Reinforcement learning is a machine learning method particularly interesting for the autonomous driving domain, as it enables autopilot training without the need for large and expensive amounts of manually labeled training data. Instead, agents are trained by evaluating the effects of their actions and punishing or rewarding them accordingly. In autonomous and particularly cooperative driving a core problem is however that multiple vehicles need to be trained in parallel while having an impact on each other's behavior. In this paper, we present a simulation solution providing cooperative training capabilities out-of-the-box and compare the quality of the resulting autopilots in an intersection scenario.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    MontiSim: Agent-Based Simulation for Reinforcement Learning of Autonomous Driving


    Beteiligte:
    Hofer, Tristan (Autor:in) / Hoppe, Mattis (Autor:in) / Kusmenko, Evgeny (Autor:in) / Rumpe, Bernhard (Autor:in)


    Erscheinungsdatum :

    2023-09-24


    Format / Umfang :

    368809 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Autonomous Driving with Deep Reinforcement Learning

    Zhu, Yuhua / Technische Universität Dresden | SLUB | 2023


    DQN-Based Deep Reinforcement Learning for Autonomous Driving

    Pérez-Gil, Óscar / Barea, Rafael / López-Guillén, Elena et al. | Springer Verlag | 2020


    Synthesizing Data for Autonomous Driving: Multi-Agent Reinforcement Learning Meets Augmented Reality

    Meng, Chao / Wang, Hanchao / Mei, Jinren et al. | SAE Technical Papers | 2023


    Reinforcement Learning Based Parking Space Egress for Autonomous Driving

    Theerthala, Raghu Ram / A R, Vimal Kumar | SAE Technical Papers | 2024


    REINFORCEMENT LEARNING-BASED AUTONOMOUS DRIVING DEVICE AND METHOD THEREFOR

    JANG HWANCHOL / LEE DONG HYUK / CHUN TAE YOON et al. | Europäisches Patentamt | 2022

    Freier Zugriff