Search

CN-121989930-A - Vehicle control method and related equipment

CN121989930ACN 121989930 ACN121989930 ACN 121989930ACN-121989930-A

Abstract

The application provides a vehicle control method and related equipment, wherein the vehicle control method comprises the steps of determining each action to be determined of a vehicle according to a target detected by the vehicle, determining an expected risk value of each action to be determined of the vehicle under the condition that the target is a known object, determining a target risk value of each action to be determined of the vehicle under the condition that the target is an unknown object according to the expected risk value, and executing the action to be determined corresponding to the minimum target risk value under the condition that the minimum target risk value is smaller than a safety threshold. According to the application, the running safety of the vehicle is improved.

Inventors

  • ZHANG ZHANHUA
  • HU GUANZHONG
  • XU BO
  • CHEN YONG

Assignees

  • 浙江吉利控股集团有限公司
  • 吉利汽车研究院（宁波）有限公司

Dates

Publication Date
20260508
Application Date
20260330

Claims (10)

  1. 1.A vehicle control method characterized by comprising: determining each action to be determined to be executed by the vehicle according to the target detected by the vehicle; determining an expected risk value of each action to be determined by the vehicle under the condition that the target is a known object; determining a target risk value of each action to be determined under the condition that the target is an unknown object according to the expected risk value; And executing the action to be determined corresponding to the minimum target risk value under the condition that the minimum target risk value is smaller than the safety threshold value.
  2. 2. The vehicle control method according to claim 1, characterized in that the determining the target risk value of the vehicle for each of the actions to be determined in the case where the target is an unknown object according to the desired risk value includes: acquiring a first probability value and a first generation value of the target as an unknown object, wherein the first generation value is used for indicating the degree of damage when a vehicle determines the unknown object as the target; and correcting the expected risk value corresponding to the action to be determined according to the first probability value and the first generation value corresponding to the action to be determined, so as to obtain a target risk value.
  3. 3. The vehicle control method according to claim 1, characterized in that the determining the expected risk value of the vehicle to perform each of the actions to be determined in the case where the target is a known object includes: determining a second probability value for the target being a different known object; determining a cost value generated by the fact that the target is misjudged as a different other object by the known object as a second cost value; determining a second probability value and a second cost value corresponding to the action to be determined in each second probability value and each second cost value; And determining the expected risk value of the action to be determined according to the second probability value corresponding to the action to be determined and the second cost value.
  4. 4. A vehicle control method according to claim 3, wherein said determining a cost value generated by a misjudgment of the target by a known object as a different other object comprises: Determining a current driving scene of the vehicle; Inquiring the cost value generated by misjudging the target as a different other object by the known object according to the current driving scene.
  5. 5. The vehicle control method according to claim 3, characterized in that the determining of the second probability value that the target is a different known object includes: inputting sensor data acquired by a sensor of the vehicle into a detection model; and determining a second probability value of the target as a different known object according to the output result of the detection model.
  6. 6. The vehicle control method according to claim 1, characterized in that the determining each of the actions to be determined to be performed by the vehicle according to the object detected by the vehicle includes: And according to actions to be executed when the vehicle misjudges the target as different other objects from the known object, the actions are used as various actions to be determined.
  7. 7. The vehicle control method according to claim 1, characterized in that after the determining that the vehicle performs the target risk value corresponding to each of the actions to be determined, further comprises: And controlling the vehicle to avoid the target under the condition that the minimum target risk value is greater than or equal to a safety threshold value.
  8. 8. A vehicle comprising a memory and a processor, wherein, The memory is connected with the processor and used for storing programs; the processor is configured to implement the vehicle control method according to any one of claims 1 to 7 by running a program in the memory.
  9. 9.A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the vehicle control method according to any one of claims 1 to 7.
  10. 10. A computer program product, characterized in that the computer program, when being executed by a processor, implements the vehicle control method according to any one of claims 1-7.

Description

Vehicle control method and related equipment Technical Field The application relates to the technical field of vehicles, in particular to a vehicle control method and related equipment. Background During the running of the vehicle, the vehicle needs to perform target detection. In an exemplary technique, after a vehicle detects a target, an action to be performed by the vehicle is determined based on the type of the target, for example, the vehicle detects that the target is a pedestrian, and the vehicle needs to be stopped or slowed down. However, if the vehicle misjudges the target, an immeasurable result is generated after the vehicle performs the motion, for example, the vehicle judges the detected target as a dynamic obstacle with slow moving speed, the vehicle performs the motion of slowing down slowly, and the target is actually a static obstacle, and the vehicle collides with the target due to slow speed of slowing down, so that a safety accident is generated on the vehicle, and the running safety of the vehicle is low. Disclosure of Invention Based on the above state of the art, the present application provides a vehicle control method and related apparatus for solving the problem of low driving safety of a vehicle. In order to achieve the technical purpose, the application specifically provides the following technical scheme: In a first aspect, the present application provides a vehicle control method including: determining each action to be determined to be executed by the vehicle according to the target detected by the vehicle; determining an expected risk value of each action to be determined by the vehicle under the condition that the target is a known object; determining a target risk value of each action to be determined under the condition that the target is an unknown object according to the expected risk value; And executing the action to be determined corresponding to the minimum target risk value under the condition that the minimum target risk value is smaller than the safety threshold value. In some embodiments, the determining, according to the expected risk value, the target risk value of each of the actions to be determined, where the target is an unknown object, includes: acquiring a first probability value and a first generation value of the target as an unknown object, wherein the first generation value is used for indicating the degree of damage when a vehicle determines the unknown object as the target; and correcting the expected risk value corresponding to the action to be determined according to the first probability value and the first generation value corresponding to the action to be determined, so as to obtain a target risk value. In some embodiments, the determining the expected risk value of the vehicle to perform each of the actions to be determined if the target is a known object includes: determining a second probability value for the target being a different known object; determining a cost value generated by the fact that the target is misjudged as a different other object by the known object as a second cost value; determining a second probability value and a second cost value corresponding to the action to be determined in each second probability value and each second cost value; And determining the expected risk value of the action to be determined according to the second probability value corresponding to the action to be determined and the second cost value. In some embodiments, the determining the cost value for the target generated by the known object misjudging as a different other object includes: Determining a current driving scene of the vehicle; Inquiring the cost value generated by misjudging the target as a different other object by the known object according to the current driving scene. In some implementations, the determining the second probability value for the target being a different known object includes: inputting sensor data acquired by a sensor of the vehicle into a detection model; and determining a second probability value of the target as a different known object according to the output result of the detection model. In some embodiments, the determining each action to be determined to be performed by the vehicle according to the target detected by the vehicle includes: And according to actions to be executed when the vehicle misjudges the target as different other objects from the known object, the actions are used as various actions to be determined. In some embodiments, after the determining the target risk value corresponding to each action to be determined is performed by the vehicle, the method further includes: And controlling the vehicle to avoid the target under the condition that the minimum target risk value is greater than or equal to a safety threshold value. In a second aspect, the present application provides a vehicle comprising a memory and a processor, wherein, The memory is connected with the processor and used for sto