汽车工程 ›› 2021, Vol. 43 ›› Issue (4): 571-579.doi: 10.19562/j.chinasae.qcgc.2021.04.015

• • 上一篇    下一篇

基于深度强化学习的驾驶员跟车模型研究

郭景华1(),李文昌1,4,罗禹贡2,陈涛3,李克强2   

  1. 1.厦门大学机电工程系,厦门 361005
    2.清华大学车辆与运载学院,北京 100084
    3.中国汽车工程研究院股份有限公司,重庆 401122
    4.同济大学汽车学院,上海 201804
  • 收稿日期:2020-10-14 出版日期:2021-04-25 发布日期:2021-04-23
  • 通讯作者: 郭景华 E-mail:guojh@xmu.edu.cn
  • 基金资助:
    国家重点研发计划(2016YFB0100900);汽车安全与节能国家重点实验室开放基金课题(KF2011)

Driver Car⁃Following Model Based on Deep Reinforcement Learning

Jinghua Guo1(),Wenchang Li1,4,Yugong Luo2,Tao Chen3,Keqiang Li2   

  1. 1.School of Aerospace Engineering,Xiamen University,Xiamen 361005
    2.School of Vehicle and Mobility,Tsinghua University,Beijing 100084
    3.China Automotive Engineering Research Institute Co. ,Ltd. ,Chongqing 401122
    4.School of Automotive Studies,Tongji University,Shanghai 201804
  • Received:2020-10-14 Online:2021-04-25 Published:2021-04-23
  • Contact: Jinghua Guo E-mail:guojh@xmu.edu.cn

摘要:

为提升智能驾驶系统的纵向跟车性能,本文构建了一种基于深度强化学习的驾驶员跟车模型。首先,设计了跟车场景截取准则并从自然驾驶数据中筛选出符合条件的典型跟车场景,并对其数据进行统计分析,即采用相关系数法分析了车间距、相对速度和车头时距等因素对驾驶员跟车行为的影响机理,得出驾驶员跟车行驶过程的行为特性及其影响因素。接着,基于深度确定性策略梯度算法建立了驾驶员跟车模型,将驾驶员跟车轨迹数据集输入到模拟跟车环境中,让智能体从经验数据中学习驾驶员的决策行为。最后,以原始工况数据为基准,对基于深度强化学习的跟车模型进行对比仿真验证,结果表明所构建的驾驶员跟车模型具有良好的跟踪性能,能真实地复现驾驶员的跟车行为。

关键词: 智能驾驶, 驾驶员模型, 跟车, 深度强化学习

Abstract:

To enhance the longitudinal car?following performance of intelligent driving system, a driver's car?following model based on deep reinforcement learning is constructed in this paper. Firstly, according to the selection rule defined of car following scenes, typical car?following scenes conforming to conditions are selected from the natural driving data, on which a statistical analysis is then conducted to analyze the influence mechanism of the factors of car spacing, relative speed and time headway on the car following behavior of driver by using correlation coefficient method, with the behavior characteristic and its affecting factors of driver's car following driving process obtained. Then a car following model of driver is established based on the deep deterministic policy gradient algorithm, and the driver's data set of car following trajectory is input into the simulated car following environment so that the intelligent agent can learn the decision?making behavior of driver from the empirical data. Finally, with the original data as the reference base, a comparative simulation verification is performed on the deep reinforcement learning?based car following model, with a result showing that the driver's car following model constructed has good tracking performance and can truly reproducing the car following behavior of driver.

Key words: intelligent driving, driver model, car following, deep reinforcement learning