English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 Local TagsRelease HistoryDetailsSummary
  Learning Visual Representations for Interactive Systems

Piater, J., Jodogne, S., Detry, R., Kraft, D., Krüger, N., Krömer, O., et al. (2011). Learning Visual Representations for Interactive Systems. In C. Pradalier, R. Siegwart, & G. Hirzinger (Eds.), Robotics Research: The 14th International Symposium ISRR (pp. 399-416). Berlin, Germany: Springer.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-0013-BCE0-A Version Permalink: https://hdl.handle.net/21.11116/0000-0002-0DA2-9
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007%2F978-3-642-19457-3_24.pdf (Publisher version)
Description:
-
OA-Status:

Creators

show
hide
 Creators:
Piater, J1, 2, Author           
Jodogne, S, Author
Detry, R, Author
Kraft, D, Author
Krüger, N, Author
Krömer, O.1, 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: We describe two quite different methods for associating action parameters to visual percepts. Our RLVC algorithm performs reinforcement learning directly on the visual input space. To make this very large space manageable, RLVC interleaves the reinforcement learner with a supervised classiamp;amp;64257;cation algorithm that seeks to split perceptual states so as to reduce perceptual aliasing. This results in an adaptive discretization of the perceptual space based on the presence or absence of visual features. Its extension RLJC also handles continuous action spaces. In contrast to the minimalistic visual representations produced by RLVC and RLJC, our second method learns structural object models for robust object detection and pose estimation by probabilistic inference. To these models, the method associates grasp experiences autonomously learned by trial and error. These experiences form a non-parametric representation of grasp success likelihoods over gripper poses, which we call a gra sp d ensi ty. Thus, object detection in a novel scene simultaneously produces suitable grasping options.

Details

show
hide
Language(s):
 Dates: 2011-01
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/978-3-642-19457-3_24
BibTex Citekey: 6070
 Degree: -

Event

show
hide
Title: 14th International Symposium on Robotics Research (ISRR 2009)
Place of Event: Luzern, Switzerland
Start-/End Date: 2009-08-31 - 2009-09-03

Legal Case

show

Project information

show

Source 1

show
hide
Title: Robotics Research: The 14th International Symposium ISRR
Source Genre: Proceedings
 Creator(s):
Pradalier, C, Editor
Siegwart, R, Editor
Hirzinger, G, Editor
Affiliations:
-
Publ. Info: Berlin, Germany : Springer
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 399 - 416 Identifier: ISBN: 978-3-642-19457-3

Source 2

show
hide
Title: Springer Tracts in Advanced Robotics
Source Genre: Series
 Creator(s):
Affiliations:
Publ. Info: -
Pages: - Volume / Issue: 70 Sequence Number: - Start / End Page: - Identifier: -