As the pretraining technique is growing in popularity, little work has been done on pretrained learning-based motion prediction methods in autonomous driving. In this paper, we propose a framework to formalize the pretraining task for trajectory prediction of traffic participants. Within our framework, inspired by the random masked model in natural language processing (NLP) and computer vision (CV), objects' positions at random timesteps are masked and then filled in by the learned neural network (NN). By changing the mask profile, our framework can easily switch among a range of motion-related tasks. We show that our proposed pretraining framework is able to deal with noisy inputs and improves the motion prediction accuracy and miss rate, especially for objects occluded over time by evaluating it on Argoverse and NuScenes datasets.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    RMP: A Random Mask Pretrain Framework for Motion Prediction


    Contributors:


    Publication date :

    2023-09-24


    Size :

    1255684 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Enhancing Motion Prediction by a Cooperative Framework

    Araluce, Javier / Justo, Alberto / Arizala, Asier et al. | IEEE | 2024


    Statistical Motion Mask and Sliding Registration

    Eiben, B / Tran, EH / Menten, MJ et al. | BASE | 2018

    Free access

    MOTION PREDICTION DEVICE, MOTION PREDICTION METHOD, AND MOTION PREDICTION PROGRAM

    OKAYAMA KEN | European Patent Office | 2022

    Free access