A more attractive future railway system needs to offer more capacity in the railway network and improve quality and punctuality. A fundamental centerpiece of future digitized railway network operations is automated and optimized planning and dispatching. The sector initiative “Digitale Schiene Deutschland” (DSD) develops a holistic and intelligent Capacity & Traffic Management System (CTMS) that can automatically plan and continuously optimize railway traffic at scale. Both, planning and dispatching tasks, are highly complex and, today, require human expertise and oversight. Our main contribution is a multi-agent deep reinforcement learning approach at the core of the envisioned CTMS, which learns from interaction with a realistic, microscopic railway simulation. Our results demonstrate that the proposed approach flexibly solves planning and re-scheduling tasks in the realistic setting of a medium-sized part of the German railway network. It exhibits response times and scaling properties that make it a promising candidate for future applications in railway operations at scale.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Intelligent Railway Capacity and Traffic Management Using Multi-Agent Deep Reinforcement Learning


    Beteiligte:
    Schneider, Stefan (Autor:in) / Ramesh, Anirudha (Autor:in) / Roets, Anne (Autor:in) / Stirbu, Ciprian (Autor:in) / Safaei, Farhad (Autor:in) / Ghriss, Faten (Autor:in) / Wulfing, Jan (Autor:in) / Gura, Mehmet (Autor:in) / Sibon, Nima (Autor:in) / Gentry, Rick (Autor:in)


    Erscheinungsdatum :

    24.09.2024


    Format / Umfang :

    554326 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Intelligent Traffic Management System using Multi-Agent Reinforcement Learning

    Shaheen, Dalaali / Paulraj, Getzi Jeba Leelipushpam / Jebadurai, Immanuel Johnraja et al. | IEEE | 2025


    Microscopic Traffic Simulation by Cooperative Multi-agent Deep Reinforcement Learning

    Bacchiani, Giulio / Molinari, Daniele / Patander, Marco | ArXiv | 2019

    Freier Zugriff


    Multi-Agent Deep Reinforcement Learning for Large-Scale Traffic Signal Control

    Chu, Tianshu / Wang, Jie / Codeca, Lara et al. | IEEE | 2020