The precise forecasting of vessel paths plays a vital role in enhancing navigation performance, streamlining voyage planning, boosting the efficiency of maritime rescue missions, and maintaining safety at sea. Nontheless, history trajectory and the interaction of different vessels attach great importance on the purpose of predicting the future trajectoy. In order to handle this problem, this paper proposes a self-supervised marine vessel trajectory prediction method. The proposed model can effectively extract the maritime spatial and temporal trajectory features, which can greatly improve the accuracy and rapidity of the trajectory prediction. The maritime dataset from the Singapore waters is used for proving the validation of our model. The experimental results demonstrate that our model largely reduce the average displacement error and final displacement error compared with other models. These advancements will facilitate the generation of precise navigation patterns, reducing navigational path discrepancies while enhancing the precision of anti-collision mechanisms. Such developments thereby strengthen early warning capabilities for maritime traffic conflicts and help mitigate the likelihood of marine incidents through proactive risk management strategies.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Vessel Trajectory Prediction based on Self-Supervised Learning Methods


    Contributors:
    Wu, Hongjie (author) / Yan, Chenyang (author) / Qing, Yuhao (author) / Wang, Yueying (author)


    Publication date :

    2025-05-23


    Size :

    436494 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Self‐supervised vessel trajectory segmentation via learning spatio‐temporal semantics

    Rui Zhang / Haitao Ren / Zhipei Yu et al. | DOAJ | 2024

    Free access

    Self‐supervised vessel trajectory segmentation via learning spatio‐temporal semantics

    Zhang, Rui / Ren, Haitao / Yu, Zhipei et al. | Wiley | 2024

    Free access

    Self-Supervised Transformer for Trajectory Prediction Using Noise Imputed Past Trajectory

    Bharilya, Vibha / Arora, Ashok / Kumar, Neetesh | IEEE | 2025


    Deep Learning Methods for Vessel Trajectory Prediction Based on Recurrent Neural Networks

    Capobianco, Samuele / Millefiori, Leonardo M. / Forti, Nicola et al. | IEEE | 2021


    Vessel Trajectory Prediction Based on Context-Assisted Information

    Wang, Jianing / Jiao, Lianmeng / Pan, Quan | IEEE | 2024