We present a control approach for autonomous vehicles based on deep reinforcement learning. A neural network agent is trained to map its estimated state to acceleration and steering commands given the objective of reaching a specific target state while considering detected obstacles. Learning is performed using state-of-the-art proximal policy optimization in combination with a simulated environment. Training from scratch takes five to nine hours. The resulting agent is evaluated within simulation and subsequently applied to control a full-size research vehicle. For this, the autonomous exploration of a parking lot is considered, including turning maneuvers and obstacle avoidance. Altogether, this work is among the first examples to successfully apply deep reinforcement learning to a real vehicle.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Controlling an Autonomous Vehicle with Deep Reinforcement Learning


    Contributors:


    Publication date :

    2019-06-01


    Size :

    1998098 byte





    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    CONTROLLING AN AUTONOMOUS VEHICLE WITH DEEP REINFORCEMENT LEARNING

    Folkers, Andreas / Rick, Matthias / Büskens, Christof | British Library Conference Proceedings | 2019


    Autonomous vehicle navigation with deep reinforcement learning

    Cabañeros López, Àlex | BASE | 2019

    Free access

    Autonomous Vehicle Simulation Using Deep Reinforcement Learning

    Kadam, Rishikesh / Vidhani, Vishakha / Valecha, Bhavika et al. | TIBKAT | 2021


    Autonomous Vehicle Driving Path Control with Deep Reinforcement Learning

    Tiong, Teckchai / Saad, Ismail / Teo, Kenneth Tze Kin et al. | IEEE | 2023


    Deep reinforcement learning-based vehicle energy efficiency autonomous learning system

    Qi, Xuewei / Luo, Yadan / Wu, Guoyuan et al. | IEEE | 2017