Assisted driving optimization method based on expected functional safety risk assessment

CN121734377BActive Publication Date: 2026-06-19ZHEJIANG GEELY HLDG GRP CO LTD +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202610244497.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2026-03-02
Publication Date
2026-06-19
Estimated Expiration
2046-03-02

AI Technical Summary

Technical Problem

In existing technologies, driver assistance systems cannot accurately reconstruct the location of obstacles and the timing of their appearance in special scenarios, resulting in low accuracy and confidence of SOTIF (Expected Functional Safety) assessments, and a lack of specific technical solutions for optimization.

Method used

By predefining risk triggering conditions for critical risk scenarios in the vehicle, the system detects and uploads driving data of critical scenarios to the optimization server in real time, calculates the first effective perception target state of obstacles, and updates the parameters of the assisted driving system when it is impossible to avoid obstacles effectively, thereby achieving closed-loop SOTIF risk assessment and optimization.

Benefits of technology

It improves the ability of the driver assistance system to cope with critical scenarios, enhances the accuracy of SOTIF risk assessment and the certainty of system capability boundaries, and achieves effective optimization for critical scenarios.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121734377B_ABST
    Figure CN121734377B_ABST
Patent Text Reader

Abstract

This invention provides a method for optimizing assisted driving based on expected functional safety risk assessment. The method is applied to an optimization server in an assisted driving optimization system, which also includes at least one vehicle deployed with the assisted driving system. The method includes: receiving critical scenario driving data uploaded by any vehicle when it detects that its actual driving scenario meets risk triggering conditions; the optimization server calculating the first effective perception target state between the assisted driving system and the obstacle when it first perceives the obstacle based on the critical scenario driving data, and reconstructing the vehicle's obstacle avoidance information; if the first effective perception target state does not exceed the safety critical target state corresponding to any critical risk scenario and the avoidance information indicates that the vehicle failed to effectively avoid the obstacle, determining a second parameter for updating the first parameter based on the first effective perception target state.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Method for evaluating acceptance level of perception delay error of automatic driving system

    CN120295369A

  • Vehicle expected function safety data driven closed-loop solving method, system and equipment and storage medium

    CN120806628A