By interpreting a traffic scene as a graph of interacting vehicles, we gain a flexible abstract representation which allows us to apply Graph Neural Network (GNN) models for traffic prediction. These naturally take interaction between traffic participants into account while being computationally efficient and providing large model capacity. We evaluate two state-of-the art GNN architectures and introduce several adaptations for our specific scenario. We show that prediction error in scenarios with much interaction decreases by 30 % compared to a model that does not take interactions into account. This suggests that interaction is important, and shows that we can model it using graphs. This makes GNNs a worthwhile addition to traffic prediction systems.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Graph Neural Networks for Modelling Traffic Participant Interaction


    Contributors:


    Publication date :

    2019-06-01


    Size :

    432349 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    ACTIVE TRAFFIC PARTICIPANT

    WEINSTEIN-RAUN BENJAMIN | European Patent Office | 2018

    Free access

    ACTIVE TRAFFIC PARTICIPANT

    WEINSTEIN-RAUN BENJAMIN | European Patent Office | 2018

    Free access

    Weak traffic participant early warning method and weak traffic participant early warning device

    JI XIAODONG / HU HAILONG | European Patent Office | 2024

    Free access

    Determining I2X traffic-participant criticality

    ADIREDDY GANESH / BOLDUC ANDREW PHILLIP | European Patent Office | 2021

    Free access

    Synthesizing Traffic Datasets Using Graph Neural Networks

    Rodriguez-Criado, Daniel / Chli, Maria / Manso, Luis J. et al. | IEEE | 2023