One of the critical pieces of the self-driving puzzle is understanding the surroundings of a self-driving vehicle (SDV) and predicting how these surroundings will change in the near future. To address this task we propose MultiXNet, an end-to-end approach for detection and motion prediction based directly on lidar sensor data. This approach builds on prior work by handling multiple classes of traffic actors, adding a jointly trained second-stage trajectory refinement step, and producing a multimodal probability distribution over future actor motion that includes both multiple discrete traffic behaviors and calibrated continuous position uncertainties. The method was evaluated on large-scale, real-world data collected by a fleet of SDV s in several cities, with the results indicating that it outperforms existing state-of-the-art approaches.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MultiXNet: Multiclass Multistage Multimodal Motion Prediction


    Contributors:
    Djuric, Nemanja (author) / Cui, Henggang (author) / Su, Zhaoen (author) / Wu, Shangxuan (author) / Wang, Huahua (author) / Chou, Fang-Chieh (author) / Martin, Luisa San (author) / Feng, Song (author) / Hu, Rui (author) / Xu, Yang (author)


    Publication date :

    2021-07-11


    Size :

    7256394 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English