About | Contact Us | Register | Login
ProceedingsSeriesJournalsSearchEAI
Intelligent Transport Systems. 8th International Conference, INTSYS 2024, Pisa, Italy, December 5–6, 2024, Revised Selected Papers

Research Article

Adaptive Stop-Skipping Scheduling Approach Using Reinforcement Learning

Cite
BibTeX Plain Text
  • @INPROCEEDINGS{10.1007/978-3-031-86370-7_10,
        author={Perla Hajjar and Le\~{n}la Kloul and Dominique Barth},
        title={Adaptive Stop-Skipping Scheduling Approach Using Reinforcement Learning},
        proceedings={Intelligent Transport Systems. 8th International Conference, INTSYS 2024, Pisa, Italy, December 5--6, 2024, Revised Selected Papers},
        proceedings_a={INTSYS},
        year={2025},
        month={4},
        keywords={Stop-skipping Adaptive bus scheduling Reinforcement Learning Simulated Annealing},
        doi={10.1007/978-3-031-86370-7_10}
    }
    
  • Perla Hajjar
    Leïla Kloul
    Dominique Barth
    Year: 2025
    Adaptive Stop-Skipping Scheduling Approach Using Reinforcement Learning
    INTSYS
    Springer
    DOI: 10.1007/978-3-031-86370-7_10
Perla Hajjar,*, Leïla Kloul, Dominique Barth
    *Contact email: perla.hajjar@uvsq.fr

    Abstract

    To adapt to real-time variations, stop-skipping control has been widely adopted in public transport systems. However, solving the optimal stopping pattern for buses in static bus scheduling problems is challenging due to its combinatorial nature. The complexity of this problem increases exponentially as the number of stations increases, making it difficult to find the best solution in real time. To overcome such a limitation, this paper proposes an adaptive scheduling game model approach using the stop skipping control strategy. The adaptive game model aims to minimize passenger delay by adjusting bus stops, demonstrating the effectiveness of continuous schedule adaptation against a fixed, pre-determined schedule. This game is then solved with Reinforcement Learning (RL) to optimize the bus scheduling sequence based the current system’s state. We compare this approach against the Simulated Annealing metaheuristic algorithm in finding a near-optimal schedule. Our results show that the RL-based adaptive scheduling outperforms the schedule found statically and all-stop schedules, reducing waiting, ride, and total trip times.

    Keywords
    Stop-skipping Adaptive bus scheduling Reinforcement Learning Simulated Annealing
    Published
    2025-04-03
    Appears in
    SpringerLink
    http://dx.doi.org/10.1007/978-3-031-86370-7_10
    Copyright © 2024–2025 ICST
    EBSCOProQuestDBLPDOAJPortico
    EAI Logo

    About EAI

    • Who We Are
    • Leadership
    • Research Areas
    • Partners
    • Media Center

    Community

    • Membership
    • Conference
    • Recognition
    • Sponsor Us

    Publish with EAI

    • Publishing
    • Journals
    • Proceedings
    • Books
    • EUDL