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.

CN115743178BActive Publication Date: 2026-05-26SHENZHEN INST OF ADVANCED TECH CHINESE ACAD OF SCI
View PDF 3 Cites 0 Cited by

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

Technical Problem

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.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN115743178B_ABST
    Figure CN115743178B_ABST
Patent Text Reader

Abstract

This application provides an autonomous driving method and system based on scene adaptive recognition. The method includes: acquiring environmental information and previous operation information in the driving scene; a path planning module determining a path planning trajectory in the current driving scene based on the previous operation information; determining the scene complexity based on the parameter space of the path planning trajectory; an imitation learning module deriving the uncertainty distribution of the decision from a neural network based on the environmental information; determining the scene anomaly degree based on the uncertainty distribution; and a decision module determining the autonomous driving method based on the scene complexity and scene anomaly degree. This solution improves the real-time performance and accuracy of autonomous driving.
Need to check novelty before this filing date? Find Prior Art