Grasp Exploration for 3D Object Shape Representation using Probabilistic Map

Title:

Grasp Exploration for 3D Object Shape Representation using Probabilistic Map

Authors:

Diego R. Faria [ website | social ]

Ricardo Martins [ website | social ]

Jorge Dias [ website | social ]

Abstract:

In this work it is shown the representation of 3D object shape acquired from grasp exploration. Electromagnetic motion tracking sensors are used on the fingers for object contour following to acquire the 3D points to represent its shape using a probabilistic volumetric map. It is used the object referential for its representation. For that, it is found the center of mass of the 3D object through the moments to define its referential. The occupancy of each individual voxel in the map is assumed to be independent from the other voxels occupancy. The posteriori achieved from Bayes’ rule is the probability distribution on the occupations percentage for each voxel. The probabilistic map in a Cartesian system is converted to the spherical coordinate system for visualization with more details on its surface.

Publisher:

DoCEIS'10 - Doctoral Conference on Computing, Electrical and Industrial Systems

Date Published:

2010-02-01

Publisher website:

http://www.springerlink.com/content/ml27uk38625800l1

DOI:

10.1007/978-3-642-11628-5_23

Alternative full-text PDF:

download full-text PDF via University of Coimbra

Keywords:

robotics, artificial perception, Bayesian modelling, grasping

Thumbnail:

image

Grasp Exploration for 3D Object Shape Representation using Probabilistic Map

Scholarly Lite is a free theme, contributed to the Drupal Community by More than Themes.