Presentation 2003/10/17
Learning Movement Primitives for Imitation Learning in Humanoid Robots
Jun NAKANISHI, Auke IJSPEERT, Stefan SCHAAL, Gordon CHENG,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we present our studies on learning complex multijoint movements by learning from demonstration. Kinematic movement plans are described in a set of nonlinear differential equations with well-defined attractor dynamics which we call "dynamical movement primitives," and demonstrated trajectories are learned using locally weighted regression. We present experimental implementation of the proposed method on our humanoid robot for learning discrete and rhythmic movements from demonstration. Furthermore, we suggest an application of rhythmic dynamical movement primitives as a CPG for biped locomotion.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Learning from Demonstration / Dynamical Movement Primitives / Locally Weithged Regression / Biped Locomotion
Paper # PRMU2003-136,NC2003-67
Date of Issue

Conference Information
Committee NC
Conference Date 2003/10/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Learning Movement Primitives for Imitation Learning in Humanoid Robots
Sub Title (in English)
Keyword(1) Learning from Demonstration
Keyword(2) Dynamical Movement Primitives
Keyword(3) Locally Weithged Regression
Keyword(4) Biped Locomotion
1st Author's Name Jun NAKANISHI
1st Author's Affiliation ATR Computational Neuroscience Laboratories()
2nd Author's Name Auke IJSPEERT
2nd Author's Affiliation EPFL, Swiss Federal Institute of Technology, Lausanne
3rd Author's Name Stefan SCHAAL
3rd Author's Affiliation University of Sourthern California:ATR Computational Neuroscience Laboratories
4th Author's Name Gordon CHENG
4th Author's Affiliation ATR Computational Neuroscience Laboratories
Date 2003/10/17
Paper # PRMU2003-136,NC2003-67
Volume (vol) vol.103
Number (no) 392
Page pp.pp.-
#Pages 6
Date of Issue