Accurately predicting the future motion of traffic participants is essential for autonomous driving in complex urban traffic scenes. Due to the frequent interactions and positioning uncertainties in the perception system, it is important to enable efficient spatial and temporal modeling of diverse entities and provide reliable distributions for future trajectories. In this work, we propose a novel Lane-aware Dynamic Spatio-temporal Transformer, called DSTformer, for effective and accurate vehicle trajectory prediction. The system aims to improve the robustness of autonomous vehicles by incorporating lane-aware scene constraints and utilizing both dynamic activities and scene context information. Specifically, we incorporate two masking methods to mitigate the impact of deviations and uncertainties from temporal and geographic spatial propagation views. Vehicles' trajectories that violate the expected lane-following rules are penalized via the Transformer-based modeling. Semantic neighborhood information is also employed via a graph masking method to capture the long-range spatial dependencies in traffic data. Additionally, the centerline waypoints based map structure is used to capture the vehicle-lane relations and enable multimodal trajectory prediction. Experimental results on the real-world dataset demonstrate that the proposed framework is resilient to imperfect data and achieves competitive performance with fewer parameters compared to current state-of-the-art prediction methods.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Lane-Aware Dynamic Spatio-Temporal Transformer for Unimodal Trajectory Prediction


    Beteiligte:
    Yuan, Yue (Autor:in) / Li, Wenqiang (Autor:in) / Liang, Yi (Autor:in) / Tay, Wee Peng (Autor:in) / Gao, Wei (Autor:in) / Shen, Feng (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.02.2025


    Format / Umfang :

    2432221 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    PreTR: Spatio-Temporal Non-Autoregressive Trajectory Prediction Transformer

    Achaji, Lina / Barry, Thierno / Fouqueray, Thibault et al. | IEEE | 2022



    TrAISformer: Spatio-Temporal Ship Trajectory Prediction Based on Transformer

    Li, Yunbo / Wang, Jiayu / Li, Tao et al. | IEEE | 2024


    Spatio-Temporal Context Graph Transformer Design for Map-Free Multi-Agent Trajectory Prediction

    Wang, Zhongning / Zhang, Jianwei / Chen, Jicheng et al. | IEEE | 2024

    Freier Zugriff

    A Dynamic Spatio-Temporal Deep Learning Model for Lane-Level Traffic Prediction

    Bao Li / Quan Yang / Jianjiang Chen et al. | DOAJ | 2023

    Freier Zugriff