Developing and testing automated driving models in the real world might be challenging and even dangerous, while simulation can help with this, especially for challenging maneuvers. Deep reinforcement learning (DRL) has the potential to tackle complex decision-making and controlling tasks through learning and interacting with the environment, thus it is suitable for developing automated driving while not being explored in detail yet. This study carried out a comprehensive study by implementing, evaluating, and comparing the two DRL algorithms, Deep Q-networks (DQN) and Trust Region Policy Optimization (TRPO), for training automated driving on the highway-env simulation platform. Effective and customized reward functions were developed and the implemented algorithms were evaluated in terms of onlane accuracy (how well the car drives on the road within the lane), efficiency (how fast the car drives), safety (how likely the car is to crash into obstacles), and comfort (how much the car makes jerks, e.g., suddenly accelerates or brakes). Results show that the TRPO-based models with modified reward functions delivered the best performance in most cases. Furthermore, to train a uniform driving model that can tackle various driving maneuvers besides the specific ones, this study expanded the highway-env and developed an extra customized training environment, namely, ComplexRoads, integrating various driving maneuvers and multiple road scenarios together. Models trained on the designed ComplexRoads environment can adapt well to other driving maneuvers with promising overall performance. Lastly, several functionalities were added to the highway-env to implement this work. The codes are open on GitHub at https://github.com/alaineman/drlcarsim-paper.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Comprehensive Training and Evaluation on Deep Reinforcement Learning for Automated Driving in Various Simulated Driving Maneuvers


    Beteiligte:
    Dong, Yongqi (Autor:in) / Datema, Tobias (Autor:in) / Wassenaar, Vincent (Autor:in) / Van de Weg, Joris (Autor:in) / Kopar, Cahit Tolga (Autor:in) / Suleman, Harim (Autor:in)


    Erscheinungsdatum :

    2023-09-24


    Format / Umfang :

    449187 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Overtaking Maneuvers in Simulated Highway Driving using Deep Reinforcement Learning

    Kaushik, Meha / Prasad, Vignesh / Krishna, K Madhava et al. | IEEE | 2018


    Data-driven Deep Reinforcement Learning for Automated Driving

    Prabu, Avinash / Li, Lingxi / Chen, Yaobin et al. | IEEE | 2023


    SYSTEM FOR SELECTING DRIVING MANEUVERS OF A VEHICLE FOR AUTOMATED DRIVING

    MATHE BENJAMIN / WENZEL KATRIN / VON BYCHOWSKI HEIDI et al. | Europäisches Patentamt | 2019

    Freier Zugriff

    System for selecting driving maneuvers of a vehicle for automated driving

    MATHE BENJAMIN / WENZEL KATRIN / VON BYCHOWSKI HEIDI et al. | Europäisches Patentamt | 2020

    Freier Zugriff

    Online intention recognition applied to real simulated driving maneuvers

    Deng, Qi / Saleh, Maryam / Tanshi, Foghor et al. | IEEE | 2020