This paper introduces a method, based on deep reinforcement learning, for automatically generating a general purpose decision making function. A Deep Q-Network agent was trained in a simulated environment to handle speed and lane change decisions for a truck-trailer combination. In a highway driving case, it is shown that the method produced an agent that matched or surpassed the performance of a commonly used reference model. To demonstrate the generality of the method, the exact same algorithm was also tested by training it for an overtaking case on a road with oncoming traffic. Furthermore, a novel way of applying a convolutional neural network to high level input that represents interchangeable objects is also introduced.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Automated Speed and Lane Change Decision Making using Deep Reinforcement Learning


    Beteiligte:
    Hoel, Carl-Johan (Autor:in) / Wolff, Krister (Autor:in) / Laine, Leo (Autor:in)


    Erscheinungsdatum :

    01.11.2018


    Format / Umfang :

    560462 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Autonomous Lane Change Decision Making Using Different Deep Reinforcement Learning Methods

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





    Lane keeping decision-making method based on deep reinforcement learning

    WANG PENGWEI / ZHOU HENGHENG / GAO SONG et al. | Europäisches Patentamt | 2023

    Freier Zugriff