Autonomous clothes manipulation using a hierarchical vision architecture

Sun, L., Aragon-Camarasa, G., Rogers, S. and Siebert, J. P. (2018) Autonomous clothes manipulation using a hierarchical vision architecture. IEEE Access, 6, pp. 76646-76662. (doi:10.1109/ACCESS.2018.2883072)

[img]
Preview
Text
173847.pdf - Published Version

7MB

Abstract

This paper presents a novel robot vision architecture for perceiving generic 3D clothes configurations. Our architecture is hierarchically structured, starting from low-level curvature features, to mid-level geometric shapes and topology descriptions, and finally high-level semantic surface descriptions. We demonstrate our robot vision architecture in a customised dual-arm industrial robot with our inhouse developed stereo vision system, carrying out autonomous grasping and dual-arm flattening. The experimental results show the advanced effectiveness of the proposed dual-arm flattening using the stereo vision system compared to single-arm flattening using the widely-cited Kinect-like sensor as the baseline. In addition, the proposed grasping approach achieves satisfactory performance on grasping various kind of garments, verifying the capability of the proposed visual perception architecture to be adapted to more than one clothing manipulation tasks.

Item Type:Articles
Additional Information:This project has received funding from the European Union’s PF7 Specific targeted research projects (STREP) under grant agreement No 288553 (CloPeMa: Clothes Perception and Manipulation, http://www.clopema.eu/).
Status:Published
Refereed:Yes
Glasgow Author(s) Enlighten ID:Sun, Mr Li and Siebert, Dr Jan and Rogers, Dr Simon and Aragon Camarasa, Dr Gerardo
Authors: Sun, L., Aragon-Camarasa, G., Rogers, S., and Siebert, J. P.
College/School:College of Science and Engineering > School of Chemistry
College of Science and Engineering > School of Computing Science
Journal Name:IEEE Access
Publisher:Institute of Electrical and Electronics Engineers
ISSN:2169-3536
ISSN (Online):2169-3536
Published Online:03 December 2018
Copyright Holders:Copyright © 2018 IEEE
First Published:First published in IEEE Access 6:76646-76662
Publisher Policy:Reproduced in accordance with the copyright policy of the publisher

University Staff: Request a correction | Enlighten Editors: Update this record

Project CodeAward NoProject NamePrincipal InvestigatorFunder's NameFunder RefLead Dept
571501CloPeMa: Clothes Perception and ManipulationJan SiebertEuropean Commission (EC)288553COM - COMPUTING SCIENCE