English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning Operational Space Control

Peters, J., & Schaal, S. (2007). Learning Operational Space Control. In G. Sukhatme, S. Schaal, W. Burgard, & D. Fox (Eds.), Robotics: Science and Systems II (pp. 255-262). Cambridge, MA, USA: MIT Press.

Item is

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Peters, J1, Author              
Schaal, S, Author              
Affiliations:
1External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 Abstract: While operational space control is of essential importance for robotics and well-understood from an analytical point of view, it can be prohibitively hard to achieve accurate control in face of modeling errors, which are inevitable in complex robots, e.g., humanoid robots. In such cases, learning control methods can offer an interesting alternative to analytical control algorithms. However, the resulting learning problem is ill-defined as it requires to learn an inverse mapping of a usually redundant system, which is well known to suffer from the property of non-convexity of the solution space, i.e., the learning system could generate motor commands that try to steer the robot into physically impossible configurations. A first important insight for this paper is that, nevertheless, a physically correct solution to the inverse problem does exit when learning of the inverse map is performed in a suitable piecewise linear way. The second crucial component for our work is based on a recent insight that many operational space controllers can be understood in terms of a constraint optimal control problem. The cost function associated with this optimal control problem allows us to formulate a learning algorithm that automatically synthesizes a globally consistent desired resolution of redundancy while learning the operational space controller. From the view of machine learning, the learning problem corresponds to a reinforcement learning problem that maximizes an immediate reward and that employs an expectation-maximization policy search algorithm. Evaluations on a three degrees of freedom robot arm illustrate the feasibility of the suggested approach.

Details

show
hide
Language(s):
 Dates: 2007-04
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.15607/RSS.2006.II.033
BibTex Citekey: 5048
 Degree: -

Event

show
hide
Title: Robotics: Science and Systems II (RSS 2006)
Place of Event: Philadelphia, PA, USA
Start-/End Date: 2006-08-16 - 2006-08-19

Legal Case

show

Project information

show

Source 1

show
hide
Title: Robotics: Science and Systems II
Source Genre: Proceedings
 Creator(s):
Sukhatme, GS, Editor
Schaal, S, Editor
Burgard, W, Editor
Fox, D, Editor
Affiliations:
-
Publ. Info: Cambridge, MA, USA : MIT Press
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 255 - 262 Identifier: ISBN: 978-0-262-69348-6