Simultaneous estimation of material properties and pose for deformable objects from depth and color images

Andreas Rune Fugl, Andreas Jordt, Henrik Gordon Petersen, Morten Willatzen, Reinhard Koch

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

In this paper we consider the problem of estimating 6D pose, material properties and deformation of an object grasped by a robot gripper. To estimate the parameters we minimize an error function incorporating visual and physical correctness. Through simulated and real-world experiments we demonstrate that we are able to find realistic 6D poses and elasticity parameters like Young's modulus. This makes it possible to perform subsequent manipulation tasks, where accurate modelling of the elastic behaviour is important.
Original languageEnglish
Title of host publicationPattern Recognition : Joint 34th DAGM and 36th OAGM Symposium, Graz, Austria, August 28-31, 2012. Proceedings
PublisherSpringer
Publication date2012
Pages165-174
ISBN (Print)978-3-642-32716-2
ISBN (Electronic)978-3-642-32717-9
DOIs
Publication statusPublished - 2012
Externally publishedYes
EventJoint Pattern Recognition Symposium (34th DAGM, 36th OAGM) - Graz, Austria
Duration: 28 Aug 201231 Aug 2012
http://dagm2012.icg.tugraz.at/

Conference

ConferenceJoint Pattern Recognition Symposium (34th DAGM, 36th OAGM)
Country/TerritoryAustria
CityGraz
Period28/08/201231/08/2012
Internet address
SeriesLecture Notes in Computer Science
Volume7476
ISSN0302-9743

Keywords

  • Elasticity
  • Pattern recognition
  • Deformation

Fingerprint

Dive into the research topics of 'Simultaneous estimation of material properties and pose for deformable objects from depth and color images'. Together they form a unique fingerprint.

Cite this