driving simulation (Col. 6 lines 14-22 “a machine learning model can be trained based on training data that includes trajectories of vehicles encountered in real-world scenarios. Based on the training data, the machine learning model can be trained to generate candidate trajectories or select candidate trajectories that are similar to those trajectories of vehicles encountered in real-world scenarios. Behavior of an agent can be simulated based on the generated and selected candidate trajectories.”; Col. 13 lines 35-49 “The example agent controller system 300 can generate behavior of an agent in a computer simulation. In various embodiments, the example agent controller system 300 can be implemented in or with the agent models module 214 and the world simulator module 216 of the example system 200 of FIG. 2. As shown, the example agent controller system 300 can include implied perception 302, contextual information 304, a heuristic agent model 306, a planner 308, a machine learning agent model 310, a naïve agent model 312, a trajectory generator 316, and a drive controller 318.”), wherein the simulated agent trajectory diverges from the real-world trajectory of the agent in the real-world driving environment (Col. 5 lines 31-43 “a trajectory can be a list of points, or a series of positions, with associated velocity information. The velocity information can include a speed associated with a point or a time associated with a point, which can imply the speed. The velocity information also can include a direction associated with a point. Based on contextual information associated with the environment that is captured using the implied perception system for the agent, one or more constraints are determined. In some examples, the implied perception system may be a system that takes into account contextual information of the environment from a data store that can be used to generate trajectories in the environment using a path planner of the agent.”; Col. 9 lines 20-67, Col. 10 lines 1-5 “The various scenarios can include, for example, real-world scenarios encountered by a driver or an autonomous vehicle system. The training data can include sensor data associated with the various scenarios. … Based on the input scenario, the machine learning agent model can generate behavior of an agent corresponding to normal driving behavior in the input scenario. As another example, a machine learning agent model can train a machine learning model with training data associated with non-standard driving behavior, such as performing a cut in.”), and wherein the simulated agent trajectory is based on the driving style type of the agent in the real-world driving environment (Col. 10 lines 7-33 “Behavior of an agent can be based on a combination of agent models. For example, behavior of an agent can be based on a combination of a naïve agent model, a heuristic agent model, and a machine learning agent model. Different agent models can be associated with different environments, different events, or different situations… Behavior of an agent in this computer simulation can be based on a combination of agent models associated with the environment, the event, the first situation, and the second situation.”); and
controlling, using the second vehicle controller, the simulated agent during the driving simulation based on the simulated agent trajectory (Fig. 3, Col. 13 lines 35-49 “The example agent controller system 300 can generate behavior of an agent in a computer simulation. In various embodiments, the example agent controller system 300 can be implemented in or with the agent models module 214 and the world simulator module 216 of the example system 200 of FIG. 2. As shown, the example agent controller system 300 can include implied perception 302, contextual information 304, a heuristic agent model 306, a planner 308, a machine learning agent model 310, a naïve agent model 312, a trajectory generator 316, and a drive controller 318.”; Col. 15 lines 32-55 “In FIG. 3, the trajectory generator 316 can be configured to generate candidate trajectories for an agent and select a trajectory from the candidate trajectories.”).
Dolben et al. fails to teach explicitly a driving style type based on at least one of: a driving aggression score of the agent; a driving skill score of the agent; a reaction time score of the agent; or a law abidance score of the agent.
Mian et al. teaches a driving style type based on at least one of: a driving aggression score of the agent; a driving skill score of the agent; a reaction time score of the agent; or a law abidance score of the agent (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
Dolben et al. and Mian et al. are analogous art because they are both related to a method for simulating vehicle behaviors.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the teaching of Mian with autonomous vehicle simulation computerized simulations of reactive agents for simulating vehicle behaviors of Dolben et al.’s invention to reproduce individual differences in driving behaviors for realistic traffic simulation (Mian et al.: Abstract).
As per Claim 2, Dolben et al. teaches the operations further comprising: determining a second driving… associated with a second real-world agent vehicle in the real-world driving environment, based on the log data, wherein the second driving style type is different from the first driving style type (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles.”; Col. 7 lines 41-47 “a computer simulation can involve a combination of simulated features including … dynamic objects, such as agents (e.g., … vehicles, …), … simulated features of a computer simulation can be based on captured sensor data.” Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”); and
controlling a second simulated agent vehicle during the driving simulation based on the second driving … (Fig. 2; Col. 7 lines 61-67, Col. 8 lines 1-6, Col. 13 lines 35-49).
Dolben et al. fails to teach explicitly a driving style type.
Mian et al. teaches a driving style type (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 3, Dolben et al. fails to teach explicitly wherein determining the driving style of the agent in the real-world driving environment comprises: determining, based on the log data, a first value associated with a first instance of a driving behavior of the agent, and a second value associated with a second instance of the driving behavior of the agent; and determining a distribution associated with the driving behavior of the agent based on the first value and the second value, wherein determining the simulated agent trajectory of the simulated agent comprises sampling a third value from the distribution.
Mian et al. teaches wherein determining the driving style score of the agent in the real-world driving environment comprises: determining, based on the log data, a first value associated with a first instance of a driving behavior of the agent, and a second value associated with a second instance of the driving behavior of the agent ((section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”)); and
determining a distribution associated with the driving behavior of the agent based on the first value and the second value, wherein determining the simulated agent trajectory of the simulated agent comprises sampling a third value from the distribution ((section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”)).
As per Claim 6 and 14, Dolben et al. teaches a method (Figure 2 & 5A-5B) comprising:
receiving log data associated with a real-world driving environment, wherein the log data indicates a real-world trajectory of a real-world vehicle in the real-world driving environment (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles. The mission logs include sensor data collected by sensors of the fleet of vehicles from various sources and geographic locations. Sensor data may be collected by, for example, sensors mounted to the vehicles themselves and/or sensors on computing devices associated with users riding within the fleet of vehicles (e.g., user mobile devices). For example, the simulation module 210 can be configured to communicate and operate with at least one data store 212 that is accessible to the simulation module 210. The data store 220 can be configured to store and maintain various types of data, such as mission logs associated with the fleet of vehicles, sensor data captured by the fleet of vehicles, disengagement information, and the like.”);
determining, based on movements of the real-world vehicle in the log data, a driving… of the real-world vehicle (Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”, “behavior of an agent in a computer simulation can be based on a naïve agent model. A naïve agent model can generate behavior of an agent that does not react to other objects. The behavior of the agent can be based on a trajectory that follows a specified path at a specified speed. The specified path can include a list of points, or a series of positions, for the agent. For example, a naïve agent model can generate a behavior of an agent (e.g., simulated vehicle) that drives along a road.”; Col. 8 lines 32-45 “behavior of an agent in a computer simulation can be based on a heuristic agent model. A heuristic agent model can generate behavior of an agent that reacts to other objects”; Col. 9 lines 27-48 “The machine learning agent model can train the one or more machine learning models based on training data that includes data associated with how objects behave in various scenarios. The various scenarios can include, for example, real-world scenarios encountered by a driver or an autonomous vehicle system. The training data can include sensor data associated with the various scenarios. For example, the training data can be associated with behavior of vehicles at an intersection or behavior of vehicles on a freeway.”),…
executing a simulation including a simulated vehicle based on the real-world vehicle, wherein the simulated vehicle is controlled during the simulation by a planning component (Col. 5 lines 20-34, “computer simulation of realistic agent behavior in various virtual environments, such as scenarios. In various embodiments, behavior of an agent (e.g., a simulated dynamic object, a simulated vehicle, etc.) in an environment involving an autonomous vehicle (or ego),” Fig. 4B, Fig. 5A step 510 “
PNG
media_image1.png
157
566
media_image1.png
Greyscale
, Fig. 2-3; Col. 7 lines 61-67, Col. 8 lines 1-6, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation”; Col. 12 lines 58-65 “In FIG. 2, the dynamics simulator 220 can be configured to generate movement information associated with an autonomous vehicle based on control instructions outputted by an autonomous vehicle system of the autonomous vehicle.”);
determining, using the planning component, a simulated trajectory for the simulated vehicle during the simulation (Col. 6 lines 14-22 “a machine learning model can be trained based on training data that includes trajectories of vehicles encountered in real-world scenarios. Based on the training data, the machine learning model can be trained to generate candidate trajectories or select candidate trajectories that are similar to those trajectories of vehicles encountered in real-world scenarios. Behavior of an agent can be simulated based on the generated and selected candidate trajectories.”; Col. 13 lines 35-49 “The example agent controller system 300 can generate behavior of an agent in a computer simulation. In various embodiments, the example agent controller system 300 can be implemented in or with the agent models module 214 and the world simulator module 216 of the example system 200 of FIG. 2. As shown, the example agent controller system 300 can include implied perception 302, contextual information 304, a heuristic agent model 306, a planner 308, a machine learning agent model 310, a naïve agent model 312, a trajectory generator 316, and a drive controller 318.”), wherein the simulated trajectory diverges from the real-world trajectory of the real-world vehicle (Col. 5 lines 31-43 “a trajectory can be a list of points, or a series of positions, with associated velocity information. The velocity information can include a speed associated with a point or a time associated with a point, which can imply the speed. The velocity information also can include a direction associated with a point. Based on contextual information associated with the environment that is captured using the implied perception system for the agent, one or more constraints are determined. In some examples, the implied perception system may be a system that takes into account contextual information of the environment from a data store that can be used to generate trajectories in the environment using a path planner of the agent.”; Col. 9 lines 20-67, Col. 10 lines 1-5 “The various scenarios can include, for example, real-world scenarios encountered by a driver or an autonomous vehicle system. The training data can include sensor data associated with the various scenarios. … Based on the input scenario, the machine learning agent model can generate behavior of an agent corresponding to normal driving behavior in the input scenario. As another example, a machine learning agent model can train a machine learning model with training data associated with non-standard driving behavior, such as performing a cut in.”), and wherein the simulated agent trajectory is based on the driving style type of the agent in the real-world driving environment (Col. 10 lines 7-33 “Behavior of an agent can be based on a combination of agent models. For example, behavior of an agent can be based on a combination of a naïve agent model, a heuristic agent model, and a machine learning agent model. Different agent models can be associated with different environments, different events, or different situations… Behavior of an agent in this computer simulation can be based on a combination of agent models associated with the environment, the event, the first situation, and the second situation.”), and wherein determining the simulated trajectory is based on the driving… of the real-world vehicle; and
controlling, using the planning component, the simulated vehicle during the simulation, based on the simulated trajectory (Fig. 3, Col. 13 lines 35-49 “The example agent controller system 300 can generate behavior of an agent in a computer simulation. In various embodiments, the example agent controller system 300 can be implemented in or with the agent models module 214 and the world simulator module 216 of the example system 200 of FIG. 2. As shown, the example agent controller system 300 can include implied perception 302, contextual information 304, a heuristic agent model 306, a planner 308, a machine learning agent model 310, a naïve agent model 312, a trajectory generator 316, and a drive controller 318.”; Col. 15 lines 32-55 “In FIG. 3, the trajectory generator 316 can be configured to generate candidate trajectories for an agent and select a trajectory from the candidate trajectories.”).
Dolben et al. fails to teach explicitly a driving style type of the real-world vehicle, based on at least one of: a driving aggression score of the real-world vehicle a driving skill score of the real-world vehicle a reaction time score of the real-world vehicle or a law abidance score of the real-world vehicle.
Mian et al. teaches a driving style type of the real-world vehicle, based on at least one of: a driving aggression score of the real-world vehicle a driving skill score of the real-world vehicle a reaction time score of the real-world vehicle or a law abidance score of the real-world vehicle (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 7 and 15, Dolben et al. teaches the operations further comprising: determining a second driving … associated with a second real-world agent vehicle in the real-world driving environment, based on the log data, wherein the second driving style type is different from the first driving … (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles.”; Col. 7 lines 41-47 “a computer simulation can involve a combination of simulated features including … dynamic objects, such as agents (e.g., … vehicles, …), … simulated features of a computer simulation can be based on captured sensor data.” Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”); and
controlling a second simulated agent vehicle during the driving simulation based on the second driving … (Fig. 2; Col. 7 lines 61-67, Col. 8 lines 1-6, Col. 13 lines 35-49).
Dolben et al. fails to teach explicitly a driving style type.
Mian et al. teaches a driving style type (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 8, Dolben et al. teaches wherein the second simulated object is at least one of a pedestrian object or a non-motorized vehicle object within the simulation (Col. 6 lines 45-60 “a computer simulation can involve a combination of simulated features including static objects (e.g., buildings, traffic signs, etc.), semi-static objects (e.g., construction areas, temporary signs, temporary structures, etc.), dynamic objects, such as agents (e.g., pedestrians, vehicles, cyclists, animals, etc.), or a combination thereof. Further, the simulated features of the computer simulation can include various road types such as roads, freeways, and intersections. In some cases, simulated features of a computer simulation can be based on captured sensor data. For example, simulated features of a computer simulation can be based on image data captured by optical cameras, point clouds captured by a LiDAR system, or radar data captured by a radar system. The simulated features of a computer simulation can be based on mission data associated with a mission travelled by a vehicle. The mission data can include sensor data captured during the course of the mission and various environmental and contextual data such as geographical location, time of day, and weather.”).
As per Claim 9 and 16, Dolben et al. fails to teach explicitly wherein determining the first driving style type of the real-world first vehicle comprises: determining, based on the log data, a first value associated with a first instance of a driving behavior of the real-world vehicle; and aggregating the first value and the second value to determine for the driving style type of the real-world vehicle.
Mian et al. teaches wherein determining the first driving style type of the real-world first vehicle comprises: determining, based on the log data, a first value associated with a first instance of a driving behavior of the real-world vehicle (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”); and
aggregating the first value and the second value to determine for the driving style type of the real-world vehicle (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 10 and 17, Dolben et al. teaches further comprising determining, based on the log data, a destination in the real-world driving environment associated with the real-world vehicle (Col. 14 lines 9-34 “The objective of the agent can be to travel to a particular destination in the environment or to perform a particular maneuver”, Fig. 4B); wherein determining the simulated trajectory of the simulated vehicle is based on the destination (Col. 14 lines 9-34 “The objective of the agent can be to travel to a particular destination in the environment or to perform a particular maneuver”, Fig. 4B).
As per Claim 11 and 18, Dolben et al. teaches further comprising:
determining second log data associated with a second real-world vehicle in the real-world driving environment (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles.”; Col. 7 lines 41-47 “a computer simulation can involve a combination of simulated features including … dynamic objects, such as agents (e.g., … vehicles, …), … simulated features of a computer simulation can be based on captured sensor data.” Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”); and
determining a second driving …of the second real- world vehicle, based on the second log data (Col. 6 lines 45-59 “the simulation module 210 has access to mission logs associated with a fleet of vehicles.”; Col. 7 lines 41-47 “a computer simulation can involve a combination of simulated features including … dynamic objects, such as agents (e.g., … vehicles, …), … simulated features of a computer simulation can be based on captured sensor data.” Fig. 4A; Col. 7 lines 61-67, Col. 8 lines 1-15, “In FIG. 2, the agent models module 214 can be configured to generate agent models on which behavior of an agent in a computer simulation can be based. …In some cases, various agent models can be used to generate behavior of an agent. The various agent models can include, for example, naïve agent models, heuristic agent models, and machine learning agent models. The various agent models can be used individually, in combination, or sequentially to generate the behavior of the agent.”),
wherein determining the simulated trajectory of the simulated vehicle is based on the second driving … of the second real-world vehicle (Fig. 2; Col. 7 lines 41-47 “a computer simulation can involve a combination of simulated features including … dynamic objects, such as agents (e.g., … vehicles, …), … simulated features of a computer simulation can be based on captured sensor data.”; Col. 7 lines 61-67, Col. 8 lines 1-6, Col. 13 lines 35-49).
Dolben et al. fails to teach explicitly driving style type.
Mian et al. teaches driving style type (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 23-24, Dolben et al. teaches wherein the log data comprises log data captured by a first vehicle in the real-world driving environment, and wherein the real-world vehicle is a second agent vehicle different from the first vehicle in the real-world driving environment (Col. 6 lines 45-59 “Sensor data may be collected by, for example, sensors mounted to the vehicles themselves and/or sensors on computing devices associated with users riding within the fleet of vehicles (e.g., user mobile devices). For example, the simulation module 210 can be configured to communicate and operate with at least one data store 212 that is accessible to the simulation module 210. The data store 220 can be configured to store and maintain various types of data, such as mission logs associated with the fleet of vehicles, sensor data captured by the fleet of vehicles, disengagement information, and the like.”).
As per Claim 27, Dolben et al. fails to teach explicitly wherein determining the driving style type of the real-world vehicle is based on at least two of: the driving aggression score of the real-world vehicle; the driving skill score of the real-world vehicle; and the reaction time score of the real-world vehicle.
Mian et al. teaches wherein determining the driving style type of the real-world vehicle is based on at least two of: the driving aggression score of the real-world vehicle; the driving skill score of the real-world vehicle; and the reaction time score of the real-world vehicle (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
As per Claim 28, Dolben et al. fails to teach explicitly wherein determining the driving style type of the real-world vehicle is further based on at least one of: the law abidance score of the real-world vehicle; or an average turn signal usage score of the real-world vehicle.
Mian et al. teaches wherein determining the driving style type of the real-world vehicle is further based on at least one of: the law abidance score of the real-world vehicle; or an average turn signal usage score of the real-world vehicle (section 3 “OCEAN factors for each driver class i.e. over-controlled, resilient, and under-controlled”, “the OCEAN traits to the IDM and MOBIL parameters”).
4. Claims 25-26 are rejected under 35 U.S.C. 103 as being unpatentable over Dolben et al. (US 11731652 B2), in view of Mian et al. (“Modeling of individual differences in driver behavior”), further in view of Xue et al. (“Rapid Driving Style Recognition in Car-Following Using Machine Learning and Vehicle Trajectory Data”) and Li et al. (Combined Trajectory Planning and Tracking for Autonomous Vehicle Considering Driving Styles).
Dolben et al. as modified by Mian et al. teaches most all the instant invention as applied to claims 1-3, 6-11, 13-18, 23-24, and 27-28 above.
As per Claim 25-26, Dolben et al. as modified by Mian et al. fails to teach explicitly wherein determining the simulated trajectory for the simulated vehicle during the simulation comprises: determining, by the planning component, a second driving style type associated with the simulated trajectory; and selecting the simulated trajectory for controlling the simulated vehicle, based on the driving style type of the real-world vehicle matching the second driving style type associated with the simulated trajectory.
Xue et al. teaches wherein determining the simulated trajectory for the simulated vehicle during the simulation comprises: determining, by the planning component, a second driving style type associated with the simulated trajectory (Figure 1 “Driving Style Recognition with Supervised Machine Learning”; section 4 “The input features of machine learning algorithms are extracted by DFT, DWT, and statistical methods from trajectory features,”).
Further Li et al. teaches selecting the simulated trajectory for controlling the simulated vehicle, based on the driving style type of the real-world vehicle matching the second driving style type associated with the simulated trajectory (Figure 6, “selecting corresponding style for the lane-changing, and the local vehicle enters in the free running mode. When the triggering condition of lane-changing is reached, the vehicle begins to change lanes in the corresponding driving style” on the right column of Pg 9458).
Dolben et al., Mian et al., Xue et al., and Li et al. are analogous art because they are all related to a method for simulating vehicle behaviors.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to combine the teachings of Xue et al. and Li et al. with autonomous vehicle simulation computerized simulations of reactive agents for simulating vehicle behaviors of Dolben et al. as modified by Mian et al.’s invention to reproduce individual differences in driving behaviors for realistic traffic simulation (Mian et al.: Abstract), to provide a system with an accurate driving style recognition microsimulation system (Xue et al.: Abstract), and to provide a novel system for improving driving safety that can be utilized in the autonomous vehicle control field reflecting driving styles (Li et al.: Abstract).
Response to Arguments
5. Applicant's arguments filed 09/26/2025 have been fully considered but they are not persuasive.
Examiner respectfully withdraws Claim Rejections - 35 USC § 112 in view of the amendment and/or applicant’s arguments.
Applicant’s arguments with respect to claims 1, 6 and 14 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 – Dolben et al. (US 11731652 B2), further in view of Mian et al. (“Modeling of individual differences in driver behavior”).
Conclusion
6. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Witt et al. (“Driver profiling – Data-based identification of driver behavior dimensions and affecting driver characteristics for multi-agent traffic simulation”)
Yuhara et al. (“Multi-driver agent-based traffic simulation systems for evaluating the effects of advanced driver assistance systems on road traffic accidents”)
Bacchiani et al. (“Microscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement Learning”).
Basir et al. (US 20160110650 A1)
7. Any inquiry concerning this communication or earlier communications from the examiner should be directed to EUNHEE KIM whose telephone number is (571)272-2164. The examiner can normally be reached Monday-Friday 9am-5pm ET.
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, Ryan Pitaro can be reached at (571)272-4071. 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.
EUNHEE KIM
Primary Examiner
Art Unit 2188
/EUNHEE KIM/ Primary Examiner, Art Unit 2188
Prosecution Insights