CN-115384550-B - Automatic driving vehicle control method and device

CN115384550BCN 115384550 BCN115384550 BCN 115384550BCN-115384550-B

Abstract

The invention provides an automatic driving vehicle control method and device, the method comprises the steps of obtaining position constraint and rotation speed constraint from a planning module, wherein the position constraint is a transverse position boundary from a current time to a preset target time, the rotation speed constraint is a steering wheel rotation speed range from the current time to the preset target time, obtaining steering wheel rotation angle, yaw rate and slip angle in a target time window, and obtaining a control instruction according to the steering wheel rotation angle, yaw rate and slip angle in the target time window and combining the position constraint and the rotation speed constraint so as to control a vehicle according to the control instruction. According to the steering wheel turning angle, the yaw rate and the slip angle in the obtained target time window, and in combination with the position constraint and the rotation speed constraint obtained from the planning module, the embodiment of the invention obtains the control instruction, improves the accuracy of the control instruction, and ensures the requirements of safety, economy, durability, comfort and the like of the vehicle when executing the control instruction through the control instruction.

Inventors

ZHANG HANQING
ZHANG SHENGQI
WANG QIUSHI
LI WEI
ZHANG PENG

Assignees

嬴彻星创智能科技(上海)有限公司

Dates

Publication Date: 20260508
Application Date: 20220831

Claims (10)

1. An automatic driving vehicle control method, characterized by comprising: Obtaining position constraint and rotation speed constraint from a planning module, wherein the position constraint is a transverse position boundary from a current time to a preset target time, and the rotation speed constraint is a steering wheel rotation speed range from the current time to the preset target time; acquiring steering wheel rotation angle, yaw rate and side deflection angle in a target time window; obtaining a control instruction according to the steering wheel rotation angle, the yaw rate and the slip angle in the target time window and combining the position constraint and the rotation speed constraint so as to control the vehicle according to the control instruction; The preset target time instant represents a future preset time instant relative to the current time instant, and the target time window represents a historical time relative to the current time instant and conforming to the target time window length.
2. The automatic driving vehicle control method according to claim 1, wherein obtaining the control command based on the steering wheel angle, the yaw rate, and the slip angle in the target time window in combination with the position constraint and the rotation speed constraint includes: According to the steering wheel turning angle, the yaw rate and the side deflection angle in the target time window, a predicted yaw rate, a predicted course angle and a predicted transverse position are obtained; and obtaining a control instruction according to the predicted yaw rate, the predicted course angle, the predicted transverse position and a pre-constructed cost function and combining the position constraint and the rotating speed constraint.
3. The method according to claim 2, wherein the obtaining the predicted yaw rate, the predicted heading angle, and the predicted lateral position from the steering wheel angle, the yaw rate, and the slip angle within the target time window includes: obtaining a predicted yaw rate according to the steering wheel angle and the yaw rate in the target time window; Obtaining a predicted slip angle according to the steering wheel angle and the slip angle in the target time window; obtaining a predicted course angle according to the predicted yaw rate; and obtaining a predicted transverse position according to the predicted course angle and the predicted slip angle.
4. The method of controlling an autonomous vehicle according to claim 3, wherein obtaining a predicted yaw rate from the steering wheel angle and the yaw rate within the target time window comprises: inputting the steering wheel turning angle and the yaw rate in the target time window into a pre-established first impulse response model, and convolving the first impulse response model based on the steering wheel turning angle and the yaw rate in the target time window and the unit impulse response of the first impulse response model to obtain the predicted yaw rate.
5. The automatic driving vehicle control method according to claim 4, characterized by comprising, before inputting the steering wheel angle and the yaw rate within the target time window into a first impulse response model established in advance: normalizing the steering wheel angle in the target time window; After obtaining the predicted yaw rate, further comprising: And updating the first impulse response model according to the predicted yaw rate, the yaw rate in the target time window and the normalized steering wheel angle.
6. The automatic driving vehicle control method according to claim 4, characterized by further comprising, before inputting the steering wheel angle and the yaw rate within the target time window into a first impulse response model established in advance: Obtaining a corresponding steering wheel angle average value and a corresponding yaw rate average value according to the steering wheel angle and the yaw rate in the target time window; respectively reducing each steering wheel angle in the target time window according to the steering wheel angle average value; and respectively reducing each yaw rate in the target time window according to the yaw rate average value.
7. The automatic driving vehicle control method according to claim 1, characterized by further comprising, after obtaining the control instruction: Controlling a vehicle according to the control instruction, and receiving a vehicle execution state returned by the vehicle based on executing the control instruction; Obtaining a vehicle boundary according to the vehicle execution state, wherein the vehicle boundary represents a position boundary corresponding to a vehicle; and sending the vehicle boundary to the planning module.
8. An automatic driving vehicle control apparatus, characterized by comprising: the constraint acquisition module acquires position constraint and rotation speed constraint from the planning module, wherein the position constraint is a transverse position boundary from the current moment to a preset target moment, and the rotation speed constraint is a steering wheel rotation speed range from the current moment to the preset target moment; The data acquisition module acquires steering wheel rotation angle, yaw rate and slip angle in a target time window; The command generation module is used for obtaining a control command according to the steering wheel rotation angle, the yaw rate and the slip angle in the target time window and combining the position constraint and the rotation speed constraint so as to control the vehicle according to the control command; The preset target time instant represents a future preset time instant relative to the current time instant, and the target time window represents a historical time relative to the current time instant and conforming to the target time window length.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the autonomous vehicle control method according to any of claims 1 to 7 when the program is executed.
10. A non-transitory computer readable storage medium having stored thereon a computer program, characterized in that the computer program when executed by a processor implements the steps of the autonomous vehicle control method of any of claims 1 to 7.

Description

Automatic driving vehicle control method and device Technical Field The invention relates to the technical field of automatic driving, in particular to a method and a device for controlling an automatic driving vehicle. Background An automatic driving vehicle (Self-DRIVINGCAR), also known as an unmanned vehicle, a computer-driven vehicle or a wheeled mobile robot, is an intelligent vehicle which realizes unmanned through a computer system. With the popularity of autonomous vehicles, the autonomous vehicles may be used as taxis or public transportation vehicles, and passengers need to input destinations when using the autonomous vehicles, which generate a travel route based on a current location and the destination, and travel according to the generated travel route. At present, a planning module is used for generating a track line, and a planning control interface is used for transmitting the generated track curve to a control module so that the control module can track according to the track line. However, because some vehicles have more boundary conditions during control, the track line planned by the planning module may not be executed, for example, the commercial vehicle still cannot maintain the vehicle speed even if the throttle is 100% in the case of full load and ascending, and some vehicles only can ensure the safety and accuracy of control and cannot consider the evaluation criteria of other dimensions, for example, the planning module does not rule to draw a vehicle sliding speed track for the control module to track, so that the economical efficiency cannot be considered. In addition, in terms of functional safety, there are control parameters that cannot be perceived by the planning module, for example, under the limiting condition of the steering wheel rotation speed of functional safety, the feasibility of the transverse planning cannot be guaranteed. Disclosure of Invention The invention provides a control method and a control device for a motor-driven vehicle, which are used for solving the defect that a planned path line cannot be executed due to the limitation of actual conditions in the prior art, improving the feasibility of planning the path line and considering the requirements of economy and durability. The invention provides an automatic driving vehicle control method which comprises the steps of obtaining position constraint and rotation speed constraint from a planning module, wherein the position constraint is a transverse position boundary from a current time to a preset target time, the rotation speed constraint is a steering wheel rotation speed range from the current time to the preset target time, obtaining steering wheel rotation angle, yaw rate and side deflection angle in a target time window, and obtaining a control instruction according to the steering wheel rotation angle, the yaw rate and the side deflection angle in the target time window and combining the position constraint and the rotation speed constraint to control the vehicle according to the control instruction. According to the steering wheel angle, the yaw rate and the side deflection angle in the target time window and combining the position constraint and the rotating speed constraint, the automatic driving vehicle control method provided by the invention comprises the steps of obtaining a predicted yaw rate, a predicted course angle and a predicted transverse position according to the steering wheel angle, the yaw rate and the side deflection angle in the target time window, and obtaining a control instruction according to the predicted yaw rate, the predicted course angle, the predicted transverse position and a pre-constructed cost function and combining the position constraint and the rotating speed constraint. The automatic driving vehicle control method comprises the steps of obtaining a predicted yaw rate, a predicted course angle and a predicted transverse position according to a steering wheel angle, a yaw rate and a side deflection angle in a target time window, obtaining the predicted yaw rate according to the steering wheel angle and the yaw rate in the target time window, obtaining the predicted side deflection angle according to the steering wheel angle and the side deflection angle in the target time window, obtaining the predicted course angle according to the predicted yaw rate, and obtaining the predicted transverse position according to the predicted course angle and the predicted side deflection angle. According to the steering wheel turning angle and the yaw rate in the target time window, the predicted yaw rate is obtained, the steering wheel turning angle and the yaw rate in the target time window are input into a first impulse response model which is built in advance, and the first impulse response model carries out convolution based on the steering wheel turning angle, the yaw rate and unit impulse response of the first impulse response model in the target time window, so that the