Advanced Search

Browse by Discipline

Scientific Societies

E-print Alerts

Add E-prints

E-print Network

  Advanced Search  

Auton Robot DOI 10.1007/s10514-009-9133-z

Summary: Auton Robot
DOI 10.1007/s10514-009-9133-z
Nonparametric representation of an approximated Poincaré map
for learning biped locomotion
Jun Morimoto · Christopher G. Atkeson
Received: 17 November 2008 / Accepted: 2 August 2009
© Springer Science+Business Media, LLC 2009
Abstract We propose approximating a Poincaré map of
biped walking dynamics using Gaussian processes. We lo-
cally optimize parameters of a given biped walking con-
troller based on the approximated Poincaré map. By using
Gaussian processes, we can estimate a probability distri-
bution of a target nonlinear function with a given covari-
ance. Thus, an optimization method can take the uncertainty
of approximated maps into account throughout the learning
process. We use a reinforcement learning (RL) method as
the optimization method. Although RL is a useful non-linear
optimizer, it is usually difficult to apply RL to real robotic
systems due to the large number of iterations required to ac-
quire suitable policies. In this study, we first approximated


Source: Atkeson, Christopher G. - Robotics Institute, School of Computer Science, Carnegie Mellon University


Collections: Computer Technologies and Information Sciences; Engineering