# US 2019/0318267 A1 · System and method for training a machine learning model deployed on a simulation platform > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318267 A1 - Document ID: US20190318267A1 - Status: Published application - Kind: A1 - Application number: 15/952,089 - Filed: 2018-04-12 - Published: 2019-10-17 - Earliest claimed: 2018-04-12 - Assignees: Baidu USA LLC - Applicants: Baidu USA LLC - Inventors: Liangliang Zhang; Siyang Yu; Dong Li; Jiangtao Hu; Jiaming Tao; Yifei Jiang - Web page: https://patentgrep.com/patent/US20190318267A1 ## CPC - G06F 30/15: Vehicle, aircraft or watercraft design - G06N 20/00: Machine learning - G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30) - G07C 5/008: {communicating information to a remotely located station (transmission systems for measured values G08C)} - G07C 5/085: {using electronic data carriers} - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE ## Abstract System and method for training a machine learning model are disclosed. In one embodiment, for each of the driving scenarios, responsive to sensor data from one or more sensors of a vehicle and the driving scenario, driving statistics and environment data of the vehicle are collected while the vehicle is driven by a human driver in accordance with the driving scenario. Upon completion of the driving scenario, the driver is requested to select a label for the completed driving scenario and the selected label is stored responsive to the driver selection. Features are extracted from the driving statistics and the environment data based on predetermined criteria. The extracted features include some of the driving statistics and some of the environment data collected at the different points in time during the driving scenario. ## Claims ### Claim 1 A computer-implemented method of training a machine learning model for evaluating autonomous driving of vehicles, the method comprising: for each of a plurality of driving scenarios, responsive to sensor data from one or more sensors of a vehicle and the driving scenario, collecting driving statistics and environment data of the vehicle while the vehicle is driven by a human driver in accordance with the driving scenario, upon completion of the driving scenario, requesting the driver to select a label for the completed driving scenario and storing the selected label responsive to the driver selection, and extracting features from the driving statistics and the environment data based on predetermined criteria, the extracted features including some of the driving statistics and some of the environment data collected at the different points in time during the driving scenario, wherein the extracted features are utilized to evaluate behaviors of autonomous driving of a plurality of autonomous driving vehicles subsequently. ### Claim 2 (depends on 1) The method of claim 1, further comprising: training a machine learning model to continuously learn driving behaviors and preferences of the human driver under the plurality of driving scenarios using the extracted features and a plurality of labels. ### Claim 3 (depends on 1) The method of claim 1, wherein some of the driving statistics includes information indicating responses of the vehicle, and some of the environment data includes obstacle information. ### Claim 4 (depends on 1) The method of claim 1, wherein the extracted features include, for each driving scenario, identifiers (IDs) that include obstacle IDs representing obstacles in the driving scenario and a vehicle ID representing the vehicle, a timestamp associated with each of the IDs, wherein the timestamp represents a time Ti, where i≥0, recorded at different points in time while the vehicle is driven through the driving scenario, information indicating responses of the vehicle captured at the recorded time Ti, and obstacle information captured at the recorded time Ti. ### Claim 5 (depends on 3) The method of claim 3, wherein the information indicating responses of the vehicle includes speed, acceleration, deceleration, and rate of change of acceleration of the vehicle, and the obstacle information includes positions of obstacles. ### Claim 6 (depends on 2) The method of claim 2, wherein each of the plurality of labels includes a label value of zero (0) or one (1), wherein 0 indicates unsafe and 1 indicates safe. ### Claim 7 (depends on 1) The method of claim 1, further comprising: subsequent to collecting driving statistics and environment data of the vehicle, storing the collected driving statistics and the environment data remotely onto a server; and prior to extracting features from the driving statistics and the environment data, retrieving the collected driving statistics and the environment data from the server. ### Claim 8 A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations, the operations comprising: for each of a plurality of driving scenarios, responsive to sensor data from one or more sensors of a vehicle and the driving scenario, collecting driving statistics and environment data of the vehicle while the vehicle is driven by a human driver in accordance with the driving scenario, upon completion of the driving scenario, requesting the driver to select a label for the completed driving scenario and storing the selected label responsive to the driver selection, and extracting features from the driving statistics and the environment data based on predetermined criteria, the extracted features including some of the driving statistics and some of the environment data collected at the different points in time during the driving scenario, wherein the extracted features are utilized to evaluate behaviors of autonomous driving of a plurality of autonomous driving vehicles subsequently. ### Claim 9 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the operations further comprise: training a machine learning model to continuously learn driving behaviors and preferences of the human driver under the plurality of driving scenarios using the extracted features and a plurality of labels. ### Claim 10 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein some of the driving statistics includes information indicating responses of the vehicle, and some of the environment data includes obstacle information. ### Claim 11 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the extracted features include, for each driving scenario, identifiers (IDs) that include obstacle IDs representing obstacles in the driving scenario and a vehicle ID representing the vehicle, a timestamp associated with each of the IDs, wherein the timestamp represents a time Ti, where i≥0, recorded at different points in time while the vehicle is driven through the driving scenario, information indicating responses of the vehicle captured at the recorded time Ti, and obstacle information captured at the recorded time Ti. ### Claim 12 (depends on 10) The non-transitory machine-readable medium of claim 10, wherein the information indicating responses of the vehicle includes speed, acceleration, deceleration, and rate of change of acceleration of the vehicle, and the obstacle information includes positions of obstacles. ### Claim 13 (depends on 9) The non-transitory machine-readable medium of claim 9, wherein each of the plurality of labels includes a label value of zero (0) or one (1), wherein 0 indicates unsafe and 1 indicates safe. ### Claim 14 (depends on 8) The non-transitory machine-readable medium of claim 8, wherein the operations further comprise: subsequent to collecting driving statistics and environment data of the vehicle, storing the collected driving statistics and the environment data remotely onto a server; and prior to extracting features from the driving statistics and the environment data, retrieving the collected driving statistics and the environment data from the server. ### Claim 15 A data processing system, comprising: a processor; and a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations, the operations including for each of a plurality of driving scenarios, responsive to sensor data from one or more sensors of a vehicle and the driving scenario, collecting driving statistics and environment data of the vehicle while the vehicle is driven by a human driver in accordance with the driving scenario, upon completion of the driving scenario, requesting the driver to select a label for the completed driving scenario and storing the selected label responsive to the driver selection, and extracting features from the driving statistics and the environment data based on predetermined criteria, the extracted features including some of the driving statistics and some of the environment data collected at the different points in time during the driving scenario, wherein the extracted features are utilized to evaluate behaviors of autonomous driving of a plurality of autonomous driving vehicles subsequently. ### Claim 16 (depends on 15) The data processing system of claim 15, wherein the operations further include training a machine learning model to continuously learn driving behaviors and preferences of the human driver under the plurality of driving scenarios using the extracted features and a plurality of labels. ### Claim 17 (depends on 15) The data processing system of claim 15, wherein some of the driving statistics includes information indicating responses of the vehicle, and some of the environment data includes obstacle information. ### Claim 18 (depends on 15) The data processing system of claim 15, wherein the extracted features include, for each driving scenario, identifiers (IDs) that include obstacle IDs representing obstacles in the driving scenario and a vehicle ID representing the vehicle, a timestamp associated with each of the IDs, wherein the timestamp represents a time Ti, where i≥0, recorded at different points in time while the vehicle is driven through the driving scenario, information indicating responses of the vehicle captured at the recorded time Ti, and obstacle information captured at the recorded time Ti. ### Claim 19 (depends on 17) The data processing system of claim 17, wherein the information indicating responses of the vehicle includes speed, acceleration, deceleration, and rate of change of acceleration of the vehicle, and the obstacle information includes positions of obstacles. ### Claim 20 (depends on 16) The data processing system of claim 16, wherein each of the plurality of labels includes a label value of zero (0) or one (1), wherein 0 indicates unsafe and 1 indicates safe. ### Claim 21 (depends on 15) The data processing system of claim 15, wherein the operations further include subsequent to collecting driving statistics and environment data of the vehicle, storing the collected driving statistics and the environment data remotely onto a server; and prior to extracting features from the driving statistics and the environment data, retrieving the collected driving statistics and the environment data from the server.