Autonomous Motion
Note: This department has relocated.

Learning operational space control

2006

Conference Paper

am

ei


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-covexity 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 exits 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 feasability of our suggested approach.

Author(s): Peters, J. and Schaal, S.
Book Title: Robotics: Science and Systems II (RSS 2006)
Pages: 255-262
Year: 2006
Editors: Gaurav S. Sukhatme and Stefan Schaal and Wolfram Burgard and Dieter Fox
Publisher: Cambridge, MA: MIT Press

Department(s): Autonomous Motion, Empirical Inference
Bibtex Type: Conference Paper (inproceedings)

Event Name: RSS 2006
Event Place: Philadelphia, PA, USA

Cross Ref: p2583
Note: clmc
URL: http://www-clmc.usc.edu/publications/P/peters-RSS2006.pdf

BibTex

@inproceedings{Peters_RSS_2006,
  title = {Learning operational space control},
  author = {Peters, J. and Schaal, S.},
  booktitle = {Robotics: Science and Systems II (RSS 2006)},
  pages = {255-262},
  editors = {Gaurav S. Sukhatme and Stefan Schaal and Wolfram Burgard and Dieter Fox},
  publisher = {Cambridge, MA: MIT Press},
  year = {2006},
  note = {clmc},
  doi = {},
  crossref = {p2583},
  url = {http://www-clmc.usc.edu/publications/P/peters-RSS2006.pdf}
}