| | |
Summary: Robotics and Autonomous Systems 47 (2004) 7991
Learning from demonstration and adaptation of biped locomotion
Jun Nakanishia,b,, Jun Morimotoa,b, Gen Endoa,c, Gordon Chenga,b,
Stefan Schaala,d, Mitsuo Kawatoa,b
a ATR Computational Neuroscience Laboratories, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan
b ICORP, Japan Science and Technology Agency, 2-2 Hikaridai, Seika-cho, Soraku-gun, Kyoto 619-0288, Japan
c Sony Corporation, 6-7-35 Kitashinagawa, Shinagawa-ku, Tokyo 141-0001, Japan
d Department of Computer Science, University of Southern California, 3641 Watt way, Los Angeles, CA 90089-2520, USA
Abstract
In this paper, we introduce a framework for learning biped locomotion using dynamical movement primitives based on
non-linear oscillators. 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 central pattern generator (CPG) of a biped robot, an approach we
havepreviouslyproposedforlearningandencodingcomplexhumanmovements.Demonstratedtrajectoriesarelearnedthrough
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 coupled oscillators. Numerical simulations
and experimental implementation on a physical robot demonstrate the effectiveness of the proposed locomotion controller.
© 2004 Elsevier B.V. All rights reserved.
Keywords: Biped locomotion; Learning from demonstration; Dynamical movement primitives; Phase resetting; Frequency adaptation
1. Introduction
There has been a growing interest in biped loco-
|
