Abstract Traffic signal control plays a crucial role in managing traffic flow and alleviating congestion on urban roads. This study proposes a deep reinforcement learning (DRL) approach to optimize traffic signal control and reduce traffic congestion in urban environments. Leveraging Perceiver transformers and a deep neural network, the approach uses traffic flow data — including speed, vehicle arrivals, and other relevant metrics — to enhance signal regulation. The DRL framework is based on the Q-learning algorithm and operates without relying on specific traffic models or rules. To evaluate different traffic control strategies, we introduce a benchmark map of Žilina city as a testing ground. Our method establishes a robust framework for optimising urban traffic, achieving significant improvements in traffic flow efficiency and congestion reduction, as demonstrated through simulations on this map.


    Access

    Download


    Export, share and cite



    Title :

    Exploring Urban Traffic Dynamics: Introducing a Benchmark Map for Comprehensive Testing and Evaluation


    Additional title:

    Int. J. ITS Res.


    Contributors:


    Publication date :

    2025-06-13




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Exploring urban traffic flow dynamics

    Malcontenti-Wilson, Adam / Vu, Hai L. / Cadusch, Peter et al. | IEEE | 2013


    Exploring urban typologies using comprehensive analysis of transportation dynamics

    Kuncheria, Anu / Walker, Joan L. / Macfarlane, Jane | Springer Verlag | 2025

    Free access


    Dynamic Comprehensive Evaluation of Traffic Congestion on Urban Roads

    Shu, Kun / Zhou, Bei / Zhang, Sheng-Rui et al. | ASCE | 2020


    Dynamic Comprehensive Evaluation of Traffic Congestion on Urban Roads

    Shu, Kun / Zhou, Bei / Zhang, Sheng-Rui et al. | TIBKAT | 2020