重庆理工大学学报2026，Vol.40Issue(1)：54-61,8.DOI:10.3969/j.issn.1674-8425(z).2026.01.007
基于安全强化学习的交叉口多车协同决策方法
Multi-vehicle cooperative decision-making method with safe reinforcement learning at urban intersections
摘要
Abstract
At urban intersections with multiple vehicles in motion,effectively characterizing the dynamic interactions between autonomous vehicles,optimizing right-of-way sequences,and ensuring driving safety remain significantly challenging.This paper proposes a collaborative control method based on safe multi-agent reinforcement learning to mitigate unsafe behaviors caused by the lack of safety constraints.First,the constrained Markov game(CMG)is integrated with multi-agent reinforcement learning.The Lagrange multiplier method and multi-agent Deep Deterministic Policy Gradient algorithm are employed to maximize the reward while minimizing the safety costs to limit dangerous behaviors.Next,a safety-awareness experience replay mechanism is proposed to mitigate the adaptability degradation and the potential for suboptimal solutions caused by over-restricting individual agents decision-making.Simulation results demonstrate the proposed algorithm outperforms existing baseline methods in safety,achieving a collision rate of 8.6%,effectively improving the collaborative decision-making capabilities of self-driving vehicles.关键词
多智能体强化学习/安全强化学习/协同通行策略/自动驾驶Key words
multi-agent reinforcement learning/safe reinforcement learning/cooperative driving strategy/autonomous driving分类
信息技术与安全科学引用本文复制引用
黄亚飞,石晴,田浩,张云龙,胡伟..基于安全强化学习的交叉口多车协同决策方法[J].重庆理工大学学报,2026,40(1):54-61,8.基金项目
贵州省科技厅自然科学项目(黔科合基础-ZK[2023]一般056) （黔科合基础-ZK[2023]一般056）
贵州大学高层次人才科研项目(贵大人基合字[2021]56号) （贵大人基合字[2021]56号）
贵州大学科研平台支持项目(2021013477 （）
2023000900 （）
2023000885) （）
贵州省智能网联汽车创新人才团队项目(CXTD2022-009) （CXTD2022-009）
