Accurately predicting the future trajectories of surrounding traffic agents is important for ensuring the safety of autonomous vehicles. To address the scenario of frequent interactions among traffic agents in the highway merging area, this paper proposes a trajectory prediction method based on interactive graph attention mechanism. Our approach integrates an interactive graph model to capture the complex interactions among traffic agents as well as the interactions between these agents and the contextual map of the highway merging area. By leveraging this interactive graph model, we establish an agent-agent interactive graph and an agent-map interactive graph. Moreover, we employ Graph Attention Network (GAT) to extract spatial interactions among trajectories, enhancing our predictions. To capture temporal dependencies within trajectories, we employ a Transformer-based multi-head self-attention mechanism. Additionally, GAT are utilized to model the interactions between traffic agents and the map. The method we propose comprehensively incorporates the influences of time, space, and the map on trajectories. The interactive graph models can serve as effective prior knowledge for learning-based approaches, thereby enhancing the acquisition of interaction patterns among traffic scenarios and facilitating the interpretability of the method. We evaluate the performances of our method using real-world trajectory datasets from the highway merging area, i.e., the Exits and Entries Drone Dataset (exiD). Comparative analysis against classical algorithms demonstrates a reduced trajectory prediction error for prediction horizons of both 3s and 4s.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Vehicle Trajectory Prediction in Highway Merging Area Using Interactive Graph Attention Mechanism


    Weitere Titelangaben:

    Sae Technical Papers


    Beteiligte:
    Chu, Duanfeng (Autor:in) / Xin, Guipeng (Autor:in) / Liu, Hongxiang (Autor:in) / Lu, Liping (Autor:in) / Wu, Xigang (Autor:in) / Deng, Zejian (Autor:in)

    Kongress:

    SAE 2023 Intelligent Urban Air Mobility Symposium ; 2023



    Erscheinungsdatum :

    31.12.2023




    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Print


    Sprache :

    Englisch




    A Pedestrian Trajectory Prediction Model Based on Interactive Attention Mechanism

    Dou, Wanqing / Lu, Lili / Huang, Yamei | Springer Verlag | 2024


    Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving

    Mo, Xiaoyu / Xing, Yang / Lv, Chen | ArXiv | 2021

    Freier Zugriff


    Attention Based Vehicle Trajectory Prediction

    Messaoud, Kaouther / Yahiaoui, Itheri / Verroust-Blondet, Anne et al. | IEEE | 2021


    Learning Interactive Knowledge Graph for Trajectory Prediction

    Zhu, Chen / Bai, Jie / Fang, Jianwu et al. | British Library Conference Proceedings | 2022