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.

Download
OA
Conference Paper | Published | English
Abstract
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
Publishing Year
Conference
HUMANOIDS
PUB-ID

Cite this

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.
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.
Main File(s)
Access Level
OA Open Access
Last Uploaded
2011-06-16 10:11:27

This data publication is cited in the following publications:
This publication cites the following data publications:

Export

0 Marked Publications

Open Data PUB

Search this title in

Google Scholar