PASCAL - Pattern Analysis, Statistical Modelling and Computational Learning

Vision-based object handling for industrial applications
Pedro J. Sanz, Antonio Requena, José Iñesta and Angel P. del Pobil
IEEE Robotics and Automation Magazine Volume 12, Number 3, pp. 44-52, 2005.


This paper reports some industrial applications of a visually-guided system for robot grasping using an inexpensive two-finger gripper. In all cases, the robot uses visual information as input and is able to reason about the shapes of the objects in the scene in order to decide the best stable grasp online. The first version of this system was able to grasp rectangular parts in arbitrary positions in the scene, and was successfully deployed. New applications in industry have been addressed, that have to cope with the cost, time and reliability requirements imposed by the industrial process. Our results show that the capabilities of the underlying methodology make it feasible to deal with more complex shapes even a priori unknown, opening new possibilities within industrial domains that have traditionally not been fully automated such as the food industry due to a large shape variability of the objects to be handled.

PDF - PASCAL Members only - Requires Adobe Acrobat Reader or other PDF viewer.
EPrint Type:Article
Project Keyword:Project Keyword UNSPECIFIED
Subjects:Machine Vision
ID Code:758
Deposited By:José Iñesta
Deposited On:30 December 2004