An object importance determination method and device based on reachability analysis
By generating a reachability set relation table in the offline phase and using Monte Carlo simulation, autonomous vehicles can directly determine whether an obstacle is within the reachable area in the online phase. This solves the problems of incomplete judgment and long development cycle caused by relying on expert experience, and achieves efficient and accurate obstacle importance determination.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN DEEPROUTE AI CO LTD
- Filing Date
- 2023-01-06
- Publication Date
- 2026-06-12
AI Technical Summary
In existing technologies, autonomous vehicles rely on expert experience to determine the importance of obstacles, resulting in incomplete judgments, long development cycles, and difficulty in scaling.
By pre-generating a reachability set relation table, important objects are defined in the offline stage using Monte Carlo simulation, and in the online stage, it is directly determined whether obstacles are within the reachable area. This adopts an object importance determination method and device based on reachability analysis.
It improves the completeness and scalability of obstacle importance determination, shortens the development cycle, facilitates debugging and reduces edge cases, and ensures the safe operation of the autonomous driving system.
Smart Images

Figure CN116052118B_ABST