Neural network autonomous driving policies are widely explored. However, no matter using imitation learning or reinforcement learning, the network policies are generally hard to train, and the learned knowledge encoded in neural network policies are hard to transfer. We propose to modularize the complicated driving policies in terms of the driving attributes, and present the parallel attribute networks (PAN), which can learn to fullfill the requirements of the attributes in the driving tasks separately, and later assemble their knowledge together. Concretely, we first train a policy network that accomplish the base lane tracking attribute. The modules for the add-on attributes such as avoiding obstacles and obeying traffic rules are then trained to map the corresponding state to a satisfactory set of the vehicle action space. Finally the reference action given by the base policy is projected into the satisfactory sets so as to satisfy the requirements of all the attributes. Using the PAN, many complicated tasks that are hard to train from scratch can be easily trained; also unseen driving tasks can be solved in a zero-shot manner by assembling the pretrained attribute modules. We have validated the capability of our model on a class of autonomous driving problems with attributes of obstacle avoidance, traffic light and speed limit in simulation. Experimental results based on an obstacle avoidance task are also presented.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Toward Modularization of Neural Network Autonomous Driving Policy Using Parallel Attribute Networks


    Contributors:
    Xu, Zhuo (author) / Chang, Haonan (author) / Tang, Chen (author) / Liu, Changliu (author) / Tomizuka, Masayoshi (author)


    Publication date :

    2019-06-01


    Size :

    1271346 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Subsea assembly modularization

    EIDE ASLE / SÆTHER MORTEN / NESSE HARALD SIGURD et al. | European Patent Office | 2023

    Free access

    SUBSEA ASSEMBLY MODULARIZATION

    EIDE ASLE / SÆTHER MORTEN / NESSE HARALD SIGURD et al. | European Patent Office | 2022

    Free access

    SUBSEA ASSEMBLY MODULARIZATION

    EIDE ASLE / SÆTHER MORTEN / NESSE HARALD SIGURD et al. | European Patent Office | 2022

    Free access


    DETERMINING DRIVING PATHS FOR AUTONOMOUS DRIVING USING PARALLEL PROCESSING

    ZHANG LIANGLIANG / LI DONG / HU JIANGTAO et al. | European Patent Office | 2019

    Free access