Vehicle control methods, devices, electronic equipment and storage media

By using machine learning models to predict occupant injuries before a vehicle collision and integrating active and passive safety controls, the problem of occupant injuries in unavoidable collisions by traditional systems is solved, and the effect of reducing occupant injuries before a collision is achieved.

CN117429416BActive Publication Date: 2026-06-30FAW JIEFANG AUTOMOTIVE CO
View PDF 2 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
FAW JIEFANG AUTOMOTIVE CO
Filing Date
2023-12-06
Publication Date
2026-06-30

AI Technical Summary

Technical Problem

Existing technologies are insufficient to effectively reduce the degree of collision injury to occupants in unavoidable vehicle collision scenarios. Traditional passive safety systems can only reduce injury after a collision occurs, while active safety systems cannot completely avoid collisions when the vehicle fails to detect the impact.

Method used

By acquiring vehicle status information and control inputs, machine learning models are used to predict collision information, convolutional neural networks are combined to predict occupant injuries, active safety and passive safety control methods are integrated, and the vehicle's motion state is adjusted to minimize occupant injuries.

Benefits of technology

In unavoidable collision scenarios, accurately predicting the degree of occupant injury and implementing integrated active and passive safety control can effectively reduce occupant collision damage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN117429416B_ABST
    Figure CN117429416B_ABST
Patent Text Reader

Abstract

This application relates to a vehicle control method, device, electronic device, storage medium, and computer program product. The method includes: acquiring the vehicle state information of the target vehicle at the current moment and the control input associated with the target vehicle when the target vehicle is in a target collision scenario; predicting predicted collision information when the target vehicle collides based on the vehicle state information and the control input; predicting the degree of collision injury to occupants at the time of the collision based on the predicted collision information, obtaining a collision injury prediction result; determining a safety control mode for the target vehicle based on the collision injury prediction result, wherein the safety control mode is obtained by fusing active and passive safety control modes; and adjusting the motion state of the target vehicle from the current moment to the moment of collision based on the safety control mode. This method can minimize the degree of collision injury to occupants in the event of an unavoidable collision.
Need to check novelty before this filing date? Find Prior Art