A Vision System for the Unfolding of Highly Non-rigid Objects on a Table by One Manipulator

In this paper, a systematic approach is presented in order to detect and classify the characteristic features of a folded piece of fabric to be unfolded by a robot. The manipulations can be made by only one manipulator on a working table and with machine vision feedback. The main goal of this method is to detect, evaluate and classify the regions of interest (ROIs) which, in the particular case, are the corners of the fabric lying on the table.

[1]  Pieter Abbeel,et al.  Cloth grasp point detection based on multiple-view geometric cues with application to robotic towel folding , 2010, 2010 IEEE International Conference on Robotics and Automation.

[2]  Y. Kamiya,et al.  Inchworm robot grippers in clothes manipulation — optimizing the tracing algorithm , 2007, 2007 International Conference on Intelligent and Advanced Systems.

[3]  Hiroaki Seki,et al.  Unfolding of Massive Laundry and Classification Types by Dual Manipulator , 2007, J. Adv. Comput. Intell. Intell. Informatics.

[4]  N.A. Aspragathos,et al.  Vision aided neuro-fuzzy control for the folding of fabric sheets , 2007, 2007 International Conference on Control, Automation and Systems.

[5]  Frank W. Paul.  Acquisition, placement, and folding of fabric materials , 2004 .

[6]  Kyoko Hamajima,et al.  Planning strategy for task of unfolding clothes , 1997, Robotics Auton. Syst..

[7]  Nelson H. C. Yung,et al.  Corner detector based on global and local curvature properties , 2008 .