English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Active learning using mean shift optimization for robot grasping

Kroemer, O., Detry, R., Piater, J., & Peters, J. (2009). Active learning using mean shift optimization for robot grasping. In 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009) (pp. 2610-2615). Piscataway, NJ, USA: IEEE Service Center.

Item is

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Kroemer, O1, 2, Author              
Detry, R, Author              
Piater, J, 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, ou_1497794              

Content

show
hide
Free keywords: -
 Abstract: When children learn to grasp a new object, they often know several possible grasping points from observing a parentlsquo;s demonstration and subsequently learn better grasps by trial and error. From a machine learning point of view, this process is an active learning approach. In this paper, we present a new robot learning framework for reproducing this ability in robot grasping. For doing so, we chose a straightforward approach: first, the robot observes a few good grasps by demonstration and learns a value function for these grasps using Gaussian process regression. Subsequently, it chooses grasps which are optimal with respect to this value function using a mean-shift optimization approach, and tries them out on the real system. Upon every completed trial, the value function is updated, and in the following trials it is more likely to choose even better grasping points. This method exhibits fast learning due to the data-efficiency of Gaussian process regression framework and the fact th at t he mean-shift method provides maxima of this cost function. Experiments were repeatedly carried out successfully on a real robot system. After less than sixty trials, our system has adapted its grasping policy to consistently exhibit successful grasps.

Details

show
hide
Language(s):
 Dates: 2009-10
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1109/IROS.2009.5354345
BibTex Citekey: 6065
 Degree: -

Event

show
hide
Title: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)
Place of Event: St. Louis, MO, USA
Start-/End Date: 2009-10-10 - 2009-10-15

Legal Case

show

Project information

show

Source 1

show
hide
Title: 2009 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2009)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE Service Center
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 2610 - 2615 Identifier: ISBN: 978-1-424-43803-7