This work introduces the multidimensional Graph Fourier Transformation Neural Network (GFTNN) for longterm trajectory predictions on highways. Similar to Graph Neural Networks (GNNs), the GFTNN is a novel network architecture that operates on graph structures. While several GNNs lack discriminative power due to suboptimal aggregation schemes, the proposed model aggregates scenario properties through a powerful operation: the multidimensional Graph Fourier Transformation (GFT). The spatio-temporal vehicle interaction graph of a scenario is converted into a spectral scenario representation using the GFT. This beneficial representation is input to the prediction framework composed of a neural network and a descriptive decoder. Even though the proposed GFTNN does not include any recurrent element, it outperforms state-of-the-art models in the task of highway trajectory prediction. For experiments and evaluation, the publicly available datasets highD and NGSIM are used.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction


    Contributors:


    Publication date :

    2022-10-08


    Size :

    653174 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



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

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

    Free access


    Multi-Agent Trajectory Prediction with Graph Attention Isomorphism Neural Network

    Liu, Yongkang / Qi, Xuewei / Sisbot, Emrah Akin et al. | IEEE | 2022



    NEURAL NETWORK TRAJECTORY PREDICTION

    CHEN YUXIAO / IVANOVIC BORIS / PAVONE MARCO | European Patent Office | 2023

    Free access