An efficient traffic management system is essential to minimize traffic problems and ensure the rapid circulation of emergency vehicles. This research proposes a new single-agent deep reinforcement-learning model using a deep Q-Network (DQN) to optimize traffic lights, aiming to reduce waiting times and increase vehicle speed, with particular emphasis on emergency vehicles. Our method incorporates a new state representation, which captures variations in vehicle density and speed that directly influence the reward structure to prioritize both traffic flow and emergency vehicle response times. The decision of the agent is enhanced by a replay memory mechanism, which ensures that experiences are effectively used in learning. The model’s effectiveness was tested in a simulated environment using SUMO, showing significant improvements in traffic management compared to traditional methods. Experimental results show that our system significantly reduces average waiting times and improves emergency vehicle prioritization.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Optimizing Traffic Light Control using Enhanced DQN: Minimizing Waiting Time for Regular and Emergency Vehicles



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource



    Optimizing road traffic of emergency vehicles

    Elmandili, Hasnaa / Toulni, Hamza / Nsiri, Benayad | IEEE | 2013


    Traffic light control system for emergency vehicles

    SHANNON ARTHUR QUINTEN | Europäisches Patentamt | 2025

    Freier Zugriff

    Traffic Light Pre-emption Control for Emergency Vehicles

    Kasim, Mohd Sallehin Mohd / Sajak, Aznida Abu Bakar / Wisman, Muhammad Rizal | IEEE | 2019


    Optimizing Traffic for Emergency Vehicles—An Improved Data-Driven Approach

    Parveen, M. Ayesha / Trishlaa, S. / Kee, Tenzin Sonam et al. | Springer Verlag | 2025


    Intelligent traffic light capable of adjusting passing time at any moment according to waiting vehicles

    NIU SHUGANG / NIU SHUQIANG | Europäisches Patentamt | 2015

    Freier Zugriff