Automated lane change is one of the most challenging task to be solved of highly automated vehicles due to its safety-critical, uncertain and multi-agent nature. This paper presents the novel deployment of the state of art $\mathbf{Q}$ learning method, namely Rainbow DQN, that uses a new safety driven rewarding scheme to tackle the issues in an dynamic and uncertain simulation environment. We present various comparative results to show that our novel approach of having reward feedback from the safety layer dramatically increases both the agent's performance and sample efficiency. Furthermore, through the novel deployment of Rainbow DQN, it is shown that more intuition about the agent's actions is extracted by examining the distributions of generated $\mathbf{Q}$ values of the agents. The proposed algorithm shows superior performance to the baseline algorithm in the challenging scenarios with only 200000 training steps (i.e. equivalent to 55 hours driving).


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    A New Approach for Tactical Decision Making in Lane Changing: Sample Efficient Deep Q Learning with a Safety Feedback Reward


    Contributors:


    Publication date :

    2020-10-19


    Size :

    726852 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    A NEW APPROACH FOR TACTICAL DECISION MAKING IN LANE CHANGING: SAMPLE EFFICIENT DEEP Q LEARNING WITH A SAFETY FEEDBACK REWARD

    Yavas, Ugur / Kumbasar, Tufan / Ure, Nazim Kemal | British Library Conference Proceedings | 2020


    Evolutionary Learning in Decision Making for Tactical Lane Changing

    Li, Tingting / Wu, Jianping / Chan, Ching-Yao | IEEE | 2019


    Vehicle lane changing decision-making method

    HOU DANYI / LIU QI / LI JIE et al. | European Patent Office | 2023

    Free access

    Hybrid automatic driving lane changing decision-making method based on deep reinforcement learning

    LIANG SHANSHAN / ZHANG JIE / CHEN CHONGCHONG et al. | European Patent Office | 2024

    Free access