In this paper, we study how to learn a harmonious deep reinforcement learning (DRL) based lane-changing strategy for autonomous vehicles without Vehicle-to-Everything (V2X) communication support. The basic framework of this paper can be viewed as a multi-agent reinforcement learning in which different agents will exchange their strategies after each round of learning to reach a zero-sum game state. Unlike cooperation driving, harmonious driving only relies on individual vehicles’ limited sensing results to balance overall and individual efficiency. Specifically, we propose a well-designed reward that combines individual efficiency with overall efficiency for harmony, instead of only emphasizing individual interests like competitive strategy. Testing results show that competitive strategy often leads to selfish lane change behaviors, anarchy of crowd, and thus the degeneration of traffic efficiency. In contrast, the proposed harmonious strategy can promote traffic efficiency in both free flow and traffic jam than the competitive strategy. This interesting finding indicates that we should take care of the reward setting for reinforcement learning-based AI robots (e.g., automated vehicles) design, when the utilities of these robots are not strictly in alignment.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Harmonious Lane Changing via Deep Reinforcement Learning


    Beteiligte:
    Wang, Guan (Autor:in) / Hu, Jianming (Autor:in) / Li, Zhiheng (Autor:in) / Li, Li (Autor:in)


    Erscheinungsdatum :

    2022-05-01


    Format / Umfang :

    3742850 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Reinforcement Learning Approach for Automated Vehicle Mandatory Lane Changing

    Ammourah, Rami / Talebpour, Alireza | Transportation Research Record | 2022


    Automatic driving vehicle lane changing method based on double-layer deep reinforcement learning

    PENG JIANKUN / SHEN YANG / ZHANG SIYU et al. | Europäisches Patentamt | 2023

    Freier Zugriff


    Automatic driving vehicle lane changing decision system and method based on deep reinforcement learning

    XIONG MINGQIANG / QIAO JIE / JIANG MENG et al. | Europäisches Patentamt | 2022

    Freier Zugriff

    Bottleneck area lane changing control method and device based on deep reinforcement learning and medium

    DUAN YAOXIN / ZHANG HUI / NIE WENDI et al. | Europäisches Patentamt | 2023

    Freier Zugriff