Taking advantage of communication and sensing technology, trajectory optimization at signalized intersection (i.e., Eco-Approach and Departure) based on information from vehicle-to-infrastructure (V2I) communications has been proven to be effective to improve vehicle energy efficiency while guaranteeing safety and mobility. However, existing approaches are either rule-based models or optimization models, which cannot achieve optimality and computational efficiency at the same time. In this article, we propose and test a novel learning-based approach, machine learning trajectory planning algorithm (MLTPA), to achieve real-time optimization by training a machine learning model to approximate the solution from a previously developed optimization-based method named graph-based trajectory planning algorithm (GBTPA). Five types of machine learning techniques, including linear regression, k-nearest neighbors, decision tree, random forest, and multilayer perceptron (MLP) neural network, are compared in terms of the prediction accuracy, and the random forest method is finally selected. The proposed MLTPA reduces computation time from tens of seconds to a few milliseconds. Simulation results illustrate that MLTPA can achieve median 5.0%-6.20% improvement on energy savings over multiple simulation runs. The proposed method also has the potential to approximate other trajectory planning algorithms to achieve real-time performance while ensuring optimality.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Machine Learning-Based Eco-Approach and Departure: Real-Time Trajectory Optimization at Connected Signalized Intersections


    Weitere Titelangaben:

    Sae International Journal of Sustainable Transportation Energy Environment and Policy
    Sae J. Steep


    Beteiligte:
    Esaid, Danial (Autor:in) / Ye, Fei (Autor:in) / Wu, Guoyuan (Autor:in) / Boriboonsomsin, Kanok (Autor:in) / Barth, Matthew (Autor:in) / Hao, Peng (Autor:in) / Wei, Zhensong (Autor:in)


    Erscheinungsdatum :

    13.10.2021


    Format / Umfang :

    13 pages




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    GlidePath: Eco-Friendly Automated Approach and Departure at Signalized Intersections

    Altan, Osman D. / Wu, Guoyuan / Barth, Matthew J. et al. | IEEE | 2017



    Real-Time Crash-Risk Optimization at Signalized Intersections

    Reyad, Passant / Sayed, Tarek / Essa, Mohamed et al. | Transportation Research Record | 2021

    Freier Zugriff


    Optimizing Vehicle Approach Strategies for Connected Signalized Intersections

    Gunther, Hendrik-Jorn / Kumar, Vivek Vijaya / Hussain, Shah et al. | IEEE | 2019