DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to the application filed on 3/31/2022. Claims 1-20 are pending in this application. Claims 1, 6, and 14 are independent claims.
Claims 1-20 are rejected under 35 U.S.C. 101.
Claims 1, 6, 7, 14, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Peake et al. (US PGPub 20200074266).
Claims 2-5, 8-13, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Peake in view of Manivasagam et al. (US PGPub 20200301799).
This action is made Non-Final.
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 an abstract idea without significantly more. Examiner has evaluated the claims under the framework provided in the 2019 Patent Eligibility Guidance published in the Federal Register 01/07/2019 and has provided such analysis below.
Step 1: Claims 1-5 are directed to systems and fall within the statutory category of machines; Claims 6-13 are directed to a method and fall within the statutory category of processes; and Claims 14-20 are directed to non-transitory computer readable media and fall within the statutory category of articles of manufacture. Therefore, claims 1-20 are directed to patent eligible categories of invention.
Step 2A Prong 1: The limitations of claim 1 of “determining, based at least in part on the simulation data, an attribute associated with the simulated object; determining radar background data, based at least in part on the simulated environment, wherein the radar background data includes a second plurality of radar data points; determining an overlay region within the radar background data, based at least in part on a position of the simulated object relative to a simulated radar sensor within the autonomous vehicle simulation; generating simulation radar data based at least in part on the radar object data and the radar background data, wherein the simulation radar data includes a first radar data point of the first plurality of radar data points within the overlay region and a second radar data point of the second plurality of radar data points within the overlay region”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an object attribute based on simulation data and determine radar background data of a plurality of radar data points based on a simulation environment. A person can also mentally determine an overlay region within radar background data of a vehicle simulation based on a position of a simulation object and generate simulation radar data based on radar object data and radar background data where the simulation data includes points within the overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong 1 step 2A.
The limitations of claims 6 and 14 of “determining, based at least in part on the data associated with the simulated object, radar object data including a first plurality of radar data points; determining radar background data including a second plurality of radar data points; generating simulation radar data based at least in part on the first plurality of radar data points and the second plurality of radar data points”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine radar object data based on simulated object data, determine radar background, and generate simulation radar data based on radar object data and radar background data. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A.
Step 2A Prong 2: This judicial exception is not integrated into a practical application. In particular, claims 1 and 14 respectively recite additional elements of “A system comprising: one or more processors; and one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising:” and “A non-transitory computer-readable medium containing program code that, when executed by one or more processors, causes the one or more processors to perform operations comprising”, which are merely recitations of generic computing components and functions being used as a tool to implement the judicial exception (see MPEP § 2106.05(f)) which does not integrate a judicial exception into a practical application.
Claim 1 also recites additional elements such as “receiving simulation data associated with an autonomous vehicle simulation, the simulation data including a simulated environment and a simulated object; retrieving, from a radar data store, radar object data corresponding to the simulated object, based at least in part on comparing the attribute to a second attribute associated with the radar object data, wherein the radar object data includes a first plurality of radar data points; and rendering the simulated object during the autonomous vehicle simulation, wherein rendering the simulated object includes providing the simulation radar data as input to the simulated radar sensor” which are merely recitations of insignificant extra-solution data gathering and outputting activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. Therefore, this additional element does not integrate the abstract idea into a practical application and it does not impose any meaningful limits on practicing the abstract idea. The claim is directed to an abstract idea under Steps 2A Prong 1 and 2. The insignificant extra-solution activities are further addressed below under step 2B as also being Well-Understood, Routine, and Conventional (WURC).
Further, claims 6 and 14 also recite additional elements such as “receiving data associated with a simulated object in a simulation; and rendering the simulated object during the simulation, wherein rendering the simulated object includes providing the simulation radar data as input to a simulated radar sensor” which are merely recitations of insignificant extra-solution data gathering outputting activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. Therefore, this additional element does not integrate the abstract idea into a practical application and it does not impose any meaningful limits on practicing the abstract idea. The claims are directed to an abstract idea under Steps 2A Prong 1 and 2. The insignificant extra-solution activities are further addressed below under step 2B as also being Well-Understood, Routine, and Conventional (WURC).
Step 2B: The claims 1, 6, and 14 do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. As discussed above with respect to integration of the abstract idea into a practical application, the additional elements amount to no more than generic computing components and functions being used as a tool to implement the judicial exception which do not amount to significantly more than the abstract idea. Further, the insignificant extra-solution data gathering and outputting activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network … iv. Storing and retrieving information in memory").
Therefore, these additional elements, alone or in combination, do not amount to significantly more than the judicial exception. Having concluded analysis within the provided framework, claims 1, 6, and 14 do not recite patent eligible subject matter under 35 U.S.C. § 101.
Regarding claims 2, 8, and 16, they recite additional limitations of “wherein generating the simulation radar data further comprises: determining, based at least in part on a first probability, a first subset of the first plurality of radar data points to retain within the overlay region; and determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain within the overlay region, wherein the first probability is greater than the second probability”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine probabilities for radar data points to retain within an overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A. Further, the claims do not recite any further additional elements and for the same reasons as above with regard to integration into a practical application and whether additional elements amount to significantly more, the claims also fail both Step 2A prong 2, thus the claims are directed to the judicial exception as they have not been integrated into a practical application, and fail Step 2B as not amounting to significantly more. Therefore, claims 2, 8, and 16 do not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claim 3, it recites additional limitations of “wherein generating the simulation radar data comprises: determining a second overlay region surrounding the overlay region within the radar background data; determining, based at least in part on a first probability, a first subset of the radar background data to retain within the overlay region; determining, based at least in part on a second probability, a second subset of the radar background data to retain within the second overlay region, wherein the first probability is less than the second probability; and determining, based at least in part on a third probability, a third subset of the radar background data to retain outside of the second overlay region, wherein the second probability is less than the third probability”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine a second overlay region surrounding an overlay region within radar background data. A person can also mentally determine a probability regarding retaining radar background within the overlay region and determine a probability regarding retaining radar background data within the second overlay region. A person can also mentally determine a probability regarding retaining radar background data outside of the second overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong 1 step 2A. Further, the claim does not recite any further additional elements and for the same reasons as above with regard to integration into a practical application and whether additional elements amount to significantly more, the claim also fails both Step 2A prong 2, thus the claim is directed to the judicial exception as they have not been integrated into a practical application, and fails Step 2B as not amounting to significantly more. Therefore, claim 3 does not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claims 4, 11, and 19, they recite additional limitations of “wherein generating the simulation radar data further comprises: determining, based at least in part on a fourth probability, a fourth subset of the radar object data to retain within the overlay region; and determining, based at least in part on a fifth probability, a fifth subset of the radar object data to retain within the second overlay region, wherein the fourth probability is greater than the fifth probability”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine probabilities for radar object data to retain within an overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A. Further, the claims do not recite any further additional elements and for the same reasons as above with regard to integration into a practical application and whether additional elements amount to significantly more, the claims also fail both Step 2A prong 2, thus the claims are directed to the judicial exception as they have not been integrated into a practical application, and fail Step 2B as not amounting to significantly more. Therefore, claims 4, 11, and 19 do not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claim 5, it recites additional limitations of “further comprising generating the radar background data, wherein generating the radar background data comprises: determining an object represented in the log data; determining a first subset of the radar data associated with the object; and determining the radar background data, by removing the first subset of the radar data associated with the object from the radar data representing the environment”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an object represented in log data, determine radar data associated with the object, and remove radar data associated with the object to determine radar background data. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A.
Further, regarding claim 5, it recites additional element recitations of “receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment” which are merely recitations of insignificant extra-solution data gathering activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. The claim does not recite any further additional elements and for the same reasons as above with regard to integration into a practical application the claim fails Step 2A prong 2, thus the claim is directed to the judicial exception as it has not been integrated into a practical application. Further, regarding Step 2B the claim does not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. In particular, the insignificant extra-solution data gathering activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network"). Thus, the claim also fails Step 2B as not amounting to significantly more. Therefore, claim 5 does not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claims 7 and 15, they recite additional limitations of “wherein generating the simulation radar data comprises: determining an overlay region within the radar background data, based at least in part on a position of the simulated object relative to the simulated radar sensor within the simulation”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an overlay region within radar background data of a simulation based on a position of a simulation object. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A.
Further regarding claims 7 and 15, they recite additional element recitations of “overlaying the radar object data onto the radar background data, within the overlay region, wherein the simulation radar data includes a first radar data point of the first plurality of radar data points within the overlay region and a second radar data point of the second plurality of radar data points within the overlay region” which are merely recitations of insignificant extra-solution data outputting activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. These claims do not recite any further additional elements and for the same reasons as above with regard to integration into a practical application these claims fail Step 2A prong 2, thus the claims are directed to the judicial exception as they have not been integrated into a practical application. Further, regarding Step 2B the claims do not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. In particular, the insignificant extra-solution data gathering activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network"). Thus, the claims also fail Step 2B as not amounting to significantly more. Therefore, claims 7 and 15 do not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claims 9 and 17, they recite additional limitations of “determining, based at least in part on a first probability, a first subset of the second plurality of radar data points to retain within the overlay region; and determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain outside of the overlay region, wherein the first probability is less than the second probability”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine probabilities for radar data points to retain within an overlay region and outside of an overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A. Further, the claims do not recite any further additional elements and for the same reasons as above with regard to integration into a practical application and whether additional elements amount to significantly more, the claims also fail both Step 2A prong 2, thus the claims are directed to the judicial exception as they have not been integrated into a practical application, and fail Step 2B as not amounting to significantly more. Therefore, claims 9 and 17 do not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claims 10 and 18, they recite additional limitations of “determining a first overlay region within the radar background data, based at least in part on a position of the simulated object relative to the simulated radar sensor within the simulation; determining a second overlay region surrounding the first overlay region within the radar background data; determining, based at least in part on a first probability, a first subset of the second plurality of radar data points to retain within the first overlay region; determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain within the second overlay region, wherein the first probability is less than the second probability; and determining, based at least in part on a third probability, a third subset of the second plurality of radar data points to retain outside of the second overlay region, wherein the second probability is less than the third probability”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an overlay region within radar background data of a simulation based on a position of a simulation object and determine a second overlay region surrounding an overlay region within radar background data. A person can also mentally determine a probability regarding retaining radar background within the overlay region and determine a probability regarding retaining radar background data within the second overlay region. A person can also mentally determine a probability regarding retaining radar background data outside of the second overlay region. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claims recite an abstract idea under Prong 1 step 2A. Further, the claims do not recite any further additional elements and for the same reasons as above with regard to integration into a practical application and whether additional elements amount to significantly more, the claims also fail both Step 2A prong 2, thus the claims are directed to the judicial exception as they have not been integrated into a practical application, and fail Step 2B as not amounting to significantly more. Therefore, claims 10 and 18 do not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claim 12, it recites additional limitations of “wherein determining the radar background data comprises: determining, based at least in part on the sensor data, that an agent is not represented within the radar data; determining, based at least in part on the sensor data, an attribute associated with the environment”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine that an agent is not represented in radar data. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong 1 step 2A.
Further regarding claim 12, it recites additional element recitations of “receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment; and storing a radar background entry in a radar background data store, the radar background entry comprising the attribute and the radar data” which are merely recitations of insignificant extra-solution data gathering activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. The claim does not recite any further additional elements and for the same reasons as above with regard to integration into a practical application the claim fails Step 2A prong 2, thus the claim is directed to the judicial exception as it has not been integrated into a practical application. Further, regarding Step 2B the claim does not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. In particular, the insignificant extra-solution data gathering activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network … iv. Storing and retrieving information in memory"). Thus, the claim also fails Step 2B as not amounting to significantly more. Therefore, claim 12 does not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claim 13, it recites additional limitations of “wherein determining the radar background data comprises: determining an object represented in the log data; determining a first subset of the radar data associated with the object; and determining the second plurality of radar data points, by removing the first subset of the radar data associated with the object from the radar data representing the environment”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an object represented in log data, determine radar data associated with the object, and remove radar data associated with the object to determine a plurality of radar data points. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong 1 step 2A.
Further regarding claim 13, it recites additional element recitations of “receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment” which are merely recitations of insignificant extra-solution data gathering activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. The claim does not recite any further additional elements and for the same reasons as above with regard to integration into a practical application the claim fails Step 2A prong 2, thus the claim is directed to the judicial exception as it has not been integrated into a practical application. Further, regarding Step 2B the claim does not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. In particular, the insignificant extra-solution data gathering activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network"). Thus, the claim also fails Step 2B as not amounting to significantly more. Therefore, claim 13 does not recite patent eligible subject matter under 35 U.S.C. §101.
Regarding claim 20, it recites additional limitations of “wherein determining the radar background data comprises: determining, based at least in part on the log data, an object represented in the log data; determining a first subset of the radar data associated with the object; and determining the second plurality of radar data points, by removing the first subset of the radar data associated with the object from the radar data representing the environment”, as drafted, is a process that, but for the recitation of generic computing components, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper. For example, a person can mentally determine an object represented in log data, determine radar data associated with the object, and remove radar data associated with the object to determine a plurality of radar data points. If a claim limitation, under its broadest reasonable interpretation, covers performance of the limitation in the mind or with the use of pen and paper but for the recitation of generic computer components, then it falls within the “Mental Processes” grouping of abstract ideas. Accordingly, the claim recites an abstract idea under Prong 1 step 2A.
Further regarding claim 20, it recites additional element recitations of “receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment” which are merely recitations of insignificant extra-solution data gathering activity (See MPEP § 2106.05(g)) which does not integrate a judicial exception into a practical application. The claim does not recite any further additional elements and for the same reasons as above with regard to integration into a practical application the claim fails Step 2A prong 2, thus the claim is directed to the judicial exception as it has not been integrated into a practical application. Further, regarding Step 2B the claim does not include additional elements, alone or in combination, that are sufficient to amount to significantly more than the judicial exception. In particular, the insignificant extra-solution data gathering activities are also Well-Understood, Routine and Conventional (see MPEP § 2106.05(d)(ll) "The courts have recognized the following computer functions as well understood, routine, and conventional functions when they are claimed in a merely generic manner (e.g., at a high level of generality) or as insignificant extra-solution activity. i. Receiving or transmitting data over a network"). Thus, the claim also fails Step 2B as not amounting to significantly more. Therefore, claim 20 does not recite patent eligible subject matter under 35 U.S.C. §101.
Accordingly, claims 1-20 do not recite patent eligible subject matter and are rejected under 35 U.S.C. §101.
Claim Rejections - 35 USC § 102
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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
Claims 1, 6, 7, 14, and 15 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Peake et al. (US PGPub 20200074266) (hereinafter “Peake”).
Regarding Claim 1, Peake anticipates a system comprising: one or more processors; and one or more computer-readable media storing computer-executable instructions that, when executed, cause the one or more processors to perform operations comprising: receiving simulation data associated with an autonomous vehicle simulation, the simulation data including a simulated environment and a simulated object ([0098] “As depicted by FIG. 1, automated training dataset generator 100 may further include a sensor simulator 104 configured to generate simulated sensor data within a virtual environment (e.g., any of the virtual environment(s) depicted and described for FIGS. 2A, 2B, 3, 4A, and/or 4B). The simulated sensor data may be associated with one or more objects or surfaces (e.g., 202-230, 292-296, 391-398, 401-418, and/or 451-482) in the virtual environment”, where [0062] “FIG. 2A illustrates an example photo-realistic scene 200 of a virtual environment in the direction of travel of an autonomous vehicle within the virtual environment of scene 200 in accordance with various embodiments disclosed herein”; [0011] Processors and non-transitory computer-readable media comprising instructions are used in generating the virtual environment);
determining, based at least in part on the simulation data, an attribute associated with the simulated object ([0098] “The simulated sensor data may be associated with one or more objects or surfaces (e.g., 202-230, 292-296, 391-398, 401-418, and/or 451-482) in the virtual environment”, where as shown in Figure 2A there are attributes determined such as different object types of vehicle types and road lines);
retrieving, from a radar data store, radar object data corresponding to the simulated object, based at least in part on comparing the attribute to a second attribute associated with the radar object data, wherein the radar object data includes a first plurality of radar data points ([0069] A point cloud generated from two lidar devices is used to generate the virtual environment of Figure 2B, which includes an object type of vehicles such as 296A and 296D compared to a second object type of a ground plane 294 underneath the vehicles. Further, the “point cloud 290 may comprise data saved in a database”; [0100] “In some aspects the, sensor simulator 104 may generate simulated lidar data or simulated radar data” and [0111] “As discussed herein, the sensors may include one or more lidar devices, cameras, radar devices, thermal imaging units, IMUs, and/or other sensor types, whether real or virtual”, thus examiner notes although lidar is used to generate the point cloud, that Peake also encompasses radar data and radar sensors being used instead);
determining radar background data, based at least in part on the simulated environment, wherein the radar background data includes a second plurality of radar data points ([0069] The point cloud generated from two lidar devices that is used to generate the virtual environment of Figure 2B, includes a ground plane 294, which is interpreted as radar background data comprising a plurality of radar data points);
determining an overlay region within the radar background data, based at least in part on a position of the simulated object relative to a simulated radar sensor within the autonomous vehicle simulation ([0069] The ground plane of 294 within the point cloud of Figure 2B is interpreted as an overlay region within the radar background data, where lidar sensors capture positions of vehicles, as shown by the different positions of vehicles 296D and 296A for example. Further the point cloud may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment);
generating simulation radar data based at least in part on the radar object data and the radar background data, wherein the simulation radar data includes a first radar data point of the first plurality of radar data points within the overlay region and a second radar data point of the second plurality of radar data points within the overlay region ([0098] “The simulated sensor data may include any of simulated lidar data, simulated camera, simulated thermal data, and/or any other simulated sensor data simulating real-world data that may be generated by, or captured by, real-world sensors”; [0069] Figure 2B shows the point clouds of vehicles 296D and 296A as including a first and second radar data point of a plurality of data points within an overlay region of the road);
and rendering the simulated object during the autonomous vehicle simulation, wherein rendering the simulated object includes providing the simulation radar data as input to the simulated radar sensor ([0069] and Figures 2A-2B, The point cloud of an autonomous vehicle simulation generated by lidar sensors as shown in Figure 2B is rendered to generate a virtual environment such as Figure 2A).
Regarding Claim 6, Peake anticipates a method comprising: receiving data associated with a simulated object in a simulation ([0098] “As depicted by FIG. 1, automated training dataset generator 100 may further include a sensor simulator 104 configured to generate simulated sensor data within a virtual environment (e.g., any of the virtual environment(s) depicted and described for FIGS. 2A, 2B, 3, 4A, and/or 4B). The simulated sensor data may be associated with one or more objects or surfaces (e.g., 202-230, 292-296, 391-398, 401-418, and/or 451-482) in the virtual environment”);
determining, based at least in part on the data associated with the simulated object, radar object data including a first plurality of radar data points ([0069] A point cloud generated from two lidar devices is used to generate the virtual environment of Figure 2B, which includes a plurality of data points associated with a simulated object of a vehicle, such as 296A; [0100] “In some aspects the, sensor simulator 104 may generate simulated lidar data or simulated radar data” and [0111] “As discussed herein, the sensors may include one or more lidar devices, cameras, radar devices, thermal imaging units, IMUs, and/or other sensor types, whether real or virtual”, thus examiner notes although lidar is used to generate the point cloud, that Peake also encompasses radar data and radar sensors being used instead);
determining radar background data including a second plurality of radar data points ([0069] The point cloud generated from two lidar devices that is used to generate the virtual environment of Figure 2B, includes a ground plane 294, which is interpreted as radar background data comprising a plurality of radar data points);
generating simulation radar data based at least in part on the first plurality of radar data points and the second plurality of radar data points ([0098] “The simulated sensor data may include any of simulated lidar data, simulated camera, simulated thermal data, and/or any other simulated sensor data simulating real-world data that may be generated by, or captured by, real-world sensors”; [0069] Figure 2B shows the lidar sensor point clouds of a vehicle 296A and a ground plane 294 as the first and second plurality of radar data points);
and rendering the simulated object during the simulation, wherein rendering the simulated object includes providing the simulation radar data as input to a simulated radar sensor ([0069] and Figures 2A-2B, The point cloud of an autonomous vehicle simulation generated by lidar sensors as shown in Figure 2B is rendered to generate a virtual environment such as Figure 2A).
Regarding Claim 7, Peake anticipates the method as recited in claim 6, wherein generating the simulation radar data comprises: determining an overlay region within the radar background data, based at least in part on a position of the simulated object relative to the simulated radar sensor within the simulation ([0069] The ground plane of 294 within the point cloud of Figure 2B is interpreted as an overlay region within the radar background data, where lidar sensors capture positions of vehicles, as shown by the different positions of vehicles 296D and 296A for example. Further the point cloud may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment);
and overlaying the radar object data onto the radar background data, within the overlay region, wherein the simulation radar data includes a first radar data point of the first plurality of radar data points within the overlay region and a second radar data point of the second plurality of radar data points within the overlay region ([0069] The lidar sensor point cloud of Figure 2B includes a vehicle such as 296A as radar object data that is overlayed on the ground plane 294 point cloud, thus also within the overlay region. Further, the point clouds of vehicles 296A and 296D include a first and second radar data point of a plurality of data points within an overlay region of the road).
Regarding claim 14, it is the system claim, having similar limitations of claim 6. The additional limitations of claim 14, with respect to claim 6, is that it has one or more non-transitory computer-readable media storing instructions executable by a processor. Peake anticipates one or more non-transitory computer-readable media storing instructions executable by a processor ([0056] “In general, a computer program or computer based product in accordance with some embodiments may include a computer usable storage medium, or tangible, non-transitory computer-readable medium (e.g., standard random access memory (RAM), an optical disc, a universal serial bus (USB) drive, or the like) having computer-readable program code or computer instructions embodied therein, wherein the computer-readable program code or computer instructions may be installed on or otherwise adapted to be executed by the processor(s) 150”). The remaining limitations of claim 14 are also rejected under the similar rationale as cited in the rejection of claim 6.
Regarding claim 15, it is the article claim, having similar limitations of claim 7. Thus, claim 15 is also rejected under the similar rationale as cited in the rejection of claim 7.
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.
Claims 2-5, 8-13, and 16-20 are rejected under 35 U.S.C. 103 as being unpatentable over Peake in view of Manivasagam et al. (US PGPub 20200301799) (hereinafter “Manivasagam”).
Regarding claim 2, Peake teaches the system as recited in claim 1. Peake does not specifically teach, however Manivasagam teaches wherein generating the simulation radar data further comprises: determining, based at least in part on a first probability, a first subset of the first plurality of radar data points to retain within the overlay region ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where a vehicle is interpreted as a subset of radar data points that has a probability of being removed or not; [0058] “Although portions of the present disclosure are described for the purpose of illustration with respect to the generation and refinement of synthetic LiDAR data, the techniques described herein can also be applied to generate and refine other forms of sensor data such as, for example, RADAR data” thus examiner notes that within Manivasagam portions that mention LiDAR can be applied to RADAR applications as well);
and determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain within the overlay region, wherein the first probability is greater than the second probability ([0132] “At 502, a computing system can obtain a three-dimensional map of an environment. The three-dimensional map can be any type of map that can be used by a physics-based approach to generate an initial three-dimensional point cloud that simulates LiDAR data captured within the environment”, where for example the point cloud can include a road, where the road is interpreted as an overlay region; [0134] LiDAR points assigned to a vehicle on the road may be removed as a non-stationary semantic class, thus having a higher probability of not being retained compared to the road).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining probabilities for radar data points to retain within an overlay region, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to prevent multiple instances of the same non-stationary object from appearing in the resulting maps (Manivasagam, [0091]).
Regarding claim 3, Peake teaches the system as recited in claim 1. Peake does not specifically teach, however Manivasagam teaches wherein generating the simulation radar data comprises: determining a second overlay region surrounding the overlay region within the radar background data ([0124] “As illustrated in FIG. 4, in some implementations, the inputs to the model include some or all of the following: Real-valued channels: range … Integer-valued channels: laser id, semantic class (e.g., road, vehicle, background … The input channels can represent observable factors potentially influencing each ray's chance of not returning”, where the background is interpreted as a second overlay region surrounding an overlay region of a road);
determining, based at least in part on a first probability, a first subset of the radar background data to retain within the overlay region ([0132] “At 502, a computing system can obtain a three-dimensional map of an environment. The three-dimensional map can be any type of map that can be used by a physics-based approach to generate an initial three-dimensional point cloud that simulates LiDAR data captured within the environment”, where for example the point cloud can include a road, where the road is interpreted as radar background data within an overlay region; [0143] “At 508, the computing system can process, using a machine-learned model, the initial three-dimensional point cloud to predict a respective dropout probability for one or more of the plurality of points”);
determining, based at least in part on a second probability, a second subset of the radar background data to retain within the second overlay region, wherein the first probability is less than the second probability ([0124]-[0125] “As illustrated in FIG. 4, in some implementations, the inputs to the model include some or all of the following: Real-valued channels: range … Integer-valued channels: laser id, semantic class (e.g., road, vehicle, background) … The input channels can represent observable factors potentially influencing each ray's chance of not returning. The output of the model is a ray dropout probability that predicts, for each element in the array, if it returns or not (e.g., with some probability)” thus since the range effects the dropout probability of a ray, the background, which is at a larger range than the road to a lidar sensor, is interpreted as having a larger dropout probability than the road);
and determining, based at least in part on a third probability, a third subset of the radar background data to retain outside of the second overlay region, wherein the second probability is less than the third probability ([0145]-[0146] “At 510, the computing system can generate an adjusted three-dimensional point cloud from the initial three-dimensional point cloud based at least in part on the respective dropout probabilities … For example, for each of such points, the computing system can determine a respective intensity value based at least in part on intensity data included in the three-dimensional map for locations within a radius of a respective location associated with such point in either the initial three-dimensional point cloud or the adjusted three-dimensional point cloud”, where locations outside of the determined radius is interpreted as radar background data outside of the second overlay region, which since locations outside of the radius are not included in the adjusted map, they have a higher dropout probability than the radar background data within the radius).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining a second overlay region surrounding the overlay region and determining probabilities regarding retaining radar background data within the overlay region and second overlay region, and outside of the second overlay region, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to generate simulation sensor data that more realistically simulates real-world sensor data, which further improves testing of autonomous vehicle systems, such as edge cases, thus leading to improved safety of autonomous vehicles (Manivasagam, [0029] and [0054]).
Regarding claim 4, Peake teaches the system as recited in claim 3. Peake does not specifically teach, however Manivasagam teaches wherein generating the simulation radar data further comprises: determining, based at least in part on a fourth probability, a fourth subset of the radar object data to retain within the overlay region ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where a vehicle is interpreted as a subset of radar data points that has a probability of being removed or not);
and determining, based at least in part on a fifth probability, a fifth subset of the radar object data to retain within the second overlay region, wherein the fourth probability is greater than the fifth probability ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where a tree is interpreted as being a radar object data in the second overlay region of the background. Further, since the vehicle may be removed as a non-stationary semantic class, it is interpreted as having a higher probability of not being retained compared to a tree).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining probabilities for radar object data to retain within an overlay region, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to prevent multiple instances of the same non-stationary object from appearing in the resulting maps (Manivasagam, [0091]).
Regarding claim 5, Peake teaches the system as recited in claim 1, further comprising generating the radar background data, wherein generating the radar background data comprises: receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment ([0069] A point cloud as shown in Figure 2B may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment, thus includes log data based on sensor data captured by a vehicle operating in an environment, where the log data includes radar data representing the environment);
determining an object represented in the log data ([0069] Figure 2B shows an object of a vehicle, such as 296A, represented in the log data);
determining a first subset of the radar data associated with the object ([0069] Figure 2B shows a point cloud generated by lidar sensors, where 296A points to a subset of radar data associated with a vehicle);
Peake does not specifically teach, however Manivasagam teaches determining the radar background data, by removing the first subset of the radar data associated with the object from the radar data representing the environment ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where points of a non-stationary semantic class that are removed is interpreted as removing a first subset of the radar data associated with an object from the radar data representing the environment; [0094] “Statistical outlier removal can be conducted to clean the road LiDAR mesh due to spurious points from incomplete dynamic object removal”, thus further the non-stationary object removal is involved in determining radar background data of the road).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining radar background data by removing a subset of radar data associated with the object from the radar data representing the environment, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to prevent multiple instances of the same non-stationary object from appearing in the resulting maps (Manivasagam, [0091]).
Regarding claim 8, it is the method claim, having similar limitations of claim 2. Thus, claim 8 is also rejected under the similar rationale as cited in the rejection of claim 2.
Regarding claim 9, Peake teaches the system as recited in claim 7. Peake does not specifically teach, however Manivasagam teaches wherein generating the simulation radar data further comprises: determining, based at least in part on a first probability, a first subset of the second plurality of radar data points to retain within the overlay region ([0132] “At 502, a computing system can obtain a three-dimensional map of an environment. The three-dimensional map can be any type of map that can be used by a physics-based approach to generate an initial three-dimensional point cloud that simulates LiDAR data captured within the environment”, where for example the point cloud can include a road, where the road is interpreted as radar background data within an overlay region; [0143] “At 508, the computing system can process, using a machine-learned model, the initial three-dimensional point cloud to predict a respective dropout probability for one or more of the plurality of points”);
and determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain outside of the overlay region, wherein the first probability is less than the second probability ([0124]-[0125] “As illustrated in FIG. 4, in some implementations, the inputs to the model include some or all of the following: Real-valued channels: range … Integer-valued channels: laser id, semantic class (e.g., road, vehicle, background) … The input channels can represent observable factors potentially influencing each ray's chance of not returning. The output of the model is a ray dropout probability that predicts, for each element in the array, if it returns or not (e.g., with some probability)” thus since the range effects the dropout probability of a ray, the background, which is at a larger range than the road to a lidar sensor, is interpreted as a second subset of a plurality of radar data points outside of the overlay region having a larger dropout probability than the road).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining probabilities for radar data points to retain within an overlay region and outside of an overlay region, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to generate simulation sensor data that more realistically simulates real-world sensor data, which further improves testing of autonomous vehicle systems, such as edge cases, thus leading to improved safety of autonomous vehicles (Manivasagam, [0029] and [0054]).
Regarding claim 10, Peake teaches the system as recited in claim 6, wherein generating the simulation radar data further comprises: determining a first overlay region within the radar background data, based at least in part on a position of the simulated object relative to the simulated radar sensor within the simulation ([0069] The ground plane of 294 within the point cloud of Figure 2B is interpreted as an overlay region within the radar background data, where lidar sensors capture positions of vehicles, as shown by the different positions of vehicles 296D and 296A for example. Further the point cloud may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment).
Peake does not specifically teach, however Manivasagam teaches determining a second overlay region surrounding the first overlay region within the radar background data ([0124] “As illustrated in FIG. 4, in some implementations, the inputs to the model include some or all of the following: Real-valued channels: range … Integer-valued channels: laser id, semantic class (e.g., road, vehicle, background) … The input channels can represent observable factors potentially influencing each ray's chance of not returning”, where the background is interpreted as a second overlay region surrounding an overlay region of a road);
determining, based at least in part on a first probability, a first subset of the second plurality of radar data points to retain within the first overlay region ([0132] “At 502, a computing system can obtain a three-dimensional map of an environment. The three-dimensional map can be any type of map that can be used by a physics-based approach to generate an initial three-dimensional point cloud that simulates LiDAR data captured within the environment”, where for example the point cloud can include a road, where the road is interpreted as radar background data within an overlay region; [0143] “At 508, the computing system can process, using a machine-learned model, the initial three-dimensional point cloud to predict a respective dropout probability for one or more of the plurality of points”);
determining, based at least in part on a second probability, a second subset of the second plurality of radar data points to retain within the second overlay region, wherein the first probability is less than the second probability ([0124]-[0125] “As illustrated in FIG. 4, in some implementations, the inputs to the model include some or all of the following: Real-valued channels: range … Integer-valued channels: laser id, semantic class (e.g., road, vehicle, background) … The input channels can represent observable factors potentially influencing each ray's chance of not returning. The output of the model is a ray dropout probability that predicts, for each element in the array, if it returns or not (e.g., with some probability)” thus since the range effects the dropout probability of a ray, the background, which is at a larger range than the road to a lidar sensor, is interpreted as having a larger dropout probability than the road);
and determining, based at least in part on a third probability, a third subset of the second plurality of radar data points to retain outside of the second overlay region, wherein the second probability is less than the third probability ([0145]-[0146] “At 510, the computing system can generate an adjusted three-dimensional point cloud from the initial three-dimensional point cloud based at least in part on the respective dropout probabilities … For example, for each of such points, the computing system can determine a respective intensity value based at least in part on intensity data included in the three-dimensional map for locations within a radius of a respective location associated with such point in either the initial three-dimensional point cloud or the adjusted three-dimensional point cloud”, where locations outside of the determined radius is interpreted as radar background data outside of the second overlay region, which since locations outside of the radius are not included in the adjusted map, they have a higher dropout probability than the radar background data within the radius).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining a second overlay region surrounding the overlay region and determining probabilities regarding retaining radar background data within the overlay region and second overlay region, and outside of the second overlay region, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to generate simulation sensor data that more realistically simulates real-world sensor data, which further improves testing of autonomous vehicle systems, such as edge cases, thus leading to improved safety of autonomous vehicles (Manivasagam, [0029] and [0054]).
Regarding claim 11, it is the method claim, having similar limitations of claim 4. Thus, claim 11 is also rejected under the similar rationale as cited in the rejection of claim 4.
Regarding claim 12, Peake teaches the system as recited in claim 6, wherein determining the radar background data comprises: receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment ([0069] A point cloud as shown in Figure 2B may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment, thus includes log data based on sensor data captured by a vehicle operating in an environment, where the log data includes radar data representing the environment);
determining, based at least in part on the sensor data, an attribute associated with the environment ([0098] “The simulated sensor data may be associated with one or more objects or surfaces (e.g., 202-230, 292-296, 391-398, 401-418, and/or 451-482) in the virtual environment”, where as shown in Figure 2A there are attributes determined such as different object types of vehicle types and road lines);
and storing a radar background entry in a radar background data store, the radar background entry comprising the attribute and the radar data ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc”, where a tree for example is interpreted as radar background entry comprising an attribute of a semantic class and radar data of a group of points and [0190] databases store various features and other information).
Peake does not specifically teach, however Manivasagam teaches determining, based at least in part on the sensor data, that an agent is not represented within the radar data ([0125] “The output of the model is a ray dropout probability that predicts, for each element in the array, if it returns or not (e.g., with some probability)”, thus a ray predicted to not return is interpreted as determining based on sensor data, that an agent is not represented within the radar data).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining that an agent is not represented within the radar data based on sensor data, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to generate simulation sensor data that more realistically simulates real-world sensor data, which further improves testing of autonomous vehicle systems, such as edge cases, thus leading to improved safety of autonomous vehicles (Manivasagam, [0029] and [0054]).
Regarding claim 13, Peake teaches the system as recited in claim 6, wherein determining the radar background data comprises: receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment ([0069] A point cloud as shown in Figure 2B may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment, thus includes log data based on sensor data captured by a vehicle operating in an environment, where the log data includes radar data representing the environment);
determining an object represented in the log data ([0069] Figure 2B shows an object of a vehicle, such as 296A, represented in the log data);
determining a first subset of the radar data associated with the object ([0069] Figure 2B shows a point cloud generated by lidar sensors, where 296A points to a subset of radar data associated with a vehicle).
Peake does not specifically teach, however Manivasagam teaches determining the second plurality of radar data points, by removing the first subset of the radar data associated with the object from the radar data representing the environment ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where points of a non-stationary semantic class that are removed is interpreted as removing a first subset of the radar data associated with an object from the radar data representing the environment; [0094] “Statistical outlier removal can be conducted to clean the road LiDAR mesh due to spurious points from incomplete dynamic object removal”, thus further the non-stationary object removal is involved in determining a second plurality of radar data points of the road).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining a second plurality of radar data points by removing a first subset of radar data associated with the object from the radar data representing the environment, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to prevent multiple instances of the same non-stationary object from appearing in the resulting maps (Manivasagam, [0091]).
Regarding claim 16, it is the article claim, having similar limitations of claim 2. Thus, claim 16 is also rejected under the similar rationale as cited in the rejection of claim 2.
Regarding claim 17, it is the article claim, having similar limitations of claim 9. Thus, claim 17 is also rejected under the similar rationale as cited in the rejection of claim 9.
Regarding claim 18, it is the article claim, having similar limitations of claim 10. Thus, claim 18 is also rejected under the similar rationale as cited in the rejection of claim 10.
Regarding claim 19, it is the article claim, having similar limitations of claim 4. Thus, claim 19 is also rejected under the similar rationale as cited in the rejection of claim 4.
Regarding claim 20, Peake teaches the system as recited in claim 6, wherein determining the radar background data comprises: receiving log data based at least in part on sensor data captured by a vehicle operating in an environment, wherein the log data includes radar data representing the environment ([0069] A point cloud as shown in Figure 2B may be generated by lidar sensors from either a virtual vehicle in the virtual environment or real-world vehicles in a real-world environment, thus includes log data based on sensor data captured by a vehicle operating in an environment, where the log data includes radar data representing the environment);
determining, based at least in part on the log data, an object represented in the log data ([0069] Figure 2B shows an object of a vehicle, such as 296A, represented in the log data);
determining a first subset of the radar data associated with the object ([0069] Figure 2B shows a point cloud generated by lidar sensors, where 296A points to a subset of radar data associated with a vehicle);
Peake does not specifically teach, however Manivasagam teaches determining the second plurality of radar data points, by removing the first subset of the radar data associated with the object from the radar data representing the environment ([0134] “In some implementations, the computing system can remove one or more moving objects from the plurality of sets of real-world LiDAR data. In some implementations, one or more segmentation algorithms can be performed to assign a semantic class (e.g., pedestrian, street sign, tree, curb, etc.) to each point (or group of points) in each set of real-world LiDAR data. Points that have been assigned to semantic classes that are non-stationary (e.g., vehicle, bicyclist, pedestrian, etc.) can be removed from the real-world LiDAR point clouds”, where points of a non-stationary semantic class that are removed is interpreted as removing a first subset of the radar data associated with an object from the radar data representing the environment; [0094] “Statistical outlier removal can be conducted to clean the road LiDAR mesh due to spurious points from incomplete dynamic object removal”, thus further the non-stationary object removal is involved in determining a second plurality of radar data points of the road).
Therefore, it would have been obvious for one of ordinary skill in the art before the effective filing date of the claimed invention to add determining a second plurality of radar data points by removing a first subset of radar data associated with the object from the radar data representing the environment, as conceptually seen from the teaching of Manivasagam, into that of Peake. Motivation to do so would have been to prevent multiple instances of the same non-stationary object from appearing in the resulting maps (Manivasagam, [0091]).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure:
Manivasagam et al “LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World” also teaches a method of predicting dropout probabilities of LiDAR points to make autonomous vehicle simulations more realistic.
Van Fleet et al (US PGPub 20190302259) teaches a method involving generating simulation radar data using reflectivity coefficients for autonomous vehicle simulation.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW JOHN SLESINGER whose telephone number is (571)272-3302. The examiner can normally be reached Monday - Friday 8 a.m. - 5:30 p.m. 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.
/A.J.S./Examiner, Art Unit 2188
/RYAN F PITARO/Supervisory Patent Examiner, Art Unit 2188
Prosecution Insights