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 .
Status of Claims
Claims 1-9, 11-18, & 20-23 of U.S. Application No. 18/526627 filed on 08/28/2025 have been examined.
Office Action is in response to the Applicant's amendments and remarks filed08/28/2025. Claims 1-2, 4, 6-7, 11-13, & 20-21 are presently amended. Claims 10 & 19 are cancelled and Claim 23 is newly added. Claims 1-9, 11-18, & 20-23 are presently pending and are presented for examination.
Response to Arguments
In regards to the previous claim objections: the amendments to the claims overcome the previous claim objection(s). Therefore, the previous claim objection(s) is/are withdrawn.
In regards to the previous rejections under 35 U.S.C. § 112(b): the amendments to the claims overcome the previous 35 USC § 112(b) rejection except for claim 13. Therefore, the previous 35 USC § 112(b) rejection is withdrawn, except for claim 13. The 112(b) rejection for claim 13 is still maintained.
In regards to the previous rejections under 35 U.S.C. § 101: the amendments to the claims overcome the previous 35 USC § 101 rejection. Therefore, the previous 35 USC § 101 rejection is withdrawn.
In regards to the previous rejection under 35 U.S.C. § 102: Applicant's arguments filed 02/16/2021 have been fully considered but they are not persuasive.
In regards to the previous rejection under 35 U.S.C. § 103: Applicant’s arguments with respect to the independent claim(s) 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. A new grounds of rejection is made in view of US 2021/0286925A1 (“Wyrwas”) & US 2020/0372822A1 (“Qin”).
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claim 13 is rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 13 recites the limitation " the adapted general traffic policies ". There is insufficient antecedent basis for this limitation in the claim.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
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 for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claim(s) 1-5, 7-9, 11-14, & 16-18, & 20-22 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2019/0050520A1 (“Alvarez”), in view of US 2021/0286925A1 (“Wyrwas”).
As per claim 1 Alvarez discloses
A method of operating an autonomous vehicle(see at least Alvarez, para. [0048]: The technique 600 may further include an operation 610 to update or output a set of driving directives or changes for an autonomous vehicle based on the data collected from the simulated driving experience performance.), the method comprising:
operating the vehicle in an automatic driving mode based on a current target driving policy for a target location (see at least Alvarez, para. [0051]: In an example, the operation 602 may include vehicle performance data which includes data collected from the vehicle driving along a predetermined course and the environmental data includes the predetermined course.);
obtaining, by the vehicle, vehicle driving data at the target location (see at least Alvarez, para. [0034]: As an example scenario, a vehicle may be driven along a designated section of a real world roadway. Data may be collected for the real world environment of that roadway. A vehicle performance fingerprint is generated for the vehicle during the time it is driven on the roadway. & para. [0048]: The technique 600 includes an operation 602 to obtain a vehicle performance fingerprint, wherein the vehicle performance fingerprint includes vehicle performance data collected from a unique vehicle while experiencing real world driving conditions. & para. [0052]: The technique 600 may further include operations to generate a driver profile based on the vehicle performance fingerprint and store, at a storage device, the driver profile. A driver profile may be generated by aggregating vehicle performance data to determine a driver handles situations and performs actions such as accelerating and braking.);
transmitting, by the vehicle, the obtained vehicle driving data and a current target driving policy for the target location to a data center (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)… The vehicle performance fingerprint 120 may be transferred to a simulator, such as a driving simulator 125 or a software simulator 135. The driving simulator 125 may be a simulator for a person to operate and drive the simulated vehicle. The software simulator 135 may be a simulator for testing the driving directives of an autonomous vehicle 130…The driving directives for the autonomous vehicle 130 may be loaded into the software simulator 135 and tasked with controlling the simulated vehicle constructed from the vehicle performance fingerprint 120. This may be utilized to determine how the autonomous vehicle 130 driving directives function with the performance specifications of a real world vehicle 105, including a vehicle at different stages of its lifespan.); and
receiving, by the vehicle, an updated target driving policy from the data center, the updated target driving policy being obtained based on traffic simulations performed by the data center for the target location using the vehicle driving data (see at least Alvarez, para. [0026]: When the driving directives have been updated, the modified driving directives may be uploaded to the autonomous vehicle 130 for use. & para. [0045]: In an example, the simulator may test the driving directives for an autonomous vehicle. The driving directives may control the simulated vehicle 545 along a course, such as simulated roadway 550. Hazards, such as pothole 560, may be inserted into the course to determine how the driving directives handle situations. Based on the actions taken by the driving directives to control the simulated vehicle 545 when encountering a hazard, the driving directives may be modified to improve the capabilities of the autonomous vehicle.),
operating the vehicle in the automatic driving mode based on the updated target driving policy for the target location (see at least Alvarez, para. [0048]: The operation 608 may perform the simulated driving experience with the simulated vehicle using an autonomous vehicle driving system of directives as the driver. The technique 600 may include performing either operation 606 or operation 608, or performing both operations. The technique 600 may further include an operation 610 to update or output a set of driving directives or changes for an autonomous vehicle based on the data collected from the simulated driving experience performance.).
However Alvarez does not explicitly disclose
receiving, by the vehicle, an updated target driving policy from the data center, the updated target driving policy being obtained based on traffic simulations performed by the data center for the target location using the vehicle driving data and further vehicle driving data from one or more further vehicles at the target location.
Wyrwas teaches
receiving, by the vehicle, an updated target driving policy from the data center, the updated target driving policy being obtained based on traffic simulations performed by the data center for the target location using the vehicle driving data and further vehicle driving data from one or more further vehicles at the target location (see at least Wyrwas, para. [0044]: Moreover, the vehicle 100 may include one or more network interfaces, e.g., network interface162, suitable for communicating with one or more networks 176 to permit the communication of information with other computers and electronic devices, including, for example, a central service, such as a cloud service, from which the vehicle 100 receives information including trained machine learning models and other data for use in autonomous control thereof. para. [0053]: For example, in some implementations, an individual simulation scenario describes aspects of the motion behavior characteristics of the autonomous vehicle 100 (an ego-vehicle) and one or more actors (e.g., other vehicles, static environmental objects, and pedestrians) in an instantiation of a three-dimensional(3D) world within which the autonomous vehicle 100 interacts. In some implementations, an individual simulation may include a variety of simulation scenarios that describe a set of tests of different specific encounters between an autonomous vehicle, its environment, and other moving and non-moving actors (e.g., other vehicles, other autonomous vehicles, pedestrians, animals, machinery like traffic lights, gates, drawbridges, and non-human moveable things like debris, etc.). para. [0113]: FIG. 18 is a flow chart illustrating another example of a method 1800 for using simulated data generated from logged data to train a machine learning model according to some implementations. In block 1805, time-series logged data is obtained for at least one autonomous vehicle 100. The time-series logged data includes localization data and tracking data. One or more steps may be taken to transform the time-series logged data into a format that facilitates generating augmented data for use in a simulation….In block 1825, the augmented data is used to generate a simulated perception system or a simulated plan for the autonomous vehicle 100. The input may, in some implementations, be a simulation scenario and execution of the simulation scenario to generate a state or condition for the perception subsystem 154 or the planning subsystem 156.); and
operating the vehicle in the automatic driving mode based on the updated target driving policy for the target location (see at least Wyrwas, para. [0113]: However, more generally the input may include simulated sensor data. In block 1830, simulation data is generated by executing the simulation scenario. In block 1835, a machine learning model 224 of the autonomous vehicle 100 is trained based at least in part on the simulation data. In block 1840, the trained machine learning model 224 is applied to control the autonomous vehicle 100.).
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 Alvarez to incorporate the teaching of receiving, by the vehicle, an updated target driving policy from the data center, the updated target driving policy being obtained based on traffic simulations performed by the data center for the target location using the vehicle driving data and further vehicle driving data from one or more further vehicles at the target location of Wyrwas, with a reasonable expectation of success, because simulation scenarios may be highly realistic because they are based off of logged data (see at least Wyrwas, para. [0069]).
As per claim 2 Alvarez discloses
wherein the steps of obtaining the vehicle driving data at the target location, transmitting the obtained vehicle driving data to the data center, and receiving the updated target driving policy from the data center based on the traffic simulations using the vehicle driving data are repeated one or more times (see at least Alvarez, para. [0022]: The vehicle 105 may be driven in specific scenarios or repeatedly along a predetermined course. & para. [0047]).
As per claim 3 Alvarez discloses
the method further comprising: obtaining general driving data and general traffic policies (see at least Alvarez, para. [0045]: The simulated vehicle 545 may be constructed from a vehicle performance fingerprint, such as one generated by vehicle 505. The simulated roadway 550 and simulated environment 555, each respectively constructed from data collected for the roadway 510 and environment 515. For example, a course may be plotted for a vehicle 505 to drive from a ten mile distance along a highway. Data is collected from the OBD system of the vehicle 505 as it drives the course. Data is collected for the roadway and environment along the course.); and
using the general driving data and the vehicle driving data to adapt the general traffic policies to the target location (see at least Alvarez, para. [0045]: Based on the actions taken by the driving directives to control the simulated vehicle 545 when encountering a hazard, the driving directives may be modified to improve the capabilities of the autonomous vehicle.).
As per claim 4 Alvarez discloses
the method further comprising, prior to receiving, by the vehicle, the updated target driving policy: performing, by the data center, the traffic simulations for the target location using the vehicle driving data to obtain the updated target driving policy (see at least Alvarez, para. [0047]: Similar to the scenario presented in FIGS. SA-SC, the vehicle performance fingerprint may be used to reproduce an accident, such as a driver losing control and the vehicle skidding off the road. Data may be collected for the environment where the accident occurred. This environmental data with the vehicle performance fingerprint may be used in a simulator to recreate the accident.); and
transmitting, by the data center, the updated target driving policy to the vehicle (see at least Alvarez, para. [0047]: The data collected from the simulation may then be applied to prevent future accidents.),
wherein the step of performing traffic simulations for the target location is based on the adapted general traffic policies (see at least Alvarez, para. [0047]: The simulation may be iteratively repeated with certain factors, such as the speed of the vehicle, altered in each iteration to create a simulation that most closely matches the outcome of the actual accident.).
However Alvarez does not explicitly disclose
performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy.
Wyrwas teaches
performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy (see at least Wyrwas, para. [0044]: Moreover, the vehicle 100 may include one or more network interfaces, e.g., network interface162, suitable for communicating with one or more networks 176 to permit the communication of information with other computers and electronic devices, including, for example, a central service, such as a cloud service, from which the vehicle 100 receives information including trained machine learning models and other data for use in autonomous control thereof. para. [0113]: FIG. 18 is a flow chart illustrating another example of a method 1800 for using simulated data generated from logged data to train a machine learning model according to some implementations. In block 1805, time-series logged data is obtained for at least one autonomous vehicle 100. The time-series logged data includes localization data and tracking data. One or more steps may be taken to transform the time-series logged data into a format that facilitates generating augmented data for use in a simulation….In block 1825, the augmented data is used to generate a simulated perception system or a simulated plan for the autonomous vehicle 100. The input may, in some implementations, be a simulation scenario and execution of the simulation scenario to generate a state or condition for the perception subsystem 154 or the planning subsystem 156.).
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 Alvarez to incorporate the teaching of performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy of Wyrwas, with a reasonable expectation of success, because simulation scenarios may be highly realistic because they are based off of logged data (see at least Wyrwas, para. [0069]).
As per claim 5 Alvarez discloses
wherein the updated target driving policy comprises an updated set of target driving policy parameters (see at least Alvarez, para. [0045]: Based on the actions taken by the driving directives to control the simulated vehicle 545 when encountering a hazard, the driving directives may be modified to improve the capabilities of the autonomous vehicle.).
As per claim 7 Alvarez discloses
the method further comprising: prior to receiving, by the vehicle, the updated target driving policy: performing, by the data center, the traffic simulations for the target location using the vehicle driving data to obtain the updated target driving policy (see at least Alvarez, para. [0045]: The simulated vehicle 545 may be constructed from a vehicle performance fingerprint, such as one generated by vehicle 505. The simulated roadway 550 and simulated environment 555, each respectively constructed from data collected for the roadway 510 and environment 515. For example, a course may be plotted for a vehicle 505 to drive from a ten mile distance along a highway. Data is collected from the OBD system of the vehicle 505 as it drives the course…the driving directives may be modified to improve the capabilities of the autonomous vehicle.); and
transmitting, by the data center, the updated target driving policy to the vehicle generating different traffic scenarios by modifying an initial traffic scenario obtained from the vehicle driving data (see at least Alvarez, para. [0045]: The simulated driving scenario 540 may be altered to test how a driver or autonomous vehicle may handle different situations. The simulated driving scenario 540 may be used to evaluate the driving performance qualifications of a driver and train driver muscle coordination in driver unknown simulated driving circumstances. Hazards may be added to the simulated driving scenario 540, such as a large pothole 560. In an example, the simulator may test the driving directives for an autonomous vehicle. The driving directives may control the simulated vehicle 545 along a course, such as simulated roadway 550. Hazards, such as pothole 560, may be inserted into the course to determine how the driving directives handle situations.),
wherein the traffic simulations for the target location are performed with the generated different traffic scenarios (see at least Alvarez, para. [0045-0047]: The simulated driving scenario 540 may be altered to test how a driver or autonomous vehicle may handle different situations. The simulated driving scenario 540 may be used to evaluate the driving performance qualifications of a driver and train driver muscle coordination in driver unknown simulated driving circumstances. Hazards may be added to the simulated driving scenario 540, such as a large pothole 560. In an example, the simulator may test the driving directives for an autonomous vehicle. The driving directives may control the simulated vehicle 545 along a course, such as simulated roadway 550. Hazards, such as pothole 560, may be inserted into the course to determine how the driving directives handle situations.).
However Alvarez does not explicitly disclose
performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy.
Wyrwas teaches
performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy (see at least Wyrwas, para. [0044]: Moreover, the vehicle 100 may include one or more network interfaces, e.g., network interface162, suitable for communicating with one or more networks 176 to permit the communication of information with other computers and electronic devices, including, for example, a central service, such as a cloud service, from which the vehicle 100 receives information including trained machine learning models and other data for use in autonomous control thereof. para. [0113]: FIG. 18 is a flow chart illustrating another example of a method 1800 for using simulated data generated from logged data to train a machine learning model according to some implementations. In block 1805, time-series logged data is obtained for at least one autonomous vehicle 100. The time-series logged data includes localization data and tracking data. One or more steps may be taken to transform the time-series logged data into a format that facilitates generating augmented data for use in a simulation….In block 1825, the augmented data is used to generate a simulated perception system or a simulated plan for the autonomous vehicle 100. The input may, in some implementations, be a simulation scenario and execution of the simulation scenario to generate a state or condition for the perception subsystem 154 or the planning subsystem 156.).
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 Alvarez to incorporate the teaching of performing, by the data center, the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data from the one or more further vehicles at the target location to obtain the updated target driving policy of Wyrwas, with a reasonable expectation of success, because simulation scenarios may be highly realistic because they are based off of logged data (see at least Wyrwas, para. [0069]).
As per claim 8 Alvarez discloses
wherein modifying the initial traffic scenario comprises at least one of:
increasing a number of agents in the traffic scenario (see at least Alvarez, para. [0037]);
modifying a velocity of an agent in the traffic scenario (see at least Alvarez, para. [0047]: The simulation may be iteratively repeated with certain factors, such as the speed of the vehicle, altered in each iteration to create a simulation that most closely matches the outcome of the actual accident.);
modifying an initial position and/or direction of an agent in the traffic scenario; and
modifying a trajectory of an agent in the traffic scenario.
As per claim 9 Alvarez discloses
wherein the target location is described by map data of a geographically limited area (see at least Alvarez, para. [0047]: Similar to the scenario presented in FIGS. SA-SC, the vehicle performance fingerprint may be used to reproduce an accident, such as a driver losing control and the vehicle skidding off the road. Data may be collected for the environment where the accident occurred. This environmental data with the vehicle performance fingerprint may be used in a simulator to recreate the accident.).
As per claim 11 Alvarez discloses
A data center (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)…), the data comprising:
a receiver configured to receive, from a vehicle, vehicle driving data at a target location and a current target driving policy for the target location (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)…),
the current target driving policy being adapted for operating the vehicle in an automatic driving mode at the target location (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)… The vehicle performance fingerprint 120 may be transferred to a simulator, such as a driving simulator 125 or a software simulator 135. The driving simulator 125 may be a simulator for a person to operate and drive the simulated vehicle. The software simulator 135 may be a simulator for testing the driving directives of an autonomous vehicle 130…The driving directives for the autonomous vehicle 130 may be loaded into the software simulator 135 and tasked with controlling the simulated vehicle constructed from the vehicle performance fingerprint 120. This may be utilized to determine how the autonomous vehicle 130 driving directives function with the performance specifications of a real world vehicle 105, including a vehicle at different stages of its lifespan.);
processing circuitry configured to perform traffic simulations for the target location using the vehicle driving data to obtain an updated target driving policy (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)… The vehicle performance fingerprint 120 may be transferred to a simulator, such as a driving simulator 125 or a software simulator 135. The driving simulator 125 may be a simulator for a person to operate and drive the simulated vehicle. The software simulator 135 may be a simulator for testing the driving directives of an autonomous vehicle 130…The driving directives for the autonomous vehicle 130 may be loaded into the software simulator 135 and tasked with controlling the simulated vehicle constructed from the vehicle performance fingerprint 120. This may be utilized to determine how the autonomous vehicle 130 driving directives function with the performance specifications of a real world vehicle 105, including a vehicle at different stages of its lifespan.); and
a transmitter configured to transmit the updated target driving policy to the vehicle (see at least Alvarez, para. [0048]: The technique 600 may further include an operation 610 to update or output a set of driving directives or changes for an autonomous vehicle based on the data collected from the simulated driving experience performance.).
However Alvarez does not explicitly disclose
receive, from one or more further vehicles, further vehicle driving data at the target location;
processing circuitry configured to perform traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain an updated target driving policy.
Wyrwas teaches
receive, from one or more further vehicles, further vehicle driving data at the target location (see at least Wyrwas, para. [0053]: For example, in some implementations, an individual simulation scenario describes aspects of the motion behavior characteristics of the autonomous vehicle 100 (an ego-vehicle) and one or more actors (e.g., other vehicles, static environmental objects, and pedestrians) in an instantiation of a three-dimensional(3D) world within which the autonomous vehicle 100 interacts. In some implementations, an individual simulation may include a variety of simulation scenarios that describe a set of tests of different specific encounters between an autonomous vehicle, its environment, and other moving and non-moving actors (e.g., other vehicles, other autonomous vehicles, pedestrians, animals, machinery like traffic lights, gates, drawbridges, and non-human moveable things like debris, etc.).);
processing circuitry configured to perform traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain an updated target driving policy (see at least Wyrwas, para. [0044]: Moreover, the vehicle 100 may include one or more network interfaces, e.g., network interface162, suitable for communicating with one or more networks 176 to permit the communication of information with other computers and electronic devices, including, for example, a central service, such as a cloud service, from which the vehicle 100 receives information including trained machine learning models and other data for use in autonomous control thereof. para. [0113]: FIG. 18 is a flow chart illustrating another example of a method 1800 for using simulated data generated from logged data to train a machine learning model according to some implementations. In block 1805, time-series logged data is obtained for at least one autonomous vehicle 100. The time-series logged data includes localization data and tracking data. One or more steps may be taken to transform the time-series logged data into a format that facilitates generating augmented data for use in a simulation….In block 1825, the augmented data is used to generate a simulated perception system or a simulated plan for the autonomous vehicle 100. The input may, in some implementations, be a simulation scenario and execution of the simulation scenario to generate a state or condition for the perception subsystem 154 or the planning subsystem 156.).
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 Alvarez to incorporate the teaching of receive, from one or more further vehicles, further vehicle driving data at the target location, processing circuitry configured to perform traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain an updated target driving policy of Wyrwas, with a reasonable expectation of success, because simulation scenarios may be highly realistic because they are based off of logged data (see at least Wyrwas, para. [0069]).
As per claim 12 Alvarez discloses
wherein the processing circuitry is further configured to use general driving data and the vehicle driving data to obtain adapted general traffic policies to the target location (see at least Alvarez, para. [0045]: The simulated vehicle 545 may be constructed from a vehicle performance fingerprint, such as one generated by vehicle 505. The simulated roadway 550 and simulated environment 555, each respectively constructed from data collected for the roadway 510 and environment 515. For example, a course may be plotted for a vehicle 505 to drive from a ten mile distance along a highway. Data is collected from the OBD system of the vehicle 505 as it drives the course. Data is collected for the roadway and environment along the course… Based on the actions taken by the driving directives to control the simulated vehicle 545 when encountering a hazard, the driving directives may be modified to improve the capabilities of the autonomous vehicle.).
As per claim 13 Alvarez discloses
wherein the processing circuitry is further configured to perform the traffic simulations for the target location based on the adapted general traffic policies (see at least Alvarez, para. [0047]: Similar to the scenario presented in FIGS. SA-SC, the vehicle performance fingerprint may be used to reproduce an accident, such as a driver losing control and the vehicle skidding off the road. Data may be collected for the environment where the accident occurred. This environmental data with the vehicle performance fingerprint may be used in a simulator to recreate the accident.).
As per claim 14 Alvarez discloses
wherein the updated target driving policy comprises an updated set of target driving policy parameters (see at least Alvarez, para. [0045]: Based on the actions taken by the driving directives to control the simulated vehicle 545 when encountering a hazard, the driving directives may be modified to improve the capabilities of the autonomous vehicle.).
As per claim 16 Alvarez discloses
wherein the processing circuitry is further configured to generate different traffic scenarios by modifying an initial traffic scenario obtained from the vehicle driving data (see at least Alvarez, para. [0045]: The simulated driving scenario 540 may be altered to test how a driver or autonomous vehicle may handle different situations. The simulated driving scenario 540 may be used to evaluate the driving performance qualifications of a driver and train driver muscle coordination in driver unknown simulated driving circumstances. Hazards may be added to the simulated driving scenario 540, such as a large pothole 560. In an example, the simulator may test the driving directives for an autonomous vehicle. The driving directives may control the simulated vehicle 545 along a course, such as simulated roadway 550. Hazards, such as pothole 560, may be inserted into the course to determine how the driving directives handle situations.); and
to perform the traffic simulations for the target location with the generated different traffic scenarios (see at least Alvarez, para. [0045-0047]: The simulated driving scenario 540 may be altered to test how a driver or autonomous vehicle may handle different situations. The simulated driving scenario 540 may be used to evaluate the driving performance qualifications of a driver and train driver muscle coordination in driver unknown simulated driving circumstances. Hazards may be added to the simulated driving scenario 540, such as a large pothole 560. In an example, the simulator may test the driving directives for an autonomous vehicle. The driving directives may control the simulated vehicle 545 along a course, such as simulated roadway 550. Hazards, such as pothole 560, may be inserted into the course to determine how the driving directives handle situations.).
As per claim 17 Alvarez discloses
wherein the processing circuitry is configured to modify the initial traffic scenario by at least one of:
increasing a number of agents in the traffic scenario (see at least Alvarez, para. [0037]);
modifying a velocity of an agent in the traffic scenario (see at least Alvarez, para. [0047]: The simulation may be iteratively repeated with certain factors, such as the speed of the vehicle, altered in each iteration to create a simulation that most closely matches the outcome of the actual accident.);
modifying an initial position and/or direction of an agent in the traffic scenario; or
modifying a trajectory of an agent in the traffic scenario.
As per claim 18 Alvarez discloses
wherein the target location is described by map data of a geographically limited area (see at least Alvarez, para. [0047]: Similar to the scenario presented in FIGS. SA-SC, the vehicle performance fingerprint may be used to reproduce an accident, such as a driver losing control and the vehicle skidding off the road. Data may be collected for the environment where the accident occurred. This environmental data with the vehicle performance fingerprint may be used in a simulator to recreate the accident.).
As per claim 20 Alvarez discloses
A system, the system comprising:
the data center according to claim 11 (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)… The vehicle performance fingerprint 120 may be transferred to a simulator, such as a driving simulator 125 or a software simulator 135. The driving simulator 125 may be a simulator for a person to operate and drive the simulated vehicle. The software simulator 135 may be a simulator for testing the driving directives of an autonomous vehicle 130…The driving directives for the autonomous vehicle 130 may be loaded into the software simulator 135 and tasked with controlling the simulated vehicle constructed from the vehicle performance fingerprint 120. This may be utilized to determine how the autonomous vehicle 130 driving directives function with the performance specifications of a real world vehicle 105, including a vehicle at different stages of its lifespan.); and
the vehicle, the vehicle configured to:
operate in the automatic driving mode based on the current target driving policy for the target location (see at least Alvarez, para. [0051]: In an example, the operation 602 may include vehicle performance data which includes data collected from the vehicle driving along a predetermined course and the environmental data includes the predetermined course.);
obtain vehicle driving data at the target location (see at least Alvarez, para. [0034]: As an example scenario, a vehicle may be driven along a designated section of a real world roadway. Data may be collected for the real world environment of that roadway. A vehicle performance fingerprint is generated for the vehicle during the time it is driven on the roadway. & para. [0048]: The technique 600 includes an operation 602 to obtain a vehicle performance fingerprint, wherein the vehicle performance fingerprint includes vehicle performance data collected from a unique vehicle while experiencing real world driving conditions.), and
transmit the obtained vehicle driving data and the current target driving policy for the target location to the data center (see at least Alvarez, para. [0024-0026]: The data collected by the data collection device 110 may be transferred to a computing device 115 (e.g., a mobile device, such as a smartphone)… The vehicle performance fingerprint 120 may be transferred to a simulator, such as a driving simulator 125 or a software simulator 135. The driving simulator 125 may be a simulator for a person to operate and drive the simulated vehicle. The software simulator 135 may be a simulator for testing the driving directives of an autonomous vehicle 130…The driving directives for the autonomous vehicle 130 may be loaded into the software simulator 135 and tasked with controlling the simulated vehicle constructed from the vehicle performance fingerprint 120. This may be utilized to determine how the autonomous vehicle 130 driving directives function with the performance specifications of a real world vehicle 105, including a vehicle at different stages of its lifespan.);
receive the updated target driving policy from the data center (see at least Alvarez, para. [0048]: The technique 600 may further include an operation 610 to update or output a set of driving directives or changes for an autonomous vehicle based on the data collected from the simulated driving experience performance. & para. [0060]); and
operate in the automatic driving mode based on the updated target driving policy for the target location (see at least Alvarez, para. [0048]: The operation 608 may perform the simulated driving experience with the simulated vehicle using an autonomous vehicle driving system of directives as the driver. The technique 600 may include performing either operation 606 or operation 608, or performing both operations. The technique 600 may further include an operation 610 to update or output a set of driving directives or changes for an autonomous vehicle based on the data collected from the simulated driving experience performance.).
As per claim 21 Alvarez discloses
configured to repeatedly perform the steps of obtaining vehicle driving data at the target location, transmitting the obtained vehicle driving data to the data center, performing the traffic simulations for the target location using the vehicle driving data to obtain the updated target driving policy, and transmitting the updated target driving policy to the vehicle (see at least Alvarez, para. [0022]: The vehicle 105 may be driven in specific scenarios or repeatedly along a predetermined course. & para. [0047]).
However Alvarez does not explicitly disclose
performing the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain the updated target driving policy.
Wyrwas teaches
performing the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain the updated target driving policy (see at least Wyrwas, para. [0044]: Moreover, the vehicle 100 may include one or more network interfaces, e.g., network interface162, suitable for communicating with one or more networks 176 to permit the communication of information with other computers and electronic devices, including, for example, a central service, such as a cloud service, from which the vehicle 100 receives information including trained machine learning models and other data for use in autonomous control thereof. para. [0053]: For example, in some implementations, an individual simulation scenario describes aspects of the motion behavior characteristics of the autonomous vehicle 100 (an ego-vehicle) and one or more actors (e.g., other vehicles, static environmental objects, and pedestrians) in an instantiation of a three-dimensional(3D) world within which the autonomous vehicle 100 interacts. In some implementations, an individual simulation may include a variety of simulation scenarios that describe a set of tests of different specific encounters between an autonomous vehicle, its environment, and other moving and non-moving actors (e.g., other vehicles, other autonomous vehicles, pedestrians, animals, machinery like traffic lights, gates, drawbridges, and non-human moveable things like debris, etc.). para. [0113]: FIG. 18 is a flow chart illustrating another example of a method 1800 for using simulated data generated from logged data to train a machine learning model according to some implementations. In block 1805, time-series logged data is obtained for at least one autonomous vehicle 100. The time-series logged data includes localization data and tracking data. One or more steps may be taken to transform the time-series logged data into a format that facilitates generating augmented data for use in a simulation….In block 1825, the augmented data is used to generate a simulated perception system or a simulated plan for the autonomous vehicle 100. The input may, in some implementations, be a simulation scenario and execution of the simulation scenario to generate a state or condition for the perception subsystem 154 or the planning subsystem 156.).
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 Alvarez to incorporate the teaching of performing the traffic simulations for the target location using the vehicle driving data and the further vehicle driving data to obtain the updated target driving policy of Wyrwas, with a reasonable expectation of success, because simulation scenarios may be highly realistic because they are based off of logged data (see at least Wyrwas, para. [0069]).
As per claim 22 Alvarez discloses
A non-transitory computer-readable storage medium comprising computer readable instructions for, when run on a computer, performing the steps of the method according to claim 1 (see at least Alvarez, para. [0061]: The term "machine readable medium" may include any medium that is capable of storing, encoding, or carrying instructions for execution by the machine 700 and that cause the machine 700 to perform any one or more of the techniques of the present disclosure, or that is capable of storing, encoding or carrying data structures used by or associated with such instructions.).
Claim(s) 6 & 15 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alvarez, in view of Wyrwas, in view of US 2020/0033868A1 (“Palanisamy”).
As per claim 6 Alvarez does not explicitly disclose
wherein performing the traffic simulations comprises training the current target driving policy to improve a confidence measure or a safety measure.
Palanisamy teaches
wherein performing the traffic simulations comprises training the current target driving policy to improve a confidence measure or a safety measure (see at least Palanisamy, para. [0075] & para. [0138]: This system will enable an aftermarket AV system to update/upgrade its driving decision making policies that are made available through the policy server 150. The policies on the policy server 150 could be updated by any means (not necessarily using a driving learner module and/or an experience memory). Rigorous testing and validation methods can be employed to validate and verify the safety levels and other performance characteristics of the policies on the policy server once and can be deployed to millions of vehicles at scale.).
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 Alvarez to incorporate the teaching of wherein performing the traffic simulations comprises training the current target driving policy to improve a confidence measure or a safety measure of Palanisamy, with a reasonable expectation of success, in order for automatic autonomous vehicle driving policy update with minimal data collection and human support on target locations (see at least Palanisamy, para. [0072]).
As per claim 15 Alvarez does not explicitly disclose
wherein the processing circuitry is further configured to train the current target driving policy to improve a confidence measure and/or a safety measure.
Palanisamy teaches
wherein the processing circuitry is further configured to train the current target driving policy to improve a confidence measure and/or a safety measure (see at least Palanisamy, para. [0075] & para. [0138]: This system will enable an aftermarket AV system to update/upgrade its driving decision making policies that are made available through the policy server 150. The policies on the policy server 150 could be updated by any means (not necessarily using a driving learner module and/or an experience memory). Rigorous testing and validation methods can be employed to validate and verify the safety levels and other performance characteristics of the policies on the policy server once and can be deployed to millions of vehicles at scale.).
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 Alvarez to incorporate the teaching of wherein the processing circuitry is further configured to train the current target driving policy to improve a confidence measure and/or a safety measure of Palanisamy, with a reasonable expectation of success, in order for automatic autonomous vehicle driving policy update with minimal data collection and human support on target locations (see at least Palanisamy, para. [0072]).
Claim(s) 23 is/are rejected under 35 U.S.C. 103 as being unpatentable over Alvarez, in view of Wyrwas, in view of Palanisamy, in view of US 2020/0372822A1 (“Qin”).
As per claim 23 Alvarez does not explicitly disclose
wherein performing the traffic simulations comprises evaluating a set of driving policies relative to a set of a driving scenario by computing a safety and confidence score for a traffic agent in each episode generated in a simulation of the traffic simulations.
Qin teaches
wherein performing the traffic simulations comprises evaluating a set of driving policies relative to a set of a driving scenario by computing a safety and confidence score for a traffic agent in each episode generated in a simulation of the traffic simulations (see at least Qin, para. [0041]: The policy search module sets an objective function in a constructed simulator and then searches for a driving control policy of the optimal objective function by means of a machine learning method, wherein the objective function includes a destination determination value for determining whether or not a vehicle has arrived at a destination…a safety determination value for determining whether or not the vehicle has been collided in the driving process…and is obtained by means of weighted summation of all the determination values. para. [0061]: The initial control policy π.sub.k is run in the simulator to obtain a motion trajectory of an unmanned vehicle in the simulator and to respectively evaluate a destination determination value, a safety determination value, a compliance determination value, and a comfort determination value of the motion trajectory, and these values are added together to obtain a result of an evaluation index after running the control policy…).
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 Alvarez to incorporate the teaching of wherein performing the traffic simulations comprises evaluating a set of driving policies relative to a set of a driving scenario by computing a safety and confidence score for a traffic agent in each episode generated in a simulation of the traffic simulations of Qin, with a reasonable expectation of success, in order for generating a safe and autonomous driving control policy (see at least Qin, para. [0006]).
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.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MOHAMED ABDO ALGEHAIM whose telephone number is (571)272-3628. The examiner can normally be reached Monday-Friday 8-5PM EST.
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, Fadey Jabr can be reached at 571-272-1516. 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.
/MOHAMED ABDO ALGEHAIM/Primary Examiner, Art Unit 3668
Prosecution Insights