Accurately predicting the trajectories of surrounding agents is critically important for the safe operation of autonomous vehicles. However, complex environments not only increase the computational cost but also introduce multimodality in the agent’s future motions, presenting significant challenges for motion prediction. Therefore, we propose FSGA, a trajectory prediction framework that constructs a relationship graph between agents and lanes in future spacetime and utilizes a graph attention mechanism to analyze the interactions between these future spacetime agents and lanes. We employ a vectorized representation method to model the traffic scene as a graph. Through this vectorized scene representation, FSGA extracts spatio-temporal features from agents’ historical trajectories, including interactions between agents, and between agents and lanes. To reduce computational costs, a lane scoring mechanism is employed, allowing the model to focus only on the lanes that have a significant impact on the current agent’s motion. To address complexity and multimodality of future trajectories, we introduce a branching tree goal prediction structure that models multiple possible motion trends by representing waypoints and endpoints at different temporal stages. Based on these predicted goals, we construct a relationship graph that captures the associations between agents and lanes in future spacetime and obtains the interactions between agents and lanes, improving trajectory prediction accuracy. Experiments show that FSGA achieves state-of-the-art performance on Argoverse1.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FSGA: Motion Prediction Method Based on Future Scene Graph Attention


    Contributors:
    Xu, Nan (author) / Chen, Chaoyi (author) / Chu, Liang (author) / Guo, Chong (author) / Pang, Tianshu (author)


    Publication date :

    2025-06-01


    Size :

    2329286 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Towards Consistent and Explainable Motion Prediction using Heterogeneous Graph Attention

    Demmler, Tobias / Tamke, Andreas / Dang, Thao et al. | IEEE | 2024


    Airport scene track prediction method based on multi-head attention mechanism

    SHI XIAOZHU / JIANG ZHIQIAN / WANG ERSHEN et al. | European Patent Office | 2022

    Free access

    SCENE TOKENIZATION FOR MOTION PREDICTION

    ZHOU YIN / JI JINGWEI / YANG ZHENPEI et al. | European Patent Office | 2025

    Free access

    Top-down scene prediction based on object motion

    MORALES MORALES ANGEL GUADALUPE / KOBILAROV MARIN / GARIMELLA GIANNI et al. | European Patent Office | 2022

    Free access

    Top-down scene prediction based on motion data

    GARIMELLA GIANNI / KOBILAROV MARIN / MORALES MORALES ANGEL GUADALUPE et al. | European Patent Office | 2022

    Free access