Self-emerging action gestalts for task segmentation

Authors:
Michael Pardowitz;Jan Steffen;Helge Ritter
Affiliations:
Universität Bielefeld, AG Neuroinformatik;Universität Bielefeld, AG Neuroinformatik;Universität Bielefeld, AG Neuroinformatik
Venue:
KI'09 Proceedings of the 32nd annual German conference on Advances in artificial intelligence
Year:
2009

Citing 4
Cited 1

Learning from observation using primitives

Learning from observation using primitives
Dynamical Stability Conditions for Recurrent Neural Networks with Unsaturating Piecewise Linear Transfer Functions

Neural Computation
A Competitive-Layer Model for Feature Binding and Sensory Segmentation

Neural Computation
Learning lateral interactions for feature binding and sensory segmentation from prototypic basis interactions

IEEE Transactions on Neural Networks

Integrating feature maps and competitive layer architectures for motion segmentation

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

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.