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

Closing the Gap: Combining Task Specification and Reinforcement Learning for Compliant Vegetable Cutting

Padalkar, Abhishek and Nieuwenhuisen, Matthias and Schulz, Dirk and Stulp, Freek (2022) Closing the Gap: Combining Task Specification and Reinforcement Learning for Compliant Vegetable Cutting. In: International Conference on Informatics in Control, Automation and Robotics Lecture Notes in Electrical Engineering, 793. Springer. pp. 187-206. doi: 10.1007/978-3-030-92442-3_11. ISBN 978-3-030-92441-6. ISSN 1876-1100.

[img] PDF - Only accessible within DLR - Published version
2MB

Official URL: https://link.springer.com/chapter/10.1007/978-3-030-92442-3_11

Abstract

Easy-to-define but flexible behaviors are key to the successful deployment of service robots in more everyday situations. Complex modeling of the world dynamics is infeasible outside of very controlled environments like manufacturing cells. Learning new behaviors has the advantage of a high flexibility, but comes at the price of prohibitively many learning iterations when applied on a real robot system. We combine learning with a simple task specification to guide the learning process with human knowledge about the problem. As application, we demonstrate a compliant manipulation task using reinforcement learning guided by the Task Frame Formalism. This allows us to specify the easy to model knowledge about a task while the robot learns the unmodeled components by reinforcement learning. We evaluate the approach by cutting vegetables with a KUKA LWR 4+ manipulator. The robot was able to learn force control policies directly on the robot without using any simulation.

Item URL in elib:https://elib.dlr.de/185811/
Document Type:Contribution to a Collection
Title:Closing the Gap: Combining Task Specification and Reinforcement Learning for Compliant Vegetable Cutting
Authors:
AuthorsInstitution or Email of AuthorsAuthor's ORCID iDORCID Put Code
Padalkar, AbhishekUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Nieuwenhuisen, MatthiasUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Schulz, DirkUNSPECIFIEDUNSPECIFIEDUNSPECIFIED
Stulp, FreekUNSPECIFIEDhttps://orcid.org/0000-0001-9555-9517UNSPECIFIED
Date:1 January 2022
Journal or Publication Title:International Conference on Informatics in Control, Automation and Robotics
Refereed publication:Yes
Open Access:No
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Volume:793
DOI:10.1007/978-3-030-92442-3_11
Page Range:pp. 187-206
Publisher:Springer
Series Name:Lecture Notes in Electrical Engineering
ISSN:1876-1100
ISBN:978-3-030-92441-6
Status:Published
Keywords:Compliant manipulation, Reinforcement learning, Task frame formalism
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 - Autonomous learning robots [RO]
Location: Oberpfaffenhofen
Institutes and Institutions:Institute of Robotics and Mechatronics (since 2013) > Cognitive Robotics
Deposited By: Padalkar, Abhishek
Deposited On:07 Jul 2022 16:26
Last Modified:20 Oct 2023 07:24

Repository Staff Only: item control page

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