English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning Robot Dynamics for Computed Torque Control Using Local Gaussian Processes Regression

Nguyen-Tuong, D., & Peters, J. (2008). Learning Robot Dynamics for Computed Torque Control Using Local Gaussian Processes Regression. In A. Stoica, E. Tunstel, T. Huntsberger, T. Arslan, S. Vijayakumar, & O. El-Rayis (Eds.), Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS 2008) (pp. 59-64). Piscataway, NJ, USA: IEEE.

Item is

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Nguyen-Tuong, D1, 2, Author              
Peters, J1, 2, Author              
Affiliations:
1Department Empirical Inference, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497795              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, Spemannstrasse 38, 72076 Tübingen, DE, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: Accurate models of the robot dynamics allow the design of significantly more precise, energy-efficient and more compliant computed torque control for robots. However, in some cases the accuracy of rigid-body models does not suffice for sound control performance due to unmodeled nonlinearities such as hydraulic cables, complex friction, or actuator dynamics. In such cases, learning the models from data poses an interesting alternative and estimating the dynamics model using regression techniques becomes an important problem. However, the most accurate regression methods, e.g. Gaussian processes regression (GPR) and support vector regression (SVR), suffer from exceptional high computational complexity which prevents their usage for large numbers of samples or online learning to date. We proposed an approximation to the standard GPR using local Gaussian processes models. Due to reduced computational cost, local Gaussian processes (LGP) is capable for an online learning. Comparisons with other nonparametric regre ssions, e.g. standard GPR, SVR and locally weighted projection regression (LWPR), show that LGP has higher accuracy than LWPR and close to the performance of standard GPR and SVR while being sufficiently fast for online learning.

Details

show
hide
Language(s):
 Dates: 2008-08
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/LAB-RS.2008.16
BibTex Citekey: 5415
 Degree: -

Event

show
hide
Title: 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS 2008)
Place of Event: Edinburgh, UK
Start-/End Date: 2008-08-06 - 2008-08-08

Legal Case

show

Project information

show

Source 1

show
hide
Title: Proceedings of the 2008 ECSIS Symposium on Learning and Adaptive Behaviors for Robotic Systems (LAB-RS 2008)
Source Genre: Proceedings
 Creator(s):
Stoica, A, Editor
Tunstel, E, Editor
Huntsberger, T, Editor
Arslan, T, Editor
Vijayakumar, S, Editor
El-Rayis, O, Editor
Affiliations:
-
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 59 - 64 Identifier: ISBN: 978-0-7695-3272-1