<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Learning by demonstration is a natural approach that can be used to build a robot’s task repertoire. In this paper we propose an algorithm that enables a learner to generalize a task representation from a small number of demonstrations of the same task. The algorithm can generalize a wide range of situations that typically occur in daily tasks. The paper also describes the supporting representation that we use in order to encode the generalized representation. The approach is validated with experimental results on a broad range of generalizations.</p></abstract>

Learning by demonstration is a natural approach that can be used to build a robot’s task repertoire. In this paper we propose an algorithm that enables a learner to generalize a task representation from a small number of demonstrations of the same task. The algorithm can generalize a wide range of situations that typically occur in daily tasks. The paper also describes the supporting representation that we use in order to encode the generalized representation. The approach is validated with experimental results on a broad range of generalizations.

Learning to Generalize from Demonstrations

University of Nevada, Reno, NV 89557, USA

Cybernetics and Information Technologies

{"article-title":"Learning to Generalize from Demonstrations"}

Learning by demonstration is a natural approach that can be used to build a robot’s task repertoire. In this paper we propose an algorithm that enables a...

Learning to Generalize from Demonstrations

Online veröffentlicht: 22. März 2013

Seitenbereich: 27 - 38

DOI: https://doi.org/10.2478/cait-2012-0019

Schlüsselwörter
Learning by Demonstration, Generalized Representation, Graph Task Representation, Behavior Graphs, Robotics

This content is open access.

Learning to Generalize from Demonstrations

Online veröffentlicht: 22. März 2013

Seitenbereich: 27 - 38

DOI: https://doi.org/10.2478/cait-2012-0019

SchlüsselwörterLearning by Demonstration, Generalized Representation, Graph Task Representation, Behavior Graphs, Robotics

This content is open access.

Schlüsselwörter
Learning by Demonstration, Generalized Representation, Graph Task Representation, Behavior Graphs, Robotics