Abstract
Task segmentation from user demonstrations is an often neglected component of robot programming by demonstration (PbD) systems. This paper presents an approach to the segmentation problem motivated by psychological findings of gestalt theory. It assumes the existence of certain “action gestalts” that correspond to basic actions a human performs. Unlike other approaches, the set of elementary actions is not prespecified, but is learned in a self-organized way by the system.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
Arsenio, A.M.: Learning task sequences from scratch: applications to the control of tools and toys by a humanoid robot. In: CCA, vol. 1, pp. 400–405 (2004)
Bentivegna, D.C.: Learning from Observation Using Primitives. PhD thesis, Georgia Institute of Technology (July 2004)
Calinon, S., Guenter, F., Billard, A.: On learning the statistical representation of a task and generalizing it to various contexts. In: ICRA (2006)
Ehrenmann, M., Zöllner, R., Rogalla, O., Vacek, S., Dillmann, R.: Observation in programming by demonstration: Training and exection environment. In: HUMANOIDS (2003)
Immersion. CyberGlove II Wireless Glove (2009)
Pardowitz, M., Haschke, R., Steil, J., Ritter, H.: Gestalt-Based Action Segmentation for Robot Task Learning. In: HUMANOIDS (2008)
Weng, S., Wersing, H., Steil, J., Ritter, H.: Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions. IEEE TNN 17(4), 843–863 (2006)
Wersing, H., Beyn, W.-J., Ritter, H.: Dynamical stability conditions for recurrent neural networks with unsaturating piecewise linear transfer functions. Neural Comput. 13(8), 1811–1825 (2001)
Wersing, H., Steil, J.J., Ritter, H.J.: A competitive-layer model for feature binding and sensory segmentation. Neural Computation 13(2), 357–387 (2001)
Zöllner, R., Asfour, T., Dillmann, R.: Programming by demonstration: Dual-arm manipulation tasks for humanoid robots. In: IROS (2004)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2009 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Pardowitz, M., Steffen, J., Ritter, H. (2009). Self-emerging Action Gestalts for Task Segmentation. In: Mertsching, B., Hund, M., Aziz, Z. (eds) KI 2009: Advances in Artificial Intelligence. KI 2009. Lecture Notes in Computer Science(), vol 5803. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-04617-9_74
Download citation
DOI: https://doi.org/10.1007/978-3-642-04617-9_74
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-04616-2
Online ISBN: 978-3-642-04617-9
eBook Packages: Computer ScienceComputer Science (R0)