Methods for learning control policies from variable-constraint demonstrations

M. Howard, S. Klanke, M. Gienger, C. Goerick, S. Vijayakumar

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Many everyday human skills can be framed in terms of performing some task subject to constraints imposed by the task or the environment. Constraints are usually not observable and frequently change between contexts. In this chapter, we explore the problem of learning control policies from data containing variable, dynamic and non-linear constraints on motion. We discuss how an effective approach for doing this is to learn the unconstrained policy in a way that is consistent with the constraints. We then go on to discuss several recent algorithms for extracting policies from movement data, where observations are recorded under variable, unknown constraints. We review a number of experiments testing the performance of these algorithms and demonstrating how the resultant policy models generalise over constraints allowing prediction of behaviour under unseen settings where new constraints apply.
Original languageEnglish
Title of host publicationFrom Motor Learning to Interaction Learning in Robots
PublisherSpringer-Verlag GmbH
Pages253-291
Number of pages39
ISBN (Print)978-3-642-05180-7
DOIs
Publication statusPublished - 2010

Publication series

NameStudies in Computational Intelligence
PublisherSpringer Berlin / Heidelberg
Volume264
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Fingerprint

Dive into the research topics of 'Methods for learning control policies from variable-constraint demonstrations'. Together they form a unique fingerprint.

Cite this