The control of connected autonomous vehicles (CAVs) for cooperative sensing and driving in mixed traffic flows is critical for the development of intelligent transportation systems. However, the challenge lies in effectively representing and learning from the interactions between heterogeneous traffic agents, as well as the complex traffic states they produce. To address this, we propose the Multi-View Graph Convolution Network Reinforcement Learning (MVGRL) algorithm for the decision-making and control of CAVs in mixed traffic scenarios. First, multi-view graphs are constructed based on multiple logical correlations and the perception-communication relationship of heterogeneous vehicles in mixed traffic. This enables us to represent the dynamic vehicle networks and gain insights into vehicle behavior. Then, the features of multi-view vehicle network graphs are derived by multi-view graph convolutional network reinforcement learning. Finally, the lane change decisions of CAVs are obtained based on complex traffic state learning. In the highway scenario, the model is able to control the CAVs to complete the ramp exit task and maintain an overall efficient traffic flow. Various test scenarios were formed by adjusting the traffic conditions under a highway off-ramp scenario for comparison experiments. The results show that the proposed MVGRL algorithm model outperforms in decision-making and robustness than the baseline models.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Multi-View Graph Convolution Network Reinforcement Learning for CAVs Cooperative Control in Highway Mixed Traffic


    Beteiligte:
    Xu, Dongwei (Autor:in) / Liu, Peiwen (Autor:in) / Li, Haijian (Autor:in) / Guo, Haifeng (Autor:in) / Xie, Zijia (Autor:in) / Xuan, Qi (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    2024-01-01


    Format / Umfang :

    2194920 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Simulated CAVs Driving and Characteristics of the Mixed Traffic Using Reinforcement Learning Method

    Guo, Jingqiu / Liu, Yangzexi / Fang, Shouen | Springer Verlag | 2019


    Cooperative Incident Management in Mixed Traffic of CAVs and Human-Driven Vehicles

    Yue, Wenwei / Li, Changle / Wang, Shangbo et al. | IEEE | 2023


    Deep Double Q-Learning Method for CAVs Traffic Signal Control

    Zhao, Chunxia / Lin, Peiqun / Liu, QingChao et al. | SAE Technical Papers | 2020


    Expressway traffic capacity cooperative regulation and control method based on lane dynamic allocation of CAVs mixed traffic flow

    HAO WEI / ZHANG ZHAOLEI / LIU LI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Deep Double Q-Learning Method for CAVs Traffic Signal Control

    Su, Ziyi / Liu, QingChao / Zhao, Chunxia et al. | British Library Conference Proceedings | 2020