An automatic driving method and system based on scene adaptive recognition
By combining path planning and imitation learning methods, adaptive identification of scene complexity and anomalies is achieved, and appropriate decision-making methods are selected. This solves the real-time and accuracy problems of autonomous driving in complex scenarios and realizes stable and reliable autonomous driving.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
- Filing Date
- 2022-11-25
- Publication Date
- 2026-05-26
AI Technical Summary
Existing autonomous driving technologies are computationally time-consuming in complex scenarios and struggle to meet real-time requirements. Imitation learning methods are highly restrictive to various scenarios and are difficult to generalize to all driving behaviors.
By combining path planning and imitation learning methods, and by acquiring environmental information and previous operation information, the path planning trajectory and scenario complexity are determined. The uncertainty distribution of the decision is derived using neural networks, and an appropriate decision-making method is selected based on scenario complexity and anomaly.
It improves the real-time performance and accuracy of autonomous driving, enabling it to adaptively identify and select appropriate decision-making schemes in different scenarios, and to complete traffic road operations stably and reliably.
Smart Images

Figure CN115743178B_ABST