In recent years, Autonomous Ships have become a focal point for research, specifically emphasizing improving ship autonomy. Machine Learning Controllers, especially those based on Reinforcement Learning, have seen significant progress. However, addressing the substantial computational demands and intricate reward structures required for their training remains critical. This paper introduces a novel approach, “Harnessing Traditional Controllers for Fast-Track Training of Deep Reinforcement Learning Control Strategies,” aimed at bridging conventional maritime control methods with cutting-edge DRL techniques for vessels. This innovative approach explores the synergies between stable traditional controllers and adaptive DRL methodologies, known for their complexity handling capabilities. To tackle the time-intensive nature of DRL training, we propose a solution: utilizing existing traditional controllers to expedite DRL training by cloning behavior from these controllers to guide DRL exploration. We rigorously assess the effectiveness of this approach through various ship maneuvering scenarios, including different trajectories and external disturbances like winds. The results unequivocally demonstrate accelerated DRL training while maintaining stringent safety standards. This approach has the potential to bridge the gap between traditional maritime practices and contemporary DRL advancements, facilitating the seamless integration of autonomous systems into naval operations, with promising implications for enhanced vessel efficiency, cost-effectiveness, and overall safety.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Harnessing traditional controllers for fast-track training of deep reinforcement learning control strategies


    Weitere Titelangaben:

    JOURNAL OF MARINE ENGINEERING & TECHNOLOGY
    M. S. ALAM and I. Carlucho


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    04.07.2025


    Format / Umfang :

    12 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch





    Multi-Intersection Control with Deep Reinforcement Learning and Ring-and-Barrier Controllers

    Muresan, Matthew / Pan, Guangyuan / Fu, Liping | Transportation Research Record | 2020


    Validation Environment for Deep Reinforcement Learning Based Gear Shift Controllers

    Altenburg, Stefan / Bause, Katharina / Albers, Albert | Springer Verlag | 2022


    Controllers for Lighter-Than-Air (LTA) Vehicles Using Deep Reinforcement Learning

    CANDIDO SALVATORE J / PONDA SAMEERA SYLVIA | Europäisches Patentamt | 2021

    Freier Zugriff


    Hierarchically Structured Controllers for Safe UAV Reinforcement Learning Applications

    Mannucci, Tommaso / Van Kampen, Erik-Jan / de Visser, Coen C. et al. | AIAA | 2017