An efficient transportation system can substantially benefit our society, but road intersections have always been among the major traffic bottlenecks leading to traffic congestion. Appropriate traffic signal timing adapted to real-time traffic may help mitigate such traffic congestion. However, most existing traffic signal control methods require a huge amount of road information, such as vehicle positions. In this paper, we focus on a particular road intersection and aim to minimize the average waiting time. We propose a traffic signal control (TSC) system based on an end-to-end off-policy deep reinforcement learning (deep RL) agent with background removal residual networks. The agent takes real-time images at the road intersection as input. Upon sufficient training, the agent can perform (near-) optimal traffic signaling based on real-time traffic conditions. We conduct experiments on different intersection scenarios and compare various TSC methods. The experimental results show that our end-to-end deep RL approach can adapt to the dynamic traffic based on the traffic images and outperforms other TSC methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Traffic Signal Control Using End-to-End Off-Policy Deep Reinforcement Learning


    Beteiligte:
    Chu, Kai-Fung (Autor:in) / Lam, Albert Y. S. (Autor:in) / Li, Victor O. K. (Autor:in)


    Erscheinungsdatum :

    2022-07-01


    Format / Umfang :

    1606763 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Deep Reinforcement Learning-based Traffic Signal Control

    Ruan, Junyun / Tang, Jinzhuo / Gao, Ge et al. | IEEE | 2023


    Applications on Deep Reinforcement Learning in Traffic Signal Control

    Sun, Haolun / Sun, Yilong / Yu, Boyang | IEEE | 2022


    Traffic signal control method based on deep reinforcement learning

    LIU DUANYANG / SHEN SI / SHEN GUOJIANG et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    A Deep Reinforcement Learning Approach to Traffic Signal Control

    Razack, Aquib Junaid / Ajith, Vysyakh / Gupta, Rajiv | IEEE | 2021


    Deep Learning vs. Discrete Reinforcement Learning for Adaptive Traffic Signal Control

    Shabestary, Soheil Mohamad Alizadeh / Abdulhai, Baher | IEEE | 2018