Learning from demonstration and adaptation of biped locomotion with dynamical movement primitives
In this paper, we report on our research for learning biped locomotion from human demonstration. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a CPG of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through the movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a novel frequency adaptation algorithm based on phase resetting and entrainment of oscillators. Numerical simulations demonstrate the effectiveness of the proposed locomotion controller.
| Author(s): | Nakanishi, J. and Morimoto, J. and Endo, G. and Schaal, S. and Kawato, M. |
| Book Title: | Workshop on Robot Learning by Demonstration, IEEE International Conference on Intelligent Robots and Systems (IROS 2003) |
| Year: | 2003 |
| Bibtex Type: | Conference Paper (inproceedings) |
| Address: | Las Vegas, NV, Oct. 27-31 |
| URL: | http://www-clmc.usc.edu/publications/N/nakanishi-IROS2003.pdf |
| Cross Ref: | p1803 |
| Electronic Archiving: | grant_archive |
| Note: | clmc |
BibTex
@inproceedings{Nakanishi_WRLDIICIRS_2003,
title = {Learning from demonstration and adaptation of biped locomotion with dynamical movement primitives},
booktitle = {Workshop on Robot Learning by Demonstration, IEEE International Conference on Intelligent Robots and Systems (IROS 2003)},
abstract = {In this paper, we report on our research for learning biped locomotion from human demonstration. Our ultimate goal is to establish a design principle of a controller in order to achieve natural human-like locomotion. We suggest dynamical movement primitives as a CPG of a biped robot, an approach we have previously proposed for learning and encoding complex human movements. Demonstrated trajectories are learned through the movement primitives by locally weighted regression, and the frequency of the learned trajectories is adjusted automatically by a novel frequency adaptation algorithm based on phase resetting and entrainment of oscillators. Numerical simulations demonstrate the effectiveness of the proposed locomotion controller.},
address = {Las Vegas, NV, Oct. 27-31},
year = {2003},
note = {clmc},
slug = {nakanishi_wrldiicirs_2003},
author = {Nakanishi, J. and Morimoto, J. and Endo, G. and Schaal, S. and Kawato, M.},
crossref = {p1803},
url = {http://www-clmc.usc.edu/publications/N/nakanishi-IROS2003.pdf}
}