汽车工程 ›› 2022, Vol. 44 ›› Issue (9): 1350-1358.doi: 10.19562/j.chinasae.qcgc.2022.09.006

所属专题: 智能网联汽车技术专题-规划&控制2022年

• • 上一篇    下一篇

基于Q学习模型的无信号交叉口离散车队控制

钱立军1,2(),陈晨1,陈健1,陈欣宇1,熊驰1   

  1. 1.合肥工业大学汽车与交通工程学院,合肥  230009
    2.南昌理工学院机电工程学院,南昌  330044
  • 收稿日期:2022-03-22 修回日期:2022-04-25 出版日期:2022-09-25 发布日期:2022-09-21
  • 通讯作者: 钱立军 E-mail:qianlijun66@163.com
  • 基金资助:
    国家自然科学基金面上项目(51875149)

Discrete Platoon Control at an Unsignalized Intersection Based on Q-learning Model

Lijun Qian1,2(),Chen Chen1,Jian Chen1,Xinyu Chen1,Chi Xiong1   

  1. 1.Department of Automotive and Traffic Engineering,Hefei University of Technology,Hefei  230009
    2.College of Electrical and Mechanical Engineering,Nanchang Institute of Technology,Nanchang  330044
  • Received:2022-03-22 Revised:2022-04-25 Online:2022-09-25 Published:2022-09-21
  • Contact: Lijun Qian E-mail:qianlijun66@163.com

摘要:

针对智能网联汽车在交通瓶颈处的行车效率问题,提出了一种面向无信号灯交叉口的车队协同控制策略。首先,根据基于车队的交通流模型和车队在交叉口的占用时间,提出了一个车队路权分配的控制框架。其次,以瞬时效率、行车延误等为复合指标,设计了一个Q学习模型来有条件地挑选车队规模。最后,依据跟车模型对分组后的车辆进行在线轨迹规划仿真。结果表明,Q学习模型可针对不同工况灵活地分配组队指令,并保证车队运动过程中的全局安全性。与非组队方法对比,所提方法可将交叉口的通行能力提升约36.1%。

关键词: 智能网联汽车, 无信号灯交叉口, 多车队协同, Q学习模型, 轨迹规划

Abstract:

In order to enhance the driving efficiency of connected and automated vehicles (CAVs) at traffic bottlenecks, a platoon cooperative control strategy at an unsignalized intersection is proposed. Firstly, a control framework for the allocation of the right of way for platoons is put forward based on the traffic flow model and occupied time of platoons at the intersection. Then, a Q-learning model is designed to conditionally select platoon sizes, with instantaneous efficiency and travel delays as compound indicators. Finally, an online trajectory planning simulation is carried out for the grouped vehicles based on vehicle following model. The results show that the Q-learning model can flexibly allocate the platooning commands according to different working conditions and ensure the overall safety of platoons during driving process. Compared with the nonplatoon scheme, the traffic capacity of the intersection is increased by around 36.1%.

Key words: connected and automated vehicles, unsignalized intersection, multi-platoon cooperation, Q-learning model, trajectory planning