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.


    Access

    Download


    Export, share and cite



    Title :

    Variable Impedance Skill Learning for Contact-Rich Manipulation


    Contributors:

    Publication date :

    2022-01-01


    Remarks:

    Scopus 2-s2.0-85133737407



    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Safe Data-Driven Contact-Rich Manipulation

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

    Free access

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

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


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

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

    Free access

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

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

    Free access

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

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

    Free access