Deep reinforcement learning combines the perception ability of deep learning with the decision-making ability of reinforcement learning, and discovers the optimal strategy for the task through continuous trial and error learning of the agent. This paper studies the deep reinforcement learning method for multi-ship path planning. We combine the characteristics of ship navigation to redesign the reward function and the continuous action space and state space, and improve the Q value calculation method based on the characteristics of ship planning. Finally, we set up a simulation experiment to show that the method proposed in this paper can effectively plan collision-free paths for multiple ships at the same time.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Research on deep reinforcement learning method for multi-ship path planning


    Contributors:
    Lirong, Lirong (author) / Wang, Ne (author) / He, Wei (author)

    Conference:

    International Conference on Mechanisms and Robotics (ICMAR 2022) ; 2022 ; Zhuhai,China


    Published in:

    Proc. SPIE ; 12331


    Publication date :

    2022-11-10





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Multi-Obstacle Path Planning using Deep Reinforcement Learning

    Morgan, Brandon / Trigg, Lena / Stringer, Alexander et al. | IEEE | 2024


    Research on path planning algorithm based on deep reinforcement learning

    Wang, Zhihao / Yan, Weiqiang / Yang, Mingjun | IEEE | 2024


    Deep Reinforcement Learning for Image-Based Multi-Agent Coverage Path Planning

    Xu, Meng / She, Yechao / Jin, Yang et al. | IEEE | 2023


    Deep Reinforcement Learning-Based UAV Path Planning Algorithm

    Wang, Kunfu / Hui, Ma / Hou, Jiajun et al. | IEEE | 2024


    A UAV Path Planning Method Based on Deep Reinforcement Learning

    Li, Yibing / Zhang, Sitong / Ye, Fang et al. | IEEE | 2020