Contact-rich manipulation tasks remain a hard problem in robotics that requires interaction with unstructured environments. Reinforcement Learning (RL) is one potential solution to such problems, as it has been successfully demonstrated on complex continuous control tasks. Nevertheless, current state-of-the-art methods require policy training in simulation to prevent undesired behavior and later domain transfer even for simple skills involving contact. In this paper, we address the problem of learning contact-rich manipulation policies by extending an existing skill-based RL framework with a variable impedance action space. Our method leverages a small set of suboptimal demonstration trajectories and learns from both position, 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 deployed directly on the real robot, without resorting to learning in simulation.


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Variable Impedance Skill Learning for Contact-Rich Manipulation


    Beteiligte:
    Yang, Quantao (Autor:in) / Dürr, Alexander (Autor:in) / Topp, Elin Anna (Autor:in) / Stork, Johannes A. (Autor:in) / Stoyanov, Todor (Autor:in)

    Erscheinungsdatum :

    2022-01-01


    Anmerkungen:

    Scopus 2-s2.0-85133737407



    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Klassifikation :

    DDC:    629



    Deformation-Aware Contact-Rich Manipulation Skills Learning and Compliant Control

    Si, Weiyong / Guo, Cheng / Dong, Jiale et al. | Springer Verlag | 2023


    Safe Data-Driven Contact-Rich Manipulation

    Mitsioni, Ioanna / Tajvar, Pouria / Kragic, Danica et al. | BASE | 2020

    Freier Zugriff

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

    Yang, Quantao / Dürr, Alexander / Topp, Elin Anna et al. | BASE | 2021

    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

    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