Automated lane change decision making ability is significant for vehicles to adjust lanes to avoid collisions or to overtake other vehicles. However, traditional methods predicting all the possible situations using hand-crafted features is inefficient. In this paper, we propose a new lane change decision making agent based on deep reinforcement learning (DRL). In order to compare the performance differences of diverse DRL methods and state representations, our agents are trained via different DRL methods (DQN, A3C) and state representations. To demonstrate transferring ability, the agent trained in simple traffic condition is tested in more complicated conditions. Furthermore, a new way of combining DRL agents is implemented to improve agents’ ability. These experiments show that our DRL agents are capable of lane change and have a superior transferring ability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Autonomous Lane Change Decision Making Using Different Deep Reinforcement Learning Methods


    Contributors:
    Feng, Xidong (author) / Hu, Jianming (author) / Huo, Yusen (author) / Zhang, Yi (author)

    Conference:

    19th COTA International Conference of Transportation Professionals ; 2019 ; Nanjing, China


    Published in:

    CICTP 2019 ; 5563-5575


    Publication date :

    2019-07-02




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning

    Hoel, Carl-Johan / Wolff, Krister / Laine, Leo | IEEE | 2018





    REINFORCEMENT LEARNING FOR AUTONOMOUS LANE CHANGE

    SHI ZHAN / JIANG YIFEI / LI ANG | European Patent Office | 2024

    Free access