计算机应用研究2024，Vol.41Issue(1)：183-187,5.DOI:10.19734/j.issn.1001-3695.2023.05.0220
基于区间分块Q学习的智能车辆安全舒适刹车算法
Interval-block-based Q-learning algorithm for safe and comfortable braking of intelligent vehicles
摘要
Abstract
To address the safety and comfort issues in intelligent vehicle braking scenarios,this paper proposed a Q-learning algorithm based on interval partitioning.Firstly,the algorithm divided the acceleration of the preceding vehicle into equal-length intervals with a certain interval in the Q-table,and used the interval median to partition the acceleration of the following vehi-cle.Secondly,the algorithm used a reward function that was negatively correlated with acceleration under safe conditions to en-courage the agent to minimize braking acceleration while ensuring safety.Finally,the algorithm followed the ε-greedy strategy during the training of the agent to reduce randomness,and followed the greedy strategy after training to maximize the utilization of the agent.This paper simulated the proposed algorithm and the traditional Q-learning algorithm on three common road sce-narios.The experimental results show that the intelligent vehicle used the proposed algorithm has a 100％safety rate in braking scenarios,with an average braking acceleration of less than 2 m/s2,and can handle continuous braking acceleration,which in-dicates that the proposed algorithm can achieve lower braking deceleration to improve passengers'comfort while ensuring safe braking of the intelligent vehicles.In addition,the algorithm is effective in complex scenarios including continuous braking de-celeration and offline environments.关键词
智能汽车/智能刹车/Q学习/区间分块Key words
intelligent vehicle/intelligent braking/Q-learning/interval block分类
信息技术与安全科学引用本文复制引用
余欣磊,周贤文,张依恋,顾伟..基于区间分块Q学习的智能车辆安全舒适刹车算法[J].计算机应用研究,2024,41(1):183-187,5.基金项目
国家自然科学基金面上项目(62176150) （62176150）
上海市地方院校能力建设项目(20040501400) （20040501400）
