Autonomous Motion
Note: This department has relocated.

Scalable techniques from nonparameteric statistics for real-time robot learning

2002

Article

am


Locally weighted learning (LWL) is a class of techniques from nonparametric statistics 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 belief that LWL methods cannot work well in high-dimensional spaces, we provide new algorithms that have been tested on up to 90 dimensional learning problems. The applicability of our LWL algorithms is demonstrated in various robot learning examples, including the learning of devil-sticking, pole-balancing by a humanoid robot arm, and inverse-dynamics learning for a seven and a 30 degree-of-freedom robot. In all these examples, the application of our statistical neural networks techniques allowed either faster or more accurate acquisition of motor control than classical control engineering.

Author(s): Schaal, S. and Atkeson, C. G. and Vijayakumar, S.
Book Title: Applied Intelligence
Volume: 17
Number (issue): 1
Pages: 49-60
Year: 2002

Department(s): Autonomous Motion
Bibtex Type: Article (article)

Cross Ref: p1420
Note: clmc
URL: http://www-clmc.usc.edu/publications/S/schaal-JAI2002.pdf

BibTex

@article{Schaal_AI_2002,
  title = {Scalable techniques from nonparameteric statistics for real-time robot learning},
  author = {Schaal, S. and Atkeson, C. G. and Vijayakumar, S.},
  booktitle = {Applied Intelligence},
  volume = {17},
  number = {1},
  pages = {49-60},
  year = {2002},
  note = {clmc},
  doi = {},
  crossref = {p1420},
  url = {http://www-clmc.usc.edu/publications/S/schaal-JAI2002.pdf}
}