Autonomous navigation for ships is recognised as a pivotal trend in the future maritime industry, especially autonomous avoidance collision decision-making in complex multi-ship encounter scenarios, which constitutes a significant area of research. This paper presents an adaptive autonomous navigation decision system for ships, which addresses the problems posed by intricate situations. A dynamic collision risk index (CRI) model based on the dangerous manoeuvring intervals is established, derived using an improved velocity obstacle (VO) algorithm, which incorporates ship manoeuvrability constraints and the Convention on International Regulations for preventing collisions at sea (COLREGs). Autonomous navigation decision-making is achieved by combining the fuzzy PID (Proportional–Integral–Derivative) course control method and the trajectory tracking of the adaptive Line-of-Sight (LOS) algorithm. Combining the Model Predictive Control (MPC) idea, this approach enables ships to navigate autonomously and adaptively in challenging water conditions. To evaluate the effectiveness of the proposed approach, two case studies involving the five-ship encounter situation and the six-ship encounter situation are conducted. The results demonstrate that the presented autonomous navigation decision-making approach efficiently tracks the planned route while safely avoiding all target ships. Moreover, the decision-making exhibits adaptability in coping with the dynamic manoeuvres of the target ships, including alterations in the course and changes in speed. These findings confirm that the proposed system significantly enhances the ability of autonomous ships to navigate safely and adaptively in complex multi-ship encounter scenarios, demonstrating its practical relevance and effectiveness for real-world maritime applications.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Adaptive collision avoidance decision system for autonomous ship navigation


    Additional title:

    JOURNAL OF MARINE ENGINEERING & TECHNOLOGY
    X. ZHAO ET AL.


    Contributors:
    Zhao, Xingya (author) / He, Yixiong (author) / Huang, Liwen (author) / Mou, Junmin (author) / Wen, Jie (author) / Zhang, Ke (author)

    Published in:

    Publication date :

    2025-03-04


    Size :

    15 pages




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Ship Collision Avoidance Autonomous Avoidance System using Deep Learning

    CHO SEOK JE / KIM HYUNG JIN / KIM SOO HO et al. | European Patent Office | 2021

    Free access

    Autonomous collision avoidance navigation system and method

    STAMENKOVICH MIROSLAV / GREER ROBERT ALEXANDER | European Patent Office | 2016

    Free access

    Inland ship navigation collision avoidance method and system

    ZHANG XIAOHAN / WU HONGGUANG / ZHAI ZHENGANG et al. | European Patent Office | 2023

    Free access

    Autonomous navigation vessels for collision avoidance

    KIM KYUNG SUNG | European Patent Office | 2022

    Free access