Abstract In the realm of autonomous vehicular systems, there has been a notable increase in end-to-end algorithms designed for complete self-navigation. Researchers are increasingly applying hierarchical reinforcement learning to autonomous driving tasks to address the rising challenges. This study proposes a novel hierarchical reinforcement learning approach that facilitates the training of sub-networks without the need for manual reward design. First, unsupervised reinforcement learning is used to train skills without predefined rewards. These skills are subsequently integrated as sub-policies in the hierarchical reinforcement learning framework to train the meta-controller, which synthesizes these skills to autonomously execute driving tasks in complex scenarios. This training strategy encapsulates the accumulated knowledge into skills, enhancing the transferability and efficiency of learning for similar tasks compared to traditional reinforcement learning methods. Additionally, compared with general hierarchical reinforcement learning, this method does not need to design rewards for each sub-policy, allowing for an indefinite expansion of diverse sub-strategies, which may potentially yield superior performance in a range of tasks.

    Highlights Skill-based hierarchical reinforcement learning applied to autonomous driving. Unsupervised reinforcement learning trains autonomous driving skills without predefined rewards. Transformer model learns multi-frame skills, enhancing semantics and interpretability.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Integrating big data analytics in autonomous driving: An unsupervised hierarchical reinforcement learning approach


    Contributors:
    Mao, Zhiqi (author) / Liu, Yang (author) / Qu, Xiaobo (author)


    Publication date :

    2024-03-30




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English




    Deep Hierarchical Reinforcement Learning for Autonomous Driving with Distinct Behaviors

    Chen, Jianyu / Wang, Zining / Tomizuka, Masayoshi | IEEE | 2018


    Hierarchical Reinforcement Learning Approach for Autonomous Cross-Country Soaring

    Notter, Stefan / Schimpf, Fabian / Müller, Gregor et al. | AIAA | 2022


    HIERARCHICAL REINFORCEMENT LEARNING APPROACH TOWARDS AUTONOMOUS CROSS-COUTRY SOARING

    Notter, Stefan / Schimpf, Fabian / Fichter, Walter | TIBKAT | 2021


    Hierarchical Reinforcement Learning Approach Towards Autonomous Cross-Country Soaring

    Notter, Stefan / Schimpf, Fabian / Fichter, Walter | AIAA | 2021