Autonomous driving is a key focus for future transportation systems, where decision-making in dynamic environments is critical. Current models have difficulty ensuring the safety of decision-making. To address this problem, a humanlike autonomous driving decision-making model is proposed, which incorporates driver style into the deep Q network (DQN) algorithm. First, by simulating different driving styles, the model can optimize decision-making, improve safety, and reduce collision rate. Then, the design of the reward function reflects the characteristics of the driver, and the $\mathbf{Q}$ function weights of DQN are adjusted to consider goal achievement, speed maintenance, safe distance, and time efficiency in highway scenarios. Simulation experiments further verify its potential in optimizing highway driving decisions. And compared with the proximal policy optimization (PPO) algorithm, the proposed model reduces the collision rate by 6.33 % in aggressive driving scenarios.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Human-Like Behavior Decision Making in Autonomous Driving Based on Deep Reinforcement Learning


    Contributors:
    Chen, Ziling (author) / Chi, Cheng (author) / Shen, Jianhao (author) / Wen, Huajie (author) / Xu, Gang (author)


    Publication date :

    2025-03-20


    Size :

    834086 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English




    Human-Like Decision Making and Planning for Autonomous Driving with Reinforcement Learning

    Zong, Ziqi / Shi, Jiamin / Wang, Runsheng et al. | IEEE | 2023




    Automatic driving behavior decision-making method based on deep reinforcement learning

    YANG MINGZHU / LIU XIANGWEI / LI ZHUOLUO | European Patent Office | 2020

    Free access