Reinforcement Learning (RL) has the potential of solving complex continuous control tasks, with direct applications to robotics. Nevertheless, current state-of-the-art methods are generally unsafe to learn directly on a physical robot as exploration by trial-and-error can cause harm to the real world systems. In this paper, we leverage a framework for learning latent action spaces for RL agents from demonstrated trajectories. We extend this framework by connecting it to a variable impedance Cartesian space controller, allowing us to learn contact-rich tasks safely and efficiently. Our method learns from trajectories that incorporate both positional, but also crucially impedance-space information. We evaluate our method on a number of peg-in-hole task variants with a Franka Panda arm and demonstrate that learning variable impedance actions for RL in Cartesian space can be safely deployed on the real robot directly, without resorting to learning in simulation and a subsequent policy transfer.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Learning Impedance Actions for Safe Reinforcement Learning in Contact-Rich Tasks


    Beteiligte:

    Erscheinungsdatum :

    2021-01-01


    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    A review on reinforcement learning for contact-rich robotic manipulation tasks

    Elguea-Aguinaco, Íñigo / Serrano-Muñoz, Antonio / Chrysostomou, Dimitrios et al. | BASE | 2022

    Freier Zugriff

    A review on reinforcement learning for contact-rich robotic manipulation tasks

    Elguea, Íñigo / Arana-Arexolaleiba, Nestor / Serrano Muñoz, Antonio | BASE | 2023

    Freier Zugriff

    Variable Impedance Skill Learning for Contact-Rich Manipulation

    Yang, Quantao / Dürr, Alexander / Topp, Elin Anna et al. | BASE | 2022

    Freier Zugriff

    Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning

    Kulkarni, Padmaja / Kober, Jens / Babuška, Robert et al. | Deutsches Zentrum für Luft- und Raumfahrt (DLR) | 2021

    Freier Zugriff

    Reinforcement learning for robotic assisted tasks

    Civit Bertran, Aniol | BASE | 2020

    Freier Zugriff