Institute Homepage DE Sign In

Back

Autonomous Motion Conference Paper 2002

Learning rhythmic movements by demonstration using nonlinear oscillators

Thumb ticker sm ss
Autonomous Motion
Stefan Schaal
  • Director

Locally weighted learning (LWL) is a class of statistical learning techniques that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional beliefs that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested in up to 50 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing of a humanoid robot arm, and inverse-dynamics learning for a seven degree-of-freedom robot.

Author(s): Ijspeert, J. A. and Nakanishi, J. and Schaal, S.
Book Title: IEEE International Conference on Intelligent Robots and Systems (IROS 2002)
Pages: 958-963
Year: 2002
Publisher: Piscataway, NJ: IEEE
Bibtex Type: Conference Paper (inproceedings)
Address: Lausanne, Sept.30-Oct.4 2002
URL: http://www-clmc.usc.edu/publications/I/ijspeert-IROS2002.pdf
Cross Ref: p1620
Electronic Archiving: grant_archive
Note: clmc

BibTex 

@inproceedings{Ijspeert_IICIRS_2002,
  title = {Learning rhythmic movements by demonstration using nonlinear oscillators},
  booktitle = {IEEE International Conference on Intelligent Robots and Systems (IROS 2002)},
  abstract = {Locally weighted learning (LWL) is a class of statistical learning techniques that provides useful representations and training algorithms for learning about complex phenomena during autonomous adaptive control of robotic systems. This paper introduces several LWL algorithms that have been tested successfully in real-time learning of complex robot tasks. We discuss two major classes of LWL, memory-based LWL and purely incremental LWL that does not need to remember any data explicitly. In contrast to the traditional beliefs that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested in up to 50 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing of a humanoid robot arm, and inverse-dynamics learning for a seven degree-of-freedom robot.},
  pages = {958-963},
  publisher = {Piscataway, NJ: IEEE},
  address = {Lausanne, Sept.30-Oct.4 2002},
  year = {2002},
  note = {clmc},
  slug = {ijspeert_iicirs_2002},
  author = {Ijspeert, J. A. and Nakanishi, J. and Schaal, S.},
  crossref = {p1620},
  url = {http://www-clmc.usc.edu/publications/I/ijspeert-IROS2002.pdf}
}