DETAILED ACTION
Claims 1-20 are presented for examination.
This Office Action is in response to submission of documents on November 18, 2022.
Rejection of claims 1-20 under 35 U.S.C. 101 for being directed to unpatentable subject matter.
Rejection of claims 1-20 under 35 U.S.C. 103 as being obvious over Brogle in view of Kar.
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-20 are rejected under 35 U.S.C. 101 because the claimed invention is directed to judicial exceptions without significantly more. The claims recite mathematical calculations and mental processes. This judicial exception is not integrated into a practical application because the additional elements that are recited in the claims are extra-solution activities that do not integrate the judicial exceptions into a practical application. The claims do not include additional elements that are sufficient to amount to significantly more than the judicial exception because courts have found that the steps of sending and transmitting data are not significantly more than a judicial exception.
Claim 1
Step 1: The claim is directed to a system, falling under one of the four statutory categories of invention.
Step 2A, Prong 1: The claim 1 limitations include (bolded for abstract idea identification):
Claim 1
Mapping Under Step 2A Prong 1
A computer-implemented system, comprising: one or more processing units; and
one or more non-transitory computer-readable media storing instructions, when executed by the one or more processing units, cause the one or more processing units to perform a method comprising:
receiving first data collected from a real-world driving scene, the first data associated with the real-world driving scene and a performance of a real-world vehicle in the real-world driving scene; and
adjusting, for a current iteration, a parameter associated with an end-to-end (E2E) vehicle simulation that simulates operations of a simulated vehicle driving in a simulated driving scene, wherein:
the simulated driving scene is a simulation of the real-world driving scene,
the adjustment is based on a fidelity value of the E2E vehicle simulation in a previous iteration, and the fidelity value is based on a comparison between second data collected from the E2E vehicle simulation in the previous iteration and the first data.
Abstract Idea: Mental Process
Adjusting a parameter is a mental process that can be carried out by a human. A human, based on observation, evaluation, and judgment, can observe the results of a simulation run, change one or more parameters (e.g., frames per second, time step size, speed of simulated vehicle) and, through judgment, determine a new value for the parameters, such as a fidelity. See e.g., MPEP 2106.04(a)(2), Subsection III.
Abstract Idea: Mathematical Calculations
A simulation is a model of a real-world environment and includes performing calculations that mimic the behavior of one or more elements in the real world according to, for example, physics equations. See MPEP § 2106.04(a)(2), Subsection I.
Abstract Idea: Mathematical Calculations
Making a comparison is a mathematical concept that includes determining which number (e.g., a parameter) is greater than another parameter. See MPEP § 2106.04(a)(2), Subsection I.
Step 2A, Prong 2: The claim 1 limitations recite (bolded for additional element identification):
Claim 1
Mapping Under Step 2A Prong 2
A computer-implemented system, comprising: one or more processing units; and one or more non-transitory computer-readable media storing instructions, when executed by the one or more processing units, cause the one or more processing units to perform a method comprising:
receiving first data collected from a real-world driving scene, the first data associated with the real-world driving scene and a performance of a real-world vehicle in the real-world driving scene; and
adjusting, for a current iteration, a parameter associated with an end-to-end (E2E) vehicle simulation that simulates operations of a simulated vehicle driving in a simulated driving scene, wherein:
the simulated driving scene is a simulation of the real-world driving scene,
the adjustment is based on a fidelity value of the E2E vehicle simulation in a previous iteration, and the fidelity value is based on a comparison between second data collected from the E2E vehicle simulation in the previous iteration and the first data.
Reciting generic computer components is the additional element of instructions to apply the recited judicial exception, which courts have found does not integrate the judicial exception into a practical application. See MPEP 2106.05(f)
Providing data (i.e., transmitting and receiving data) is an extra-solution activity that does not integrate the judicial exception into a practical application. The limitation does not recite, with specificity, how the data is provided nor received and therefore does not improve the functioning of a computer. See MPEP 2106.05(d)(II).
Step 2B: Regarding Step 2B, the inquiry is whether any of the additional elements (i.e., the elements that are not the judicial exception) amount to significantly more than the recited judicial exception. Courts have found that reciting generic components and transmitting data do not amount to significantly more than the recited judicial exceptions. See Alice Corp. v. CLS Bank, 573 U.S. 208, 221, 110 USPQ2d 1976, 1982-83 (2014), Gottschalk v. Benson, 409 U.S. 63, 70, 175 USPQ 673, 676 (1972), Ultramercial, Inc. v. Hulu, LLC, 772 F.3d 709, 112 USPQ2d 1750 (Fed. Cir. 2014); Electric Power Group, LLC v. Alstom, S.A., 830 F.3d 1350, 119 USPQ2d 1739 (Fed. Cir. 2016). See also Diamond v. Diehr, 450 U.S. 175, 192 n.14, 209 USPQ 1, 10 n. 14 (1981); Bilski v. Kappos, 561 U.S. 593, 612, 95 USPQ2d 1001, 1010 (2010); Affinity Labs of Texas v. DirecTV, LLC, 838 F.3d 1253, 120 USPQ2d 1201 (Fed. Cir. 2016); Ultramercial, 772 F.3d at 716, 112 USPQ2d at 1755 (limiting use of abstract idea to the Internet); Electric Power, 830 F.3d at 1354, 119 USPQ2d at 1742 (limiting application of abstract idea to power grid data); Intellectual Ventures I LLC v. Erie Indem. Co., 850 F.3d 1315, 1328-29, 121 USPQ2d 1928, 1939 (Fed. Cir. 2017) (limiting use of abstract idea to use with XML tags).
Accordingly, claim 1 is rejected for being directed to unpatentable subject matter.
Claim 2
Claim 2 recites wherein the method further comprises:
executing the E2E vehicle simulation in the previous iteration;
Executing a simulation is a mathematical process that requires performing one or more mathematical operations to simulate a real world environment.
collecting, from the E2E vehicle simulation, the second data associated with the simulated driving scene and a performance of the simulated vehicle in the simulated driving scene; and
Providing data (i.e., transmitting and receiving data) is an extra-solution activity that does not integrate the judicial exception into a practical application. The limitation does not recite, with specificity, how the data is provided nor received and therefore does not improve the functioning of a computer. See MPEP 2106.05(d)(II).
calculating the fidelity value for the E2E vehicle simulation based on the comparison between the first data and the second data.
Making a comparison is a mathematical concept that includes determining which number (e.g., a parameter) is greater than another parameter. See MPEP § 2106.04(a)(2), Subsection I.
Accordingly, claim 2 is rejected for being directed to unpatentable subject matter.
Claim 3
Claim 3 recites wherein the parameter adjusted based on the fidelity value of the E2E vehicle simulation in the previous iteration is for a component model modeling a component in the real-world driving scene. The limitation specifies a type of parameter that is adjusted. As previously indicated, “adjusting a parameter” is a mental process and the type of parameter that is adjusted does not change the previous analysis of the step as a judicial exception. See MPEP 2106.04(a)(2), Subsection III. Accordingly, claim 3 is rejected for being directed to unpatentable subject matter.
Claim 4
Claim 4 recites wherein the component model for which the parameter is adjusted models a sensor in the real-world driving scene. The component model is component of the simulation which has previously been identified as an abstract idea (i.e., a mathematical concept). A model that is a part of the simulation is also a mathematical concepts and includes generating data that corresponds to a real world phenomenon. See MPEP 2106.04(a)(2), Subsection I. Accordingly, claim 4 is rejected for being directed to unpatentable subject matter.
Claim 5
Claim 5 recites wherein the component model for which the parameter is adjusted models an object in the real-world driving scene. The component model is component of the simulation which has previously been identified as an abstract idea (i.e., a mathematical concept). A model that is a part of the simulation is also a mathematical concepts and includes generating data that corresponds to a real world phenomenon. See MPEP 2106.04(a)(2), Subsection I. Accordingly, claim 5 is rejected for being directed to unpatentable subject matter.
Claim 6
Claim 6 recites wherein the component model for which the parameter is adjusted models at least one of a pose or vehicle dynamic of the real-world vehicle. The component model is component of the simulation which has previously been identified as an abstract idea (i.e., a mathematical concept). A model that is a part of the simulation is also a mathematical concepts and includes generating data that corresponds to a real world phenomenon. See MPEP 2106.04(a)(2), Subsection I. Accordingly, claim 6 is rejected for being directed to unpatentable subject matter.
Claim 7
Claim 7 recites wherein the component model for which the parameter is adjusted models a road attribute. The component model is component of the simulation which has previously been identified as an abstract idea (i.e., a mathematical concept). A model that is a part of the simulation is also a mathematical concepts and includes generating data that corresponds to a real world phenomenon. See MPEP 2106.04(a)(2), Subsection I. Accordingly, claim 7 is rejected for being directed to unpatentable subject matter.
Claim 8
Claim 8 recites wherein the adjusting the parameter associated with the E2E vehicle simulation comprises: identifying a mismatch between the component in the real-world driving scene and the component model in the simulated driving scene. Identifying a mismatch between two components is a mental process that can be performed by a human. For example, a user can observe the execution of a simulation and compare the simulation to a presentation of the real world event. Based on observation, evaluation, and opinion, a human can determine that the simulation does not match with what occurred in the real world driving experience. See MPEP 2106.04(a)(2), Subsection III. According, claim 8 is rejected for being directed to unpatentable subject matter.
Claim 9
Claim 9 recites wherein the adjusting the parameter associated with the E2E vehicle simulation comprises:
executing, based on a component test definition, a test for the component model;
Executing a test on a model is a mental process that can include checking any number of parameters, inputs, outputs, and/or other operations performed by a component and determining, through observation, judgment, evaluation, and opinion, whether the component (model) operates in a manner that is consistent with expected performance. See MPEP 2106.04(a)(2), Subsection III.
collecting third data from the executing the test;
The limitation is directed to the extra-solution activity of data gathering. The limitation does not impose meaningful limits on the claim and thus is minimally or tangentially related to the invention. See MPEP 2106.05(g).
Courts have found that the extra-solution activity of data gathering is insignificantly more than the recited judicial exception. See, e.g., In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989); In re Meyers, 688 F.2d 789, 794; 215 USPQ 193, 196-97 (CCPA 1982); OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93; CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011).
receiving fourth data collected from the component in the real-world driving scene, the fourth data based on the component test definition; and
The limitation is directed to the extra-solution activity of data gathering. The limitation does not impose meaningful limits on the claim and thus is minimally or tangentially related to the invention. See MPEP 2106.05(g).
Courts have found that the extra-solution activity of data gathering is insignificantly more than the recited judicial exception. See, e.g., In re Grams, 888 F.2d 835, 839-40; 12 USPQ2d 1824, 1827-28 (Fed. Cir. 1989); In re Meyers, 688 F.2d 789, 794; 215 USPQ 193, 196-97 (CCPA 1982); OIP Technologies, 788 F.3d at 1363, 115 USPQ2d at 1092-93; CyberSource v. Retail Decisions, Inc., 654 F.3d 1366, 1375, 99 USPQ2d 1690, 1694 (Fed. Cir. 2011).
calculating a fidelity value for the component model based on a comparison of the third data to the fourth data.
Making a comparison is a mathematical concept that includes determining which number (e.g., a parameter) is greater than another parameter. See MPEP § 2106.04(a)(2), Subsection I.
Accordingly, claim 9 is directed to unpatentable subject matter.
Claim 10
Claim 10 recites wherein the adjusting the parameter associated with the E2E vehicle simulation is based on the fidelity value in the previous iteration failing to satisfy a threshold. Determining whether a value satisfies a threshold value is a mathematical concept (or alternatively, a mental process) that includes comparing two values and determining whether a first value (e.g., the fidelity value) exceeds a threshold value. See MPEP 2106.04(a)(2), Subsections I and II. Accordingly, claim 10 is directed to unpatentable subject matter.
Claim 11-16
Claim 11 recites a method that includes steps that are substantially the same as the steps performed by the system of claim 1. Further, claims 12-16 recite limitations that are substantially the same as the limitations that are recited in one or more of steps 2-10. Accordingly, for at least the same reasons as claims 1-10, claims 11-16 are rejected under 35 U.S.C. 101 as being directed to unpatentable subject matter.
Claim 17-20
Claim 17 recites non-transitory memory that stores a method that includes steps that are substantially the same as the steps performed by the system of claim 1. Further, claims 17-20 recite limitations that are substantially the same as the limitations that are recited in one or more of steps 2-10. Accordingly, for at least the same reasons as claims 1-10, claims 16720 are rejected under 35 U.S.C. 101 as being directed to unpatentable subject matter.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
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.
Claims 1-20 are rejected under 35 U.S.C. 103 as being obvious over Brogle, et al, (“Hardware-in-the-Loop Autonomous Driving Simulation Without Real-Time Constraints,” hereinafter “Brogle”) in view of Kar, et al., (“Meta-Sim: Learning to Generate Synthetic Datasets,” hereinafter “Kar”).
Claim 1
Brogle discloses:
A computer-implemented system, comprising: one or more processing units; and one or more non-transitory computer-readable media storing instructions, when executed by the one or more processing units, cause the one or more processing units to perform a method comprising:
The autonomous driving simulator consists of a computer (Intel i7-4770 processor, 8GB DDR3-1066 RAM, Nvidia Titan X (Maxwell) graphics processing unit (GPU)) running the aforementioned CARLA driving simulator and ROS simulation node which receives input from the Logitech G920 racing wheel over a USB connection, and performs bidirectional communication with an Nvidia Jetson TX1 over a network connection… Brogle at 377.
receiving first data collected from a real-world driving scene, the first data associated with the real-world driving scene and a performance of a real-world vehicle in the real-world driving scene; and
The current iteration of the path planning procedure uses obstacle detection of the cones to determine the correct path. The current code uses the same as, but simplifies it to allow for quicker calculation. Our cone driving module accepts cone locations from either the map, LiDAR or camera, classifying them as objects. Then, the vehicle navigates to drive within the track formed by cones safely without collision. Brogle at 380.
The vehicle navigating the drive is analogous to “performance of a real-world vehicle in the real-world driving scene.”
adjusting, for a current iteration, a parameter associated with an end-to-end (E2E) vehicle simulation that simulates operations of a simulated vehicle driving in a simulated driving scene, wherein: the
In the current implementation, all vehicle dynamics are handled purely by CARLA through Unreal Engine's vehicle physics. Some qualitative efforts have been made to match the stability of the FSAE vehicle during acceleration, braking and cornering actions through adjustments to existing vehicle parameters. This could be further reinforced by the completion of a quantitative comparison of the real and simulated vehicles’ poses during common driving scenarios. In the event that these results differ significantly, more accurate vehicle physics could then be implemented. Brogle at 383.
“More accurate vehicle physics” is analogous to “a parameter associated with operation of a simulated vehicle.
simulated driving scene is a simulation of the real-world driving scene,
The aim of this experiment was to verify that the LiDAR output obtained from the simulation using the method described in Section IV-A was sufficiently similar to that generated by the SICK LiDAR available on the FSAE vehicle.
Brogle does not appear to disclose:
the adjustment is based on a fidelity value of the E2E vehicle simulation in a previous iteration, and
the fidelity value is based on a comparison between second data collected from the E2E vehicle simulation in the previous iteration and the first data.
Kar, which is analogous art to the claimed invention, discloses:
the adjustment is based on a fidelity value of the E2E vehicle simulation in a previous iteration, and
The first objective of training our model is to bring the distribution of the rendered images to be closer to the distribution of real imagery XR. The Maximum Mean Discrepancy (MMD) [15] metric is a frequentist measure of the similarity of two distributions and has been used for training generative models [8, 29, 26] to match statistics of the generated distribution with the target distribution. Kar at pg. 4, col. 1.
the fidelity value is based on a comparison between second data collected from the E2E vehicle simulation in the previous iteration and the first data.
We, on other hand, use the MMD [15] distance metric for comparing distributions and also optimize a meta objective to produce samples suitable for a downstream task. Kar at pg. 2, col. 1.
The comparison of the distributions from the real world scenario and the simulation scenario is analogous to a “comparison between second data collected from the E2E vehicle simulation in the previous iteration and the first data.”
The optimization of a meta objective is analogous to an adjustment in a subsequent iteration of the simulation.
See also, FIG. 2:
PNG
media_image1.png
250
554
media_image1.png
Greyscale
See also FIG. 4, illustrating the MMD comparison:
PNG
media_image2.png
263
292
media_image2.png
Greyscale
Kar is analogous art to the claimed invention because both are directed to determining an accuracy of a driving simulation based on previous simulation results and a comparison to real world driving data. It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine the driving simulation analysis of Brogle with the MMD comparison of Kar to result in a system that compares simulation data distribution data with real world data and adjusts one or more parameters to reduce discrepancies between the real world and the simulation. Motivation to combine includes improved accuracy of subsequent simulation runs by improving the accuracy of the model that is utilized in the simulation (i.e., setting parameters to reduce a reality gap between the real world and the simulation), thus resulting in a simulation that can more accurately measure the safety of autonomous vehicles.
Claim 2
Brogle does not appear to disclose:
wherein the method further comprises: executing the E2E vehicle simulation in the previous iteration; collecting, from the E2E vehicle simulation, the second data associated with the simulated driving scene and a performance of the simulated vehicle in the simulated driving scene; and calculating the fidelity value for the E2E vehicle simulation based on the comparison between the first data and the second data.
Kar discloses:
wherein the method further comprises: executing the E2E vehicle simulation in the previous iteration;
After validating our approach on controlled experiments in a simulated setting, we now evaluate our approach for object detection on the challenging KITTI [12] dataset. KITTI was captured with a camera mounted on top of a car driving around the city of Karlsruhe in Germany. It consists of challenging traffic scenarios and scenes ranging from highways to urban to more rural neighborhoods. Contrary to the previous experiments, the distribution gap which we wish to reduce arises naturally here. Kar at pg. 7, col. 1.
collecting, from the E2E vehicle simulation, the second data associated with the simulated driving scene and a performance of the simulated vehicle in the simulated driving scene; and
Validation data V is formed by taking 100 random images (and their labels) from the KITTI train set. The rest of the training data (images only) forms XR. Kar at pg. 7, col. 1
calculating the fidelity value for the E2E vehicle simulation based on the comparison between the first data and the second data.
Table 3 reports the average precision at 0.5 IoU of the task network trained using data generated from different methods, when tested on the KITTI val set. We see that training with Meta-Sim beats just using the data from the probabilistic grammar. Kar at pg. 7, col. 2.
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine the driving simulation analysis of Brogle with the MMD comparison of Kar to result in a system that compares simulation data distribution data with real world data and adjusts one or more parameters to reduce discrepancies between the real world and the simulation. Motivation to combine includes improved accuracy of subsequent simulation runs by improving the accuracy of the model that is utilized in the simulation (i.e., setting parameters to reduce a reality gap between the real world and the simulation), thus resulting in a simulation that can more accurately measure the safety of autonomous vehicles.
Claim 3
Brogle discloses:
a component model modeling a component in the real-world driving scene.
…the LiDAR-based cone detection operates by clustering the LiDAR points, and classifying them as cones based on the number of points in the cluster, which has been tuned to the maximum distance at which cones are detected reliably based on the resolution of the SICK LiDAR. Brogle at 381.
Brogle does not appear to teach or disclose:
wherein the parameter adjusted based on the fidelity value of the E2E vehicle simulation in the previous iteration is for
Kar discloses:
wherein the parameter adjusted based on the fidelity value of the E2E vehicle simulation in the previous iteration is for
The first objective of training our model is to bring the distribution of the rendered images to be closer to the distribution of real imagery XR. The Maximum Mean Discrepancy (MMD) [15] metric is a frequentist measure of the similarity of two distributions and has been used for training generative models [8, 29, 26] to match statistics of the generated distribution with the target distribution. Kar at pg. 4, col. 1.
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to utilize the cone classification model of Brogle with the fidelity calculation of Kar to determine the fidelity of the simulation based on variations in cone identification in the real-world and the simulation because the cone classification model includes data collected from a previous iteration of the simulation. Motivation to combine includes improved fidelity determination by taking into account locations of objects in the real-world versus objects identified in the simulation, thus more accurately identifying deviations between the simulation and the real-world. By identifying where a simulation deviates from the real-world, adjustments can be made to the simulation to reduce error when using the simulation for testing.
Claim 4
Brogle discloses:
wherein the component model for which the parameter is adjusted models a sensor in the real-world driving scene.
The aim of this experiment was to verify that the LiDAR output obtained from the simulation using the method described in Section IV-A was sufficiently similar to that generated by the SICK LiDAR available on the FSAE vehicle. Brogle at 380.
Claim 5
Brogle discloses:
wherein the component model for which the parameter is adjusted models an object in the real-world driving scene.
This is required in order to allow cone detection algorithms to be tested on the driving simulator with a high degree of certainty that the results will be transferable to the SICK LiDAR. This was achieved by simulating a scenario mimicing that of a previous test of the FSAE vehicle, and verifying that a similar set of cones was detected by the same algorithm used in the FSAE vehicle test. Brogle at 380.
Claim 6
Brogle discloses:
wherein the component model for which the parameter is adjusted models at least one of a pose or vehicle dynamic of the real-world vehicle.
The results of these scenarios for both the real and simulated vehicles are presented in Table III, in which it can be seen that the radius of the turning circle of the simulated vehicle is within 5% of the physical vehicle on average. While there is some error present in the vehicle dynamics exhibited by the simulation system, the constant feedback loop during autonomous operation works to minimise the effects of these differences. Brogle at 380.
Claim 7
Brogle discloses:
wherein the component model for which the parameter is adjusted models a road attribute.
This should result in the vehicle being capable of driving and mapping a semi-structured race track (with edges delineated by either cones, as displayed in Fig. 1, or road edges) with no prior knowledge before generating an optimised path and redriving the track at a greater speed. Brogle at 375.
Claim 8
Brogle discloses:
wherein the adjusting the parameter associated with the E2E vehicle simulation comprises: identifying a mismatch between the component in the real-world driving scene and the component model in the simulated driving scene.
This was achieved by simulating a scenario mimicing that of a previous test of the FSAE vehicle, and verifying that a similar set of cones was detected by the same algorithm used in the FSAE vehicle test. Brogle at 380.
Claim 9
Brogle discloses:
executing, based on a component test definition, a test for the component model; collecting third data from the executing the test; receiving fourth data collected from the component in the real-world driving scene, the fourth data based on the component test definition; and
As can be seen in Fig. 13, the number of points returned by the simulated LiDAR is within ≈15% of the physical LiDAR, and demonstrates a realistic decrease in the number of points returned by an object as distance increases. Brogle at 381.
FIG. 13 illustrates four tests of a LiDAR component according to specifications of the component. For each of the tests, the real and simulated results are shown and compared (i.e., the number of points returned by the simulated LiDAR is within ≈15% of the physical LiDAR).
PNG
media_image3.png
542
584
media_image3.png
Greyscale
Kar discloses:
calculating a fidelity value for the component model based on [the E2E vehicle simulation in a previous iteration]
The first objective of training our model is to bring the distribution of the rendered images to be closer to the distribution of real imagery XR. The Maximum Mean Discrepancy (MMD) [15] metric is a frequentist measure of the similarity of two distributions and has been used for training generative models [8, 29, 26] to match statistics of the generated distribution with the target distribution. Kar at pg. 4, col. 1.
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine the testing performed by Brogle with the fidelity determination of Kar to result in a system that utilizes test cases in determining the fidelity of the model because the tests are performed in previous iterations of the simulation. Motivation to combine includes better control over what component of the simulation is being tested and therefore which parts of the simulation contribute to the fidelity of the simulation. Thus, more discrete issues with the simulation can be addressed, resulting in a more accurate simulation for later utilization in tests of vehicles.
Claim 10
Brogle discloses:
This could be further reinforced by the completion of a quantitative comparison of the real and simulated vehicles’ poses during common driving scenarios. In the event that these results differ significantly, more accurate vehicle physics could then be implemented. The response time of our simulation to a control command is significantly lower than that of the FSAE vehicle. In order to improve the accuracy of the simulator, it is proposed that a processing delay be added to control commands. Brogle at 383.
The “quantitative comparison of the real and simulated vehicles’ poses during common driving scenarios” is analogous to “previous iterations” of the driving simulator.
The “results that differ significantly” is analogous to a failure of a comparison (e.g., a fidelity value) to satisfy a threshold.
“More accurate vehicle physics could then be implemented” is analogous to adjusting a parameter.
Brogle does not appear to disclose:
wherein the adjusting the parameter associated with the E2E vehicle simulation
Kar discloses:
wherein the adjusting the parameter associated with the E2E vehicle simulation
In the current implementation, all vehicle dynamics are handled purely by CARLA through Unreal Engine's vehicle physics. Some qualitative efforts have been made to match the stability of the FSAE vehicle during acceleration, braking and cornering actions through adjustments to existing vehicle parameters. This could be further reinforced by the completion of a quantitative comparison of the real and simulated vehicles’ poses during common driving scenarios. In the event that these results differ significantly, more accurate vehicle physics could then be implemented. Brogle at 383.
“More accurate vehicle physics” is analogous to “a parameter associated with operation of a simulated vehicle.
It would have been obvious to a person having ordinary skill in the art, before the effective filing date of the claimed invention, to combine the identification of an unacceptable value from a previous iteration with the disclosure of Kar related to adjusting parameters of the simulation and further disclosure of a fidelity value to compare a fidelity value calculated from a previous iteration with a threshold and, if the simulation did not perform as expected, adjust the simulation to improve future iterations. Motivation to combine includes an improved simulation that has been tuned over a number of iterations to iteratively adjust parameters, thus resulting in a more accurate representation of a real-world scenario when the simulation is implemented.
Claims 11-16
Claims 11-16 include substantially the same steps as those performed by the system recited in claims 1-4 and 8-9. Accordingly, for at least the same reasons, claims 11-16 are rejected under 35 U.S.C. 103 as being obvious over Brogle in view of Kar.
Claims 17-20
Claims 17-20 include substantially the same steps as those performed by the system recited in claims 1-2 and 8-9. Accordingly, for at least the same reasons, claims 11-16 are rejected under 35 U.S.C. 103 as being obvious over Brogle in view of Kar.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Rong, et al., "LGSVL Simulator: A High Fidelity Simulator for Autonomous Driving," 2020 IEEE 23rd International Conference on Intelligent Transportation Systems (ITSC)
Stocco, et al., "Mind the Gap! A Study on the Transferability of Virtual Versus Physical-World Testing of Autonomous Driving Systems," IEEE Transactions on Software Engineering, Volume: 49, Issue: 4
Communication
Any inquiry concerning this communication or earlier communications from the examiner should be directed to JOSEPH MORRIS whose telephone number is (703)756-5735. The examiner can normally be reached M-F 8:30-5:00.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, 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.
JOSEPH MORRIS
Examiner
Art Unit 2188
/JOSEPH P MORRIS/Examiner, Art Unit 2188
/EUNHEE KIM/Primary Examiner, Art Unit 2188
Prosecution Insights