One essential task for autonomous driving is to accurately predict the future motions of surrounding traffic agents. Recently, Graph Neural Network (GNN) approaches have shown potential in motion prediction due to the fact that information in the traffic scenario can be inherently formed into a graph structure. However, existing approaches are limited to using a static graph representing the states of the current timestamp, ignoring the prediction scenario’s derivation. In this work, we propose the Future Graph Network (FGNet) a two-stage GNN-based model for accurate and real-time multi-agent motion prediction. We design a future graph decoder that takes first-stage F mode multi-agent prediction result as input and reconstructs a graph to represent the derivation result of the scenario. The decoder enhances the first-stage result by (1) Constraining the agent’s future trajectory in the same modal to be harmonious and (2) Introducing the subsequent road information to guide the long-term prediction. Meanwhile, we incorporate statistical characteristics of the vehicles’ trajectory into the design of the loss function, which further boosts the performance of our model. Experiments show that FGNet achieves competitive performance on the Argoverse motion forecasting benchmark with real-time inference.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    FGNet: A Graph-Based Motion Forecasting Method From a Future Perspective


    Contributors:
    Tang, Xiaqiang (author) / Guo, Yafeng (author) / Sun, Yiyang (author) / Hu, Siyuan (author) / Wang, Jun (author)


    Publication date :

    2023-06-04


    Size :

    1832348 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    STGT: FORECASTING PEDESTRIAN MOTION USING SPATIO-TEMPORAL GRAPH TRANSFORMER

    Syed, Arsal / Morris, Brendan | British Library Conference Proceedings | 2021


    FSGA: Motion Prediction Method Based on Future Scene Graph Attention

    Xu, Nan / Chen, Chaoyi / Chu, Liang et al. | IEEE | 2025



    FFINet: Future Feedback Interaction Network for Motion Forecasting

    Kang, Miao / Wang, Shengqi / Zhou, Sanping et al. | IEEE | 2024


    Goal-based motion forecasting

    CHOUDHURY SANJIBAN / KUMAR SUMIT / MARCHETTI-BOWICK MICOL | European Patent Office | 2023

    Free access