In this paper, a learning experience reuse - reinforcement learning collision avoidance (LER-RLCA) method is proposed, which can synthesize near-optimal collision avoidance policy with efficient sampling and good seamanship, to solve the local safety sailing of autonomous ship in a multi-obstacle environment. Lying on the general reinforcement learning (RL), using learning experience reuse, the hidden features of historical training data were mined. Meanwhile, a new reward function combining external revenue signal with internal incentive signal was designed to encourage search the environment with a low probability of state transition. We further applied LER-RLCA algorithm to the simulation of autonomous ship collision avoidance. The results show that the proposed LER-RLCA algorithm can well realize the collision-free and safe navigation of autonomous ships, to avoid falling into local iteration, greatly improve the convergence speed of the algorithm, and improve the performance of online collision avoidance decision-making.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Efficient Reinforcement Learning for Autonomous Ship Collision Avoidance under Learning Experience Reuse


    Beteiligte:
    Wang, Chengbo (Autor:in) / Zhang, Xinyu (Autor:in) / Gao, Hongbo (Autor:in) / Su, Huiping (Autor:in) / Zheng, Kangjie (Autor:in) / Wang, Weisong (Autor:in)


    Erscheinungsdatum :

    2022-10-28


    Format / Umfang :

    2565592 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Ship Collision Avoidance Autonomous Avoidance System using Deep Learning

    CHO SEOK JE / KIM HYUNG JIN / KIM SOO HO et al. | Europäisches Patentamt | 2021

    Freier Zugriff

    Towards Safe Deep Reinforcement Learning for Autonomous Airborne Collision Avoidance Systems

    Panoutsakopoulos, Christos / Yuksek, Burak / Inalhan, Gokhan et al. | AIAA | 2022


    Towards Safe Deep Reinforcement Learning for Autonomous Airborne Collision Avoidance Systems

    Panoutsakopoulos, Christos / Yuksek, Burak / Inalhan, Gokhan et al. | TIBKAT | 2022


    Method for collision avoidance based on deep reinforcement learning with path-speed control for an autonomous ship

    Do-Hyun Chun / Myung-Il Roh / Hye-Won Lee et al. | DOAJ | 2024

    Freier Zugriff

    Deep Learning for Autonomous Collision Avoidance

    Strömgren, Oliver | BASE | 2018

    Freier Zugriff