Reinforcement learning (RL) can be used to design smart driving policies in complex situations where traditional methods cannot. However, they are frequently black-box in nature, and the resulting policy may perform poorly, including in scenarios where few training cases are available. In this paper, we propose a method to use RL under two conditions: (i) RL works together with a baseline rule-based driving policy; and (ii) the RL intervenes only when the rule-based method seems to have difficulty handling and when the confidence of the RL policy is high. Our motivation is to use a not-well trained RL policy to reliably improve AV performance. The confidence of the policy is evaluated by Lindeberg-Levy Theorem using the recorded data distribution in the training process. The overall framework is named “confidence-aware reinforcement learning” (CARL). The condition to switch between the RL policy and the baseline policy is analyzed and presented. Driving in a two-lane roundabout scenario is used as the application case study. Simulation results show the proposed method outperforms the pure RL policy and the baseline rule-based policy.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Confidence-Aware Reinforcement Learning for Self-Driving Cars


    Contributors:
    Cao, Zhong (author) / Xu, Shaobing (author) / Peng, Huei (author) / Yang, Diange (author) / Zidek, Robert (author)


    Publication date :

    2022-07-01


    Size :

    3290906 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    HYBRID ONLINE POMDP PLANNING AND DEEP REINFORCEMENT LEARNING FOR SAFER SELF-DRIVING CARS

    Pusse, Florian / Klusch, Matthias | British Library Conference Proceedings | 2019




    SELF DRIVING CARS

    KIM SI HYEONG / HAN YURIM / YEON HEE LEE et al. | European Patent Office | 2022

    Free access

    SELF DRIVING CARS

    European Patent Office | 2022

    Free access