Multi-task long-range autonomous driving in urban areas is a challenging task. Traditional methods are not applicable to situations with high-dimensional observations. Current reinforcement learning (RL) based algorithms are able to train agents to utilize high-dimensional signals for vehicle control and accomplish short-range tasks. However, current RL methods do not work well on multi-task long-range urban driving tasks. In this paper, we propose a novel Hierarchical-planning and Spatial-encoding-based Multi-task Reinforcement Learning (HSMRL) model for the autonomous driving problem in urban areas. For long-range tasks, global routes are planned in real-time based on the A* algorithm, and short-range tasks are constructed based on the global routes, through which the short-range tasks are regarded as sub-tasks of long-range tasks. Then the short-range task information is efficiently encoded using spatial encoding, and the short-range tasks are accomplished by RL algorithms. We also prove that under our settings, multiple autonomous driving tasks are capable of training a shared policy. Experiments show that our method can stably accomplish the multi-task long-range driving tasks and performs significantly better than the state-of-the-art methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Multi-Task Long-Range Urban Driving Based on Hierarchical Planning and Reinforcement Learning


    Contributors:
    Zhang, Xiaoqin (author) / Wu, Mouyu (author) / Ma, Huimin (author) / Hu, Tianyu (author) / Yuan, Jian (author)


    Publication date :

    2021-09-19


    Size :

    1160859 byte




    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Urban Driving with Multi-Objective Deep Reinforcement Learning

    Li, Changjian / Czarnecki, Krzysztof | ArXiv | 2018

    Free access

    Multi-lane Cruising Using Hierarchical Planning and Reinforcement Learning

    Rezaee, Kasra / Yadmellat, Peyman / Nosrati, Masoud S. et al. | IEEE | 2019




    Parking task allocation and trajectory planning system based on multi-agent reinforcement learning

    WANG MEILING / CHEN SIYUAN / SONG WENJIE et al. | European Patent Office | 2023

    Free access