DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

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

Kulkarni, Padmaja and Kober, Jens and Babuška, Robert and Della Santina, Cosimo (2021) Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning. Advanced Intelligent Systems, 4 (1). Wiley. doi: 10.1002/aisy.202100095. ISSN 2640-4567.

[img] PDF - Published version

Official URL: https://dx.doi.org/10.1002/aisy.202100095


Adapting to uncertainties is essential yet challenging for robots while conducting assembly tasks in real-world scenarios. Reinforcement learning (RL) methods provide a promising solution for these cases. However, training robots with RL can be a data-extensive, time-consuming, and potentially unsafe process. In contrast, classical control strategies can have near-optimal performance without training and be certifiably safe. However, this is achieved at the cost of assuming that the environment is known up to small uncertainties. Herein, an architecture aiming at getting the best out of the two worlds, by combining RL and classical strategies so that each one deals with the right portion of the assembly problem, is proposed. A time-varying weighted sum combines a recurrent RL method with a nominal strategy. The output serves as the reference for a task space impedance controller. The proposed approach can learn to insert an object in a frame within a few minutes of real-world training. A success rate of 94% in the presence of considerable uncertainties is observed. Furthermore, the approach is robust to changes in the experimental setup and task, even when no retrain is performed. For example, the same policy achieves a success rate of 85% when the object properties change.

Item URL in elib:https://elib.dlr.de/193634/
Document Type:Article
Title:Learning Assembly Tasks in a Few Minutes by Combining Impedance Control and Residual Recurrent Reinforcement Learning
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Kulkarni, PadmajaDelft University of TechnologyUNSPECIFIEDUNSPECIFIED
Kober, JensUNSPECIFIEDhttps://orcid.org/0000-0001-7257-5434UNSPECIFIED
Babuška, RobertDelft University of TechnologyUNSPECIFIEDUNSPECIFIED
Della Santina, CosimoUNSPECIFIEDhttps://orcid.org/0000-0003-1067-1134UNSPECIFIED
Date:2 September 2021
Journal or Publication Title:Advanced Intelligent Systems
Refereed publication:Yes
Open Access:Yes
Gold Open Access:Yes
In ISI Web of Science:Yes
Keywords:impedance control; reinforcement learning
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Robotics
DLR - Research area:Raumfahrt
DLR - Program:R RO - Robotics
DLR - Research theme (Project):R - Robot Dynamics & Simulation [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Analysis and Control of Advanced Robotic Systems
Institute of Robotics and Mechatronics (since 2013)
Deposited By: Strobl, Dr. Klaus H.
Deposited On:28 Jan 2023 12:04
Last Modified:30 Jan 2023 07:56

Repository Staff Only: item control page

Help & Contact
electronic library is running on EPrints 3.3.12
Website and database design: Copyright © German Aerospace Center (DLR). All rights reserved.