Publication

Determining where to grasp cloth using depth information

Conference Article

Conference

Catalan Conference on Artificial Intelligence (CCIA)

Edition

14th

Pages

199-207

Doc link

http://dx.doi.org/10.3233/978-1-60750-842-7-199

File

Download the digital copy of the doc pdf document

Abstract

In this paper we address the problem of finding an initial good grasping point for the robotic manipulation of textile objects lying on a flat surface. Given as input a point cloud of the cloth acquired with a 3D camera, we propose choosing as grasping points those that maximize a new measure of wrinkledness, computed from the distribution of normal directions over local neighborhoods. Real grasping experiments using a robotic arm are performed, showing that the proposed measure leads to promising results.

Categories

pattern recognition.

Author keywords

deformable objects, computer vision, grasping point selection

Scientific reference

A. Ramisa, G. Alenyà, F. Moreno-Noguer and C. Torras. Determining where to grasp cloth using depth information, 14th Catalan Conference on Artificial Intelligence, 2011, Lleida, in Artificial Intelligence Research and Development, Vol 232 of Frontiers in Artificial Intelligence and Applications, pp. 199-207, 2011, IOS Press.