Intelligent automobile lane-changing decision method and device, electronic equipment and storage medium

By constructing a decision-making model based on a single-step deep Q-neural network, generating virtual lane-changing scenarios using simulation methods, and training it using a greedy algorithm and an experience replay pool, the adaptability and safety issues of intelligent vehicle lane-changing decisions in complex traffic environments are solved, achieving efficient and safe lane-changing decisions.

CN115782880BActive Publication Date: 2026-04-21TSINGHUA UNIVERSITY
2 Cites 0 Cited by

Patent Information

Application Number
CN202211508728.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2022-11-29
Publication Date
2026-04-21
Estimated Expiration
2042-11-29

AI Technical Summary

Technical Problem

In existing technologies, intelligent vehicle lane-changing decision-making methods lack adaptability and safety in complex traffic environments, and have high training costs and difficult-to-interpret parameter tuning. Existing deep reinforcement learning methods also have poor generalization ability in lane-changing decisions.

Method used

By constructing a decision model based on a single-step deep Q-neural network, a virtual lane-changing scenario is generated using simulation methods. The model is then trained using a greedy algorithm and an experience replay pool to generate a lane-changing decision model for intelligent vehicles that can adapt to different traffic flow conditions and be applied in real-world scenarios.

Benefits of technology

It improves training efficiency and adaptability, reduces development costs, ensures the safety and robustness of lane-changing decisions, simplifies the neural network structure, and facilitates deployment in MCUs.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The intelligent automobile lane-changing decision method and device, the electronic device and the storage medium provided by the embodiments of the present disclosure comprise: constructing a virtual lane-changing scene by using a simulation method; constructing a decision model for determining a mapping function between a state and a reward, obtaining a Q table for evaluating the lane-changing feasibility of an intelligent automobile based on the mapping function, and obtaining a lane-changing decision, i.e., "lane-changing" or "not lane-changing"; based on a greedy algorithm, making the intelligent automobile produce a random lane-changing behavior in the constructed virtual lane-changing scene, storing the state and the reward of the current lane-changing behavior in an experience replay pool, when the number of state-reward pairs in the experience replay pool reaches a minimum sample number, randomly sampling a plurality of state-reward pairs from the experience replay pool for single-step training of the decision model, storing a new state-reward pair generated in the training process in the experience replay pool, repeatedly performing the above training process until a maximum training number is reached, and obtaining a lane-changing decision model. The lane-changing decision generated by the present disclosure is high in safety and wide in applicability.
Need to check novelty before this filing date? Find Prior Art