Human driving depends on latent states, such as aggression and intent, that cannot be directly observed. In this work, we propose a method for learning driver models that can account for unobserved states. When trained on a synthetic dataset, our model is able to learn encodings for vehicle trajectories that distinguish between four distinct classes of driver behavior. Such encodings are learned without any knowledge of the number of driver classes or any objective that directly requires the model to learn encodings for each class. We show that latent state driving policies outperform baseline methods at replicating driver behavior. Furthermore, we demonstrate that the actions chosen by our policy are heavily influenced by its assigned latent state.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Simultaneous policy learning and latent state inference for imitating driver behavior


    Contributors:


    Publication date :

    2017-10-01


    Size :

    208098 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Imitating Driver Behavior with Generative Adversarial Networks

    Kuefler, Alex / Morton, Jeremy / Wheeler, Tim et al. | British Library Conference Proceedings | 2017


    Imitating driver behavior with generative adversarial networks

    Kuefler, Alex / Morton, Jeremy / Wheeler, Tim et al. | IEEE | 2017


    Trajectory planning for vehicle collision avoidance imitating driver behavior

    Yang, Bin / Song, Xuewei / Gao, Zhenhai et al. | SAGE Publications | 2022


    Underwater fishtail-imitating soft driver and control system thereof

    MENG QINGXIN / SUN XUEFENG / XIAO JIAXIN et al. | European Patent Office | 2024

    Free access