Learning Potential-based Policies from Constrained Motion

Matthew Howard, Stefan Klanke, Michael Gienger, Christian Goerick, Sethu Vijayakumar

Research output: Chapter in Book/Report/Conference proceedingConference paper

6 Citations (Scopus)

Abstract

We present a method for learning potential-based policies from constrained motion data. In contrast to previous approaches to direct policy learning, our method can combine observations from a variety of contexts where different constraints are in force, to learn the underlying unconstrained policy in form of its potential function. This allows us to generalise and predict behaviour where novel constraints apply. As a key ingredient, we first create multiple simple local models of the potential, and align those using an efficient algorithm. We can then detect and discard unsuitable subsets of the data and learn a global model from a cleanly pre-processed training set. We demonstrate our approach on systems of varying complexity, including kinematic data from the ASIMO humanoid robot with 22 degrees of freedom.
Original languageEnglish
Title of host publicationHumanoids 2008. 8th IEEE-RAS International Conference on Humanoid Robots, 2008
PublisherIEEE
Pages714-735
Number of pages22
ISBN (Print)978-1-4244-2821-2
DOIs
Publication statusPublished - 2008

Fingerprint

Dive into the research topics of 'Learning Potential-based Policies from Constrained Motion'. Together they form a unique fingerprint.

Cite this