For autonomous vehicles to proactively plan safe trajectories and make informed decisions, they must be able to predict the future occupancy states of the local environment. However, common issues with occupancy prediction include predictions where moving objects vanish or become blurred, particularly at longer time horizons. We propose an environment prediction framework that incorporates environment semantics for future occupancy prediction. Our method first semantically segments the environment and uses this information along with the occupancy information to predict the spatiotemporal evolution of the environment. We validate our approach on the real-world Waymo Open Dataset. Compared to baseline methods, our model has higher prediction accuracy and is capable of maintaining moving object appearances in the predictions for longer prediction time horizons.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Predicting Future Spatiotemporal Occupancy Grids with Semantics for Autonomous Driving


    Contributors:


    Publication date :

    2024-06-02


    Size :

    2564221 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Occupancy Grids Generation Using Deep Radar Network for Autonomous Driving

    Engelhardt, Nick / Perez, Rodrigo / Rao, Qing | IEEE | 2019



    Predicting Future Occupancy Grids in Dynamic Environment with Spatio-Temporal Learning

    Mann, Khushdeep S. / Tomy, Abhishek / Paigwar, Anshul et al. | IEEE | 2022


    Danger detection using occupancy grids for autonomous systems and applications

    OH SANG-MIN / DEMIROZ BENJAMIN E / PAN GANG et al. | European Patent Office | 2023

    Free access

    HAZARD DETECTION USING OCCUPANCY GRIDS FOR AUTONOMOUS SYSTEMS AND APPLICATIONS

    OH SANGMIN / DEMIROZ BARIS EVRIM / PAN GANG et al. | European Patent Office | 2023

    Free access