Gestalt-Based Action Segmentation for Robot Task Learning

Pardowitz M, Haschke R, Steil JJ, Ritter H (2008)
In: IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS). 347-352.

Konferenzbeitrag | Veröffentlicht | Englisch
 
Download
OA
Abstract / Bemerkung
In Programming by Demonstration (PbD) systems, the problem of task segmentation and task decomposition has not been addressed with satisfactory attention. In this article we propose a method relying on psychological gestalt theories originally developed for visual perception and apply it to the domain of action segmentation. We propose a computational model for gestalt-based segmentation called Competitive Layer Model (CLM). The CLM relies on features mutually supporting or inhibiting each other to form segments by competition. We analyze how gestalt laws for actions can be learned from human demonstrations and how they can be beneficial to the CLM segmentation method. We validate our approach with two reported experiments on action sequences and present the results obtained from those experiments
Stichworte
CoR-Lab Publication
Erscheinungsjahr
2008
Titel des Konferenzbandes
IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS)
Seite(n)
347-352
Konferenz
HUMANOIDS
Page URI
https://pub.uni-bielefeld.de/record/1996821

Zitieren

Pardowitz M, Haschke R, Steil JJ, Ritter H. Gestalt-Based Action Segmentation for Robot Task Learning. In: IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS). 2008: 347-352.
Pardowitz, M., Haschke, R., Steil, J. J., & Ritter, H. (2008). Gestalt-Based Action Segmentation for Robot Task Learning. IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS), 347-352. doi:10.1109/ICHR.2008.4756003
Pardowitz, M., Haschke, R., Steil, J. J., and Ritter, H. (2008). “Gestalt-Based Action Segmentation for Robot Task Learning” in IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS) 347-352.
Pardowitz, M., et al., 2008. Gestalt-Based Action Segmentation for Robot Task Learning. In IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS). pp. 347-352.
M. Pardowitz, et al., “Gestalt-Based Action Segmentation for Robot Task Learning”, IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS), 2008, pp.347-352.
Pardowitz, M., Haschke, R., Steil, J.J., Ritter, H.: Gestalt-Based Action Segmentation for Robot Task Learning. IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS). p. 347-352. (2008).
Pardowitz, Michael, Haschke, Robert, Steil, Jochen J., and Ritter, Helge. “Gestalt-Based Action Segmentation for Robot Task Learning”. IEEE-RAS 7th International Conference on Humanoid Robots (HUMANOIDS). 2008. 347-352.
Alle Dateien verfügbar unter der/den folgenden Lizenz(en):
Copyright Statement:
This Item is protected by copyright and/or related rights. [...]
Volltext(e)
Access Level
OA Open Access
Zuletzt Hochgeladen
2019-09-06T08:57:17Z
MD5 Prüfsumme
12a5c721422ee1facc210b60c0109a2e

Export

Markieren/ Markierung löschen
Markierte Publikationen

Open Data PUB

Suchen in

Google Scholar