English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  Learning Visual Representations for Perception-Action Systems

Piater, J., Jodogne, S., Detry, R., Kraft, R., Krüger, N., Kroemer, O., et al. (2011). Learning Visual Representations for Perception-Action Systems. The International Journal of Robotics Research, 30(3), 294-307. doi:10.1177/0278364910382464.

Item is

Files

show Files

Locators

show
hide
Description:
-

Creators

show
hide
 Creators:
Piater, J, Author              
Jodogne, S, Author
Detry, R, Author
Kraft, R, Author
Krüger, N, Author
Kroemer, 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 discuss vision as a sensory modality for systems that interact flexibly with uncontrolled environments. Instead of trying to build a generic vision system that produces task-independent representations, we argue in favor of task-specific, learnable representations. This concept is illustrated by two examples of our own work. First, 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 classification 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, additionally 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 grasp density. Thus, object detection in a novel scene simultaneously produces suitable grasping options.

Details

show
hide
Language(s):
 Dates: 2011-02
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1177/0278364910382464
BibTex Citekey: 6707
 Degree: -

Event

show

Legal Case

show

Project information

show

Source 1

show
hide
Title: The International Journal of Robotics Research
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Cambridge, MA : Sage Publications, Inc.
Pages: - Volume / Issue: 30 (3) Sequence Number: - Start / End Page: 294 - 307 Identifier: ISSN: 0278-3649
CoNE: https://pure.mpg.de/cone/journals/resource/954925506289