公开(公告)号：US20240353839A1

公开(公告)日：2024-10-24

申请号：US18662273

申请日：2024-05-13

Applicant: TuSimple, Inc.

Inventor： Jun CHEN ,  Wutu LIN ,  Liu LIU

IPC: G05D1/00 ,  G05D1/246 ,  G05D1/247 ,  G05D1/81 ,  G06N3/00 ,  G06N3/08

CPC classification number: G05D1/0221 ,  G05D1/246 ,  G05D1/247 ,  G05D1/81 ,  G06N3/00 ,  G06N3/08

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.

公开(公告)号：US20230161354A1

公开(公告)日：2023-05-25

申请号：US18094363

申请日：2023-01-08

Applicant: TuSimple, Inc.

Inventor： Jun CHEN ,  Wutu LIN ,  Liu LIU

IPC: G05D1/02 ,  G05D1/00 ,  G06N3/00

CPC classification number: G05D1/0221 ,  G05D1/0088 ,  G05D1/0274 ,  G05D1/0285 ,  G06N3/00

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.

公开(公告)号：US20210132620A1

公开(公告)日：2021-05-06

申请号：US17147836

申请日：2021-01-13

Applicant: TuSimple, Inc.

Inventor： Jun CHEN ,  Wutu LIN ,  Liu LIU

IPC: G05D1/02 ,  G05D1/00 ,  G06N3/00

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.