Machine learning techniques have been shown to outperform many rule-based systems for the decision-making of autonomous vehicles. However, applying machine learning is challenging due to the possibility of executing unsafe actions and slow learning rates. We address these issues by presenting a reinforcement learning-based approach, which is combined with formal safety verification to ensure that only safe actions are chosen at any time. We let a deep reinforcement learning (RL) agent learn to drive as close as possible to a desired velocity by executing reasonable lane changes on simulated highways with an arbitrary number of lanes. By making use of a minimal state representation, consisting of only 13 continuous features, and a Deep Q-Network (DQN), we are able to achieve fast learning rates. Our RL agent is able to learn the desired task without causing collisions and outperforms a complex, rule-based agent that we use for benchmarking.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    High-level Decision Making for Safe and Reasonable Autonomous Lane Changing using Reinforcement Learning


    Contributors:


    Publication date :

    2018-11-01


    Size :

    1839818 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Safe Reinforcement Learning for Autonomous Lane Changing Using Set-Based Prediction

    Krasowski, Hanna / Wang, Xiao / Althoff, Matthias | IEEE | 2020


    Autonomous Lane Change Decision Making Using Different Deep Reinforcement Learning Methods

    Feng, Xidong / Hu, Jianming / Huo, Yusen et al. | ASCE | 2019




    Lane changing decision-making method for autonomous vehicle

    YUE WEIQI / ZHENG PENGJUN / HOU JIAWEI et al. | European Patent Office | 2024

    Free access