# US 11,029,693 B2 · Neural network based vehicle dynamics model > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,029,693 B2 - Document ID: US11029693B2 - Status: Granted - Kind: B2 - Application number: 15/672,207 - Filed: 2017-08-08 - Published: 2019-02-14 - Granted: 2021-06-08 - Earliest claimed: 2017-08-08 - Assignees: Tusimple, Inc. - Applicants: TuSimple, Inc. - Inventors: Jun Chen; Wutu Lin; Liu Liu - Web page: https://patentgrep.com/patent/US11029693B2 ## CPC - G06N 3/08: Learning methods - G05D 1/00: Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots (drive control systems specially adapted for autonomous road vehicles B60W60/00) - G05D 1/0274: {using mapping information stored in a memory device (navigation using map-matching G01C21/30)} - G05D 1/0285: {using signals transmitted via a public communication network, e.g. GSM network} - G05D 1/246: using environment maps, e.g. simultaneous localisation and mapping [SLAM] - G05D 1/247: using signals provided by artificial sources external to the vehicle, e.g. navigation beacons - G05D 1/81: Handing over between on-board automatic and on-board manual control - G06N 3/00: Computing arrangements based on biological models - G06N 3/0499: Feedforward networks - G06N 3/09: Supervised learning - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS - G05D: SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES ## Abstract A system and method for implementing a neural network based vehicle dynamics model are disclosed. A particular embodiment includes: training a machine learning system with a training dataset corresponding to a desired autonomous vehicle simulation environment; receiving vehicle control command data and vehicle status data, the vehicle control command data not including vehicle component types or characteristics of a specific vehicle; by use of the trained machine learning system, the vehicle control command data, and vehicle status data, generating simulated vehicle dynamics data including predicted vehicle acceleration data; providing the simulated vehicle dynamics data to an autonomous vehicle simulation system implementing the autonomous vehicle simulation environment; and using data produced by the autonomous vehicle simulation system to modify the vehicle status data for a subsequent iteration. ## Claims ### Claim 1 A system comprising: a data processor; and a memory storing a vehicle dynamics modeling module, executable by the data processor to: train a machine learning system with a training dataset corresponding to a desired autonomous vehicle simulation environment; receive vehicle control command data and vehicle status data; by use of the trained machine learning system, generate predicted vehicle acceleration data based on the vehicle control command data and the vehicle status data; generate simulated vehicle dynamics data comprising the predicted vehicle acceleration data; provide the simulated vehicle dynamics data to an autonomous vehicle simulation system implementing the autonomous vehicle simulation environment; and conduct an iteration process periodically, wherein the iteration process comprises: receiving the vehicle status data modified by data produced by the autonomous vehicle simulation system; and by use of the trained machine learning system, generating modified simulated vehicle dynamics data based on the vehicle control command data and the modified vehicle status data. ### Claim 2 (depends on 1) The system of claim 1 wherein the machine learning system is a neural network. ### Claim 3 (depends on 1) The system of claim 1 wherein the vehicle control command data comprises throttle, brake, and steering control information corresponding to specific simulated autonomous vehicles. ### Claim 4 (depends on 1) The system of claim 1 wherein the vehicle status data comprises speed and pitch information corresponding to specific simulated autonomous vehicles. ### Claim 5 (depends on 1) The system of claim 1 wherein the training dataset corresponds to recorded historical vehicle driving data captured from real world vehicle operations or simulated vehicle movements. ### Claim 6 (depends on 1) The system of claim 1 wherein the vehicle dynamics modeling operation is further configured for use with any type of simulated vehicle by changing the training dataset accordingly. ### Claim 7 (depends on 1) The system of claim 1 wherein the vehicle dynamics modeling operation is further configured to use the simulated vehicle dynamics data to generate validation data to validate the training dataset. ### Claim 8 (depends on 1) The system of claim 1 wherein the vehicle dynamics modeling operation is further configured to generate validation data to validate an accuracy of the training dataset. ### Claim 9 (depends on 1) The system of claim 1 wherein the simulated vehicle dynamics data further comprises predicted vehicle torque data generated by use of the trained machine learning system based on the vehicle control command data and the vehicle status data, wherein the vehicle control command data does not comprise steering control data. ### Claim 10 A method comprising: training a machine learning system with a training dataset corresponding to a desired autonomous vehicle simulation environment; receiving vehicle control command data and vehicle status data; by use of the trained machine learning system, generating predicted vehicle acceleration data based on the vehicle control command data and the vehicle status data, wherein simulated vehicle dynamics data comprises the predicted vehicle acceleration data; providing the simulated vehicle dynamics data to an autonomous vehicle simulation system implementing the autonomous vehicle simulation environment; and conducting an iteration process periodically, wherein the iteration process comprises: receiving the vehicle status data modified by data produced by the autonomous vehicle simulation system; and by use of the trained machine learning system, generating modified simulated vehicle dynamics data based on the vehicle control command data and the modified vehicle status data. ### Claim 11 (depends on 10) The method of claim 10 wherein the machine learning system comprises artificial neural networks or connectionist systems. ### Claim 12 (depends on 10) The method of claim 10 wherein the vehicle control command data and the vehicle status data are inputted for each time step. ### Claim 13 (depends on 10) The method of claim 10 wherein the iteration process is conducted periodically at a pre-determined rate. ### Claim 14 (depends on 10) The method of claim 10 wherein the iteration process is conducted periodically within a pre-determined rate. ### Claim 15 (depends on 10) The method of claim 10 wherein the vehicle control command data does not comprise vehicle component types or characteristics of a specific vehicle. ### Claim 16 (depends on 15) The method of claim 15 wherein the vehicle component types comprise at least one of engine type and transmission type. ### Claim 17 (depends on 10) The method of claim 10 wherein the simulated vehicle dynamics data further comprises predicted vehicle torque data generated by use of the trained machine learning system based on the vehicle control command data and the vehicle status data, wherein the vehicle control command data does not comprise steering control data, wherein the vehicle status data does not comprise pitch information. ### Claim 18 (depends on 10) The method of claim 10 wherein the simulated vehicle dynamics data further comprises predicted vehicle torque data generated by use of the trained machine learning system based on the vehicle control command data and the vehicle status data, wherein vehicle speed data is generated based on the predicted vehicle torque data. ### Claim 19 A non-transitory machine-useable storage medium embodying instructions which, when executed by a machine, cause the machine to: train a machine learning system with a training dataset corresponding to a desired autonomous vehicle simulation environment; receive vehicle control command data and vehicle status data; by use of the trained machine learning system, generate predicted vehicle acceleration data based on the vehicle control command data and the vehicle status data, wherein simulated vehicle dynamics data comprises the predicted vehicle acceleration data; provide the simulated vehicle dynamics data to an autonomous vehicle simulation system implementing the autonomous vehicle simulation environment; and conduct an iteration process periodically, wherein the iteration process comprises: receiving the vehicle status data modified by data produced by the autonomous vehicle simulation system; and by use of the trained machine learning system, generating modified simulated vehicle dynamics data based on the vehicle control command data and the modified vehicle status data. ### Claim 20 (depends on 19) The non-transitory machine-useable storage medium of claim 19 wherein the iteration process is conducted repeatedly at regular intervals of time.