Institute Homepage DE Sign In

Back

Autonomous Motion Conference Paper 2002

A locally weighted learning composite adaptive controller with structure adaptation

Thumb ticker sm ss
Autonomous Motion
Stefan Schaal
  • Director

This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator. This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator

Author(s): Nakanishi, J. and Farrell, J. A. and Schaal, S.
Book Title: IEEE International Conference on Intelligent Robots and Systems (IROS 2002)
Year: 2002
Bibtex Type: Conference Paper (inproceedings)
Address: Lausanne, Sept.30-Oct.4 2002
URL: http://www-clmc.usc.edu/publications/N/nakanishi-IROS2002.pdf
Cross Ref: p1622
Electronic Archiving: grant_archive
Note: clmc

BibTex 

@inproceedings{Nakanishi_IICIRS_2002,
  title = {A locally weighted learning composite adaptive controller with structure adaptation},
  booktitle = {IEEE International Conference on Intelligent Robots and Systems (IROS 2002)},
  abstract = {This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator. This paper introduces a provably stable adaptive learning controller which employs nonlinear function approximation with automatic growth of the learning network according to the nonlinearities and the working domain of the control system. The unknown function in the dynamical system is approximated by piecewise linear models using a nonparametric regression technique. Local models are allocated as necessary and their parameters are optimized on-line. Inspired by composite adaptive control methods, the pro-posed learning adaptive control algorithm uses both the tracking error and the estimation error to up-date the parameters. We provide Lyapunov analyses that demonstrate the stability properties of the learning controller. Numerical simulations illustrate rapid convergence of the tracking error and the automatic structure adaptation capability of the function approximator},
  address = {Lausanne, Sept.30-Oct.4 2002},
  year = {2002},
  note = {clmc},
  slug = {nakanishi_iicirs_2002},
  author = {Nakanishi, J. and Farrell, J. A. and Schaal, S.},
  crossref = {p1622},
  url = {http://www-clmc.usc.edu/publications/N/nakanishi-IROS2002.pdf}
}