Summary: Learning from Demonstration and Adaptation of Biped Locomotion
with Dynamical Movement Primitives
Jun Nakanishi1
, Jun Morimoto1
, Gen Endo1,2
, Gordon Cheng1
, Stefan Schaal1,3
and Mitsuo Kawato1
1
ATR Computational Neuroscience Laboratories, Kyoto 619­0288, Japan
2
Sony Intelligent Dynamics Laboratory, Tokyo 141­0001, Japan
3
University of Southern California, Los Angeles, CA 90089-2520, USA
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

Source: Atkeson, Christopher G. - Robotics Institute, School of Computer Science, Carnegie Mellon University
Southern California, University of - School of Engineering, Center for Robotics and Embedded Systems
Zeglin, Garth - Robotics Institute, Carnegie Mellon University

Collections: Computer Technologies and Information Sciences; Engineering