ERS-7 up close

A Model-Based Approach to Robot Joint Control

Daniel Stronger and Peter Stone. A Model-Based Approach to Robot Joint Control. In Daniele Nardi, Martin Riedmiller, and Claude Sammut, editors, RoboCup-2004: Robot Soccer World Cup VIII, Lecture Notes in Artificial Intelligence, pp. 297–309, Springer Verlag, Berlin, 2005.
Official version from Publisher's Webpage© Springer-Verlag

Download

[PDF]235.3kB  [postscript]489.4kB  

Abstract

Despite efforts to design precise motor controllers, robot joints do not always move exactly as desired. This paper introduces a general model-based method for improving the accuracy of joint control. First, a model that predicts the effects of joint requests is built based on empirical data. Then this model is approximately inverted to determine the control requests that will most closely lead to the desired movements. We implement and validate this approach on a popular, commercially available robot, the Sony Aibo ERS-210A.

BibTeX Entry

@incollection(LNAI2004-joints,
author="Daniel Stronger and Peter Stone",
title="A Model-Based Approach to Robot Joint Control",
booktitle= "{R}obo{C}up-2004: Robot Soccer World Cup {VIII}",
Editor="Daniele Nardi and Martin Riedmiller and Claude Sammut",
Publisher="Springer Verlag",address="Berlin",year="2005",
series="Lecture Notes in Artificial Intelligence",
volume="3276",
pages="297--309",
abstract={
Despite efforts to design precise motor controllers,
robot joints do not always move exactly as desired.
This paper introduces a general model-based method
for improving the accuracy of joint control. First,
a model that predicts the effects of joint requests
is built based on empirical data. Then this model is
approximately inverted to determine the control
requests that will most closely lead to the desired
movements. We implement and validate this approach
on a popular, commercially available robot, the Sony
Aibo {ERS-210A}.
},
wwwnote = {Official version from <a href="http://www.springerlink.com/index/5HEKU6UDMFATC0UE">Publisher's Webpage</a>&copy Springer-Verlag},
)

Valid CSS!
Valid XHTML 1.0!