elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Impressum | Datenschutz | Kontakt | English
Schriftgröße: [-] Text [+]

Online task segmentation by merging symbolic and data-driven skill recognition during kinesthetic teaching

Eiband, Thomas und Liebl, Johanna und Willibald, Christoph und Lee, Dongheui (2023) Online task segmentation by merging symbolic and data-driven skill recognition during kinesthetic teaching. Robotics and Autonomous Systems, 162, Seite 104367. Elsevier. doi: 10.1016/j.robot.2023.104367. ISSN 0921-8890.

[img] PDF - Verlagsversion (veröffentlichte Fassung)
2MB

Offizielle URL: https://www.sciencedirect.com/science/article/pii/S0921889023000064

Kurzfassung

Programming by Demonstration (PbD) is used to transfer a task from a human teacher to a robot, where it is of high interest to understand the underlying structure of what has been demonstrated. Such a demonstrated task can be represented as a sequence of so-called actions or skills. This work focuses on the recognition part of the task transfer. We propose a framework that recognizes skills online during a kinesthetic demonstration by means of position and force-torque (wrench) sensing. Therefore, our framework works independently of visual perception. The recognized skill sequence constitutes a task representation that lets the user intuitively understand what the robot has learned. The skill recognition algorithm combines symbolic skill segmentation, which makes use of pre- and post-conditions, and data-driven prediction, which uses support vector machines for skill classification. This combines the advantages of both techniques, which is inexpensive evaluation of symbols and usage of data-driven classification of complex observations. The framework is thus able to detect a larger variety of skills, such as manipulation and force-based skills that can be used in assembly tasks. The applicability of our framework is proven in a user study that achieves a 96% accuracy in the online skill recognition capabilities and highlights the benefits of the generated task representation in comparison to a baseline representation. The results show that the task load could be reduced, trust and explainability could be increased, and, that the users were able to debug the robot program using the generated task representation.

elib-URL des Eintrags:https://elib.dlr.de/194567/
Dokumentart:Zeitschriftenbeitrag
Titel:Online task segmentation by merging symbolic and data-driven skill recognition during kinesthetic teaching
Autoren:
AutorenInstitution oder E-Mail-AdresseAutoren-ORCID-iDORCID Put Code
Eiband, ThomasThomas.Eiband (at) dlr.deNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Liebl, JohannaTechnical University of MunichNICHT SPEZIFIZIERTNICHT SPEZIFIZIERT
Willibald, ChristophChristoph.Willibald (at) dlr.dehttps://orcid.org/0000-0003-3579-4130NICHT SPEZIFIZIERT
Lee, DongheuiDongheui.Lee (at) dlr.dehttps://orcid.org/0000-0003-1897-7664NICHT SPEZIFIZIERT
Datum:20 Januar 2023
Erschienen in:Robotics and Autonomous Systems
Referierte Publikation:Ja
Open Access:Ja
Gold Open Access:Nein
In SCOPUS:Ja
In ISI Web of Science:Ja
Band:162
DOI:10.1016/j.robot.2023.104367
Seitenbereich:Seite 104367
Verlag:Elsevier
ISSN:0921-8890
Status:veröffentlicht
Stichwörter:Learning from demonstration Programming by demonstration Robot Symbolic Subsymbolic Data-driven Task segmentation Action segmentation Skill recognition Task representation Interactive robot programming Intuitive robot programming Force-based Tactile Online segmentation Kinesthetic teaching
HGF - Forschungsbereich:Luftfahrt, Raumfahrt und Verkehr
HGF - Programm:Raumfahrt
HGF - Programmthema:Robotik
DLR - Schwerpunkt:Raumfahrt
DLR - Forschungsgebiet:R RO - Robotik
DLR - Teilgebiet (Projekt, Vorhaben):R - Autonome, lernende Roboter [RO]
Standort: Oberpfaffenhofen
Institute & Einrichtungen:Institut für Robotik und Mechatronik (ab 2013) > Leitungsbereich
Hinterlegt von: Geyer, Günther
Hinterlegt am:31 Mär 2023 12:11
Letzte Änderung:26 Mär 2024 13:13

Nur für Mitarbeiter des Archivs: Kontrollseite des Eintrags

Blättern
Suchen
Hilfe & Kontakt
Informationen
electronic library verwendet EPrints 3.3.12
Gestaltung Webseite und Datenbank: Copyright © Deutsches Zentrum für Luft- und Raumfahrt (DLR). Alle Rechte vorbehalten.