Conflict control method for shared driving, and storage medium and electronic device
AssigneeJingdong Kunpeng (Jiangsu) Technology Co., Ltd.
InventorsXin Xu, Liangliang Zhang
Life of this patent
Estimating the term…
Abstract
A conflict control method for shared driving, and an electronic device are provided. The method includes: establishing, based on a deterministic steering torque of a driver and a stochastic steering torque of the driver, a game model for human-machine path tracking control corresponding to a human-machine interaction behavior; obtaining human-machine torque conflict information by solving the game model for human-machine path tracking control; determining a shared control strategy according to the human-machine torque conflict information; and controlling a shared driving vehicle according to the shared control strategy.
Claims16
A conflict control method for shared driving, performed by a shared driving system, the method comprising:
- establishing, based on a driver's deterministic steering torque and a driver's stochastic steering torque, a game model for human-machine path tracking control corresponding to a human-machine interaction action;
- obtaining human-machine torque conflict information by solving the game model for human-machine path tracking control;
- determining a shared control strategy based on the human-machine torque conflict information;
- and
- controlling a shared driving vehicle based on the shared control strategy;
- wherein the game model for human-machine path tracking control comprises an open-loop game model, and establishing the game model for human-machine path tracking control corresponding to the human-machine interaction action, comprises:
- establishing, based on the driver's deterministic steering torque and the driver's stochastic steering torque, a first discrete state update equation for a dynamics system of the shared driving vehicle in an open-loop information mode, wherein the first discrete state update equation comprises a first stochastic steering torque related term;
- determining a prediction output vector in a prediction time domain based on the first discrete state update equation, and determining a driver reference trajectory vector and a driving system reference trajectory vector, wherein the prediction output vector comprises a prediction output term that is based on the first stochastic steering torque related term;
- and
- establishing, based on the prediction output vector, the driver reference trajectory vector, and the driving system reference trajectory vector, a first driver trajectory cost function and a first driving system trajectory cost function, to obtain the game model for human-machine path tracking control.
A non-transitory computer-readable storage medium having a computer program stored thereon, which when executed by a processor, causes a conflict control method for shared driving to be implemented, wherein the conflict control method for shared driving comprises:
- establishing, based on a driver's deterministic steering torque and a driver's stochastic steering torque, a game model for human-machine path tracking control corresponding to a human-machine interaction action;
- obtaining human-machine torque conflict information by solving the game model for human-machine path tracking control;
- determining a shared control strategy based on the human-machine torque conflict information;
- and
- controlling a shared driving vehicle based on the shared control strategy;
- wherein the game model for human-machine path tracking control comprises an open-loop game model, and establishing the game model for human-machine path tracking control corresponding to the human-machine interaction action, comprises:
- establishing, based on the driver's deterministic steering torque and the driver's stochastic steering torque, a first discrete state update equation for a dynamics system of the shared driving vehicle in an open-loop information mode, wherein the first discrete state update equation comprises a first stochastic steering torque related term;
- determining a prediction output vector in a prediction time domain based on the first discrete state update equation, and determining a driver reference trajectory vector and a driving system reference trajectory vector, wherein the prediction output vector comprises a prediction output term that is based on the first stochastic steering torque related term;
- and
- establishing, based on the prediction output vector, the driver reference trajectory vector, and the driving system reference trajectory vector, a first driver trajectory cost function and a first driving system trajectory cost function, to obtain the game model for human-machine path tracking control.
An electronic device, comprising:
- one or more processors;
- and
- a storage unit for storing one or more programs, which when executed by the one or more processors, cause the one or more processors to be configured to:
- establish, based on a driver's deterministic steering torque and a driver's stochastic steering torque, a game model for human-machine path tracking control corresponding to a human-machine interaction action;
- obtain human-machine torque conflict information by solving the game model for human-machine path tracking control;
- determine a shared control strategy based on the human-machine torque conflict information;
- and
- control a shared driving vehicle based on the shared control strategy;
- wherein the one or more processors are further configured to:
- establish, based on the driver's deterministic steering torque and the driver's stochastic steering torque, a first discrete state update equation for a dynamics system of the shared driving vehicle in an open-loop information mode, wherein the first discrete state update equation comprises a first stochastic steering torque related term;
- determine a prediction output vector in a prediction time domain based on the first discrete state update equation, and determine a driver reference trajectory vector and a driving system reference trajectory vector, wherein the prediction output vector comprises a prediction output term that is based on the first stochastic steering torque related term;
- and
- establish, based on the prediction output vector, the driver reference trajectory vector, and the driving system reference trajectory vector, a first driver trajectory cost function and a first driving system trajectory cost function, to obtain the game model for human-machine path tracking control.
Dependencies are inferred from the claim text.