This paper presents an approach for autonomous docking of a fully actuated autonomous surface vessel using expert demonstration data. We frame the docking problem as an imitation learning task and employ inverse reinforcement learning (IRL) to learn a reward function from expert trajectories. A two-stage neural network architecture is implemented to incorporate both environmental context from sensors and vehicle kinematics into the reward function. The learned reward is then used with a motion planner to generate docking trajectories. Experiments in simulation demonstrate the effectiveness of this approach in producing human-like docking behaviors across different environmental configurations.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data


    Beteiligte:

    Erschienen in:

    Erscheinungsdatum :

    23.09.2024


    Format / Umfang :

    1033228 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Learning Autonomous Docking Operation of Fully Actuated Autonomous Surface Vessel from Expert data

    Vijayakumar, Akash / A, Atmanand M / Somayajula, Abhilash | ArXiv | 2024

    Freier Zugriff

    Autonomous docking of a feeder vessel

    de Kruif, Bas J. | Taylor & Francis Verlag | 2024

    Freier Zugriff

    AUTONOMOUS OPERATION OF A VESSEL

    JOKIOINEN ESA ANTTI / SKOGVOLD MORTEN / POIKONEN JONNE KALEVI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    WATER SURFACE AUTONOMOUS VESSEL

    HAUMONTE LUC / VELAY LAURENT | Europäisches Patentamt | 2017

    Freier Zugriff

    AN AUTONOMOUS SURFACE VESSEL

    MAKA MAITRAI | Europäisches Patentamt | 2019

    Freier Zugriff