In this study, we propose a data-driven multi-agent system (D-MAS), in which dynamic interactions among different maritime agents, representing shore station-vessel, vessel-vessel, and virtual agent-physical agent, are modeled, to enhance maritime traffic safety management. The multi-agent framework is proposed through integrating learning, forecasting and planning technologies. Our prototype multi-agent system provides solutions to accommodate maritime data analysis and simulation for maritime traffic dynamics and safety evaluation and management. The prototype system developed on top of a set of universal APIs enables adaption to different algorithms for simulation and modeling. Based on multi-agent characterization, we have presented agent-based situational awareness, traffic forecasting, intelligent route planning that are of high importance for maritime traffic safety. The framework proposed can be further developed and applied for applications in maritime safety management.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Data-driven multi-agent system for maritime traffic safety management


    Contributors:


    Publication date :

    2017-10-01


    Size :

    2173223 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Maritime safety management system

    PARK CHANG WOO / LEE CHANG JO | European Patent Office | 2020

    Free access

    Bidirectional Data-Driven Trajectory Prediction for Intelligent Maritime Traffic

    Xiao, Ye / Li, Xingchen / Yao, Wen et al. | IEEE | 2023



    Maritime Traffic Networks: From Historical Positioning Data to Unsupervised Maritime Traffic Monitoring

    Fernandez Arguedas, Virginia / Pallotta, Giuliana / Vespe, Michele | IEEE | 2018

    Free access

    Nautical traffic simulation with multi-agent system for safety

    Xiao, Fangliang / Ligteringen, Han / van Gulijk, Coen et al. | IEEE | 2013