English
 
User Manual Privacy Policy Disclaimer Contact us
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
  An Information-Theoretic On-Line Update Principle for Perception-Action Coupling

Peng, Z., Genewein, T., Leibfried, F., & Braun, D. (2017). An Information-Theoretic On-Line Update Principle for Perception-Action Coupling. In IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017) (pp. 789-796). Piscataway, NJ, USA: IEEE.

Item is

Basic

show hide
Item Permalink: http://hdl.handle.net/21.11116/0000-0000-C387-B Version Permalink: http://hdl.handle.net/21.11116/0000-0000-C388-A
Genre: Conference Paper

Files

show Files

Locators

show
hide
Locator:
Link (Any fulltext)
Description:
-

Creators

show
hide
 Creators:
Peng, Z1, 2, Author              
Genewein, T1, 2, 3, 4, Author              
Leibfried, F1, 2, Author              
Braun, DA1, 2, 3, Author              
Affiliations:
1Research Group Sensorimotor Learning and Decision-Making, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497809              
2Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497794              
3Research Group Sensorimotor Learning and Decision-making, Max Planck Institute for Intelligent Systems, Max Planck Society, ou_1688138              

Content

show
hide
Free keywords: -
 Abstract: Inspired by findings of sensorimotor coupling in humans and animals, there has recently been a growing interest in the interaction between action and perception in robotic systems [1]. Here we consider perception and action as two serial information channels with limited information-processing capacity. We follow [2] and formulate a constrained optimization problem that maximizes utility under limited information-processing capacity in the two channels. As a solution we obtain an optimal perceptual channel and an optimal action channel that are coupled such that perceptual information is optimized with respect to downstream processing in the action module. The main novelty of this study is that we propose an online optimization procedure to find bounded-optimal perception and action channels in parameterized serial perception-action systems. In particular, we implement the perceptual channel as a multi-layer neural network and the action channel as a multinomial distribution. We illustrate our method in a NAO robot simulator with a simplified cup lifting task.

Details

show
hide
Language(s):
 Dates: 2017-09
 Publication Status: Published in print
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Method: -
 Identifiers: DOI: 10.1109/IROS.2017.8202240
BibTex Citekey: PengGLB2017
 Degree: -

Event

show
hide
Title: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)
Place of Event: Vancouver, BC, Canada
Start-/End Date: -

Legal Case

show

Project information

show

Source 1

show
hide
Title: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2017)
Source Genre: Proceedings
 Creator(s):
Affiliations:
Publ. Info: Piscataway, NJ, USA : IEEE
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 789 - 796 Identifier: ISBN: 978-1-5386-2682-5