With the breakthrough of connected and autonomous vehicles (CAVs) technology, vehicle trajectories can be collected by various sensors installed on CAVs continuously and sent to the traffic control center for operation and management. However, the trajectory data collected by CAVs may contain incomplete part owing to sensor limitation, thus hindering the data availability. To address this issue, we propose a CNN-based generative model for reconstructing multiple vehicle trajectories in multi-lane traffic scenarios using hybrid detection data from both CAVs and fixed sensors. Specifically, we generate missing trajectories using a Generative Adversarial Network (GAN) architecture with spatio-temporal features extracted by Convolutional Neural Networks (CNNs). The performance of the method is examined on a simulated arterial by assessing the mean absolute error (MAE) of the reconstructed data. The results indicate our method is robust even at a low CAV penetration rate.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A CNN-based generative model for vehicle trajectory reconstruction in mixed traffic flow


    Beteiligte:
    Hu, Jianghan (Autor:in) / Lian, Song (Autor:in) / Hu, Simon (Autor:in) / Demartino, Cristoforo (Autor:in) / Wang, Gaoang (Autor:in) / Liu, Xin (Autor:in) / Li, Yongfu (Autor:in) / Roncoli, Claudio (Autor:in) / Lee, Der-Horng (Autor:in)


    Erscheinungsdatum :

    14.06.2023


    Format / Umfang :

    1307378 byte




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Evaluating Generative Vehicle Trajectory Models for Traffic Intersection Dynamics

    Ranjan, Yash / Sengupta, Rahul / Rangarajan, Anand et al. | ArXiv | 2025

    Freier Zugriff

    Calibration of Vehicle-Following Model Parameters Using Mixed Traffic Trajectory Data

    Anand, P. Anusree / Atmakuri, Priyanka / Anne, Viswa Sri Rupa et al. | Springer Verlag | 2019


    Expressway traffic flow full-sample trajectory reconstruction method based on automatic driving vehicle movement detection

    CHEN PENG / WEI LEI / WANG YUNPENG | Europäisches Patentamt | 2020

    Freier Zugriff

    Trajectory Data and Flow Characteristics of Mixed Traffic

    Kanagaraj, Venkatesan / Asaithambi, Gowri / Toledo, Tomer et al. | Transportation Research Record | 2019