Vehicle trajectory prediction is an important task that can ensure high safety performance in collision avoidance systems and applications of autonomous vehicles. Machine learning methods for vehicle trajectory prediction have been proposed in recent literature in an effort to increase traffic safety by accurately predicting vehicle trajectories in various traffic scenarios. This paper presents a comprehensive review of recently proposed methods of vehicle trajectory prediction that utilize machine learning (ML) techniques. Moreover, it proposes a novel neural network framework for vehicle trajectory prediction that aims to be implemented in a connected vehicles (CV) environment.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Machine Learning in Connected Vehicle Environments


    Beteiligte:
    Bezerra, Jean (Autor:in) / Adla, Rawa (Autor:in)


    Erscheinungsdatum :

    2023-07-24


    Format / Umfang :

    243911 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Vehicle Reidentification in a Connected Vehicle Environment using Machine Learning Algorithms

    Miao, Zuoyu / Head, K. Larry / Beak, Byungho | Transportation Research Record | 2018


    Machine Learning for Security Resiliency in Connected Vehicle Applications

    Boddupalli, Srivalli / Owoputi, Richard / Duan, Chengwei et al. | Springer Verlag | 2023


    Trajectory-Based Signal Control in Mixed Connected Vehicle Environments

    Talukder, Md Abu Sufian / Lidbe, Abhay D. / Tedla, Elsa G. et al. | ASCE | 2021


    Detecting Imminent Lane Change Maneuvers in Connected Vehicle Environments

    Bakhit, Peter R. / Osman, Osama A. / Ishak, Sherif | Transportation Research Record | 2017


    A Survey of Safety Warnings Under Connected Vehicle Environments

    Li, Haijian / Zhao, Guoqiang / Qin, Lingqiao et al. | IEEE | 2021