Autonomous Motion
Note: This department has relocated.

On-line learning and modulation of periodic movements with nonlinear dynamical systems

2009

Article

am


Abstract  The paper presents a two-layered system for (1) learning and encoding a periodic signal without any knowledge on its frequency and waveform, and (2) modulating the learned periodic trajectory in response to external events. The system is used to learn periodic tasks on a humanoid HOAP-2 robot. The first layer of the system is a dynamical system responsible for extracting the fundamental frequency of the input signal, based on adaptive frequency oscillators. The second layer is a dynamical system responsible for learning of the waveform based on a built-in learning algorithm. By combining the two dynamical systems into one system we can rapidly teach new trajectories to robots without any knowledge of the frequency of the demonstration signal. The system extracts and learns only one period of the demonstration signal. Furthermore, the trajectories are robust to perturbations and can be modulated to cope with a dynamic environment. The system is computationally inexpensive, works on-line for any periodic signal, requires no additional signal processing to determine the frequency of the input signal and can be applied in parallel to multiple dimensions. Additionally, it can adapt to changes in frequency and shape, e.g. to non-stationary signals, such as hand-generated signals and human demonstrations.

Author(s): Gams, A. and Ijspeert, A. and Schaal, S. and Lenarčič, J.
Book Title: Autonomous Robots
Volume: 27
Number (issue): 1
Pages: 3-23
Year: 2009

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

Cross Ref: p10344
Note: clmc
URL: http://www-clmc.usc.edu/publications/G/gams-AR2009.pdf

BibTex

@article{Gams_AR_2009,
  title = {On-line learning and modulation of periodic movements with nonlinear dynamical systems},
  author = {Gams, A. and Ijspeert, A. and Schaal, S. and Lenarčič, J.},
  booktitle = {Autonomous Robots},
  volume = {27},
  number = {1},
  pages = {3-23},
  year = {2009},
  note = {clmc},
  doi = {},
  crossref = {p10344},
  url = {http://www-clmc.usc.edu/publications/G/gams-AR2009.pdf}
}