An experiment to evaluate robotic grasping of occluded objects - Robotics Institute Carnegie Mellon University

An experiment to evaluate robotic grasping of occluded objects

Arnon Hurwitz, Marshal Childers, Andrew Dornbush, Dhruv Mauria Saxena, Maxim Likhachev, and Craig Lennon
Conference Paper, Proceedings of SPIE Unmanned Systems Technology XX, Vol. 10640, May, 2018

Abstract

In December of 2017, members of the Army Research Laboratory’s Robotics Collaborative Technology Alliance (RCTA) conducted an experiment to evaluate the progress of research on robotic grasping of occluded objects. This experiment used the Robotic Manipulator (RoMan) platform equipped with an Asus Xtion to identify an object on a table cluttered with other objects, and to grasp and pick up the target object. The identification and grasping was conducted with varying input factor assignments following a formal design of experiments; these factors comprised different sizes of target, varied target orientation, variation in the number and positions of objects which occluded the target object from view, and different levels of lighting. The grasping was successful in 18 out of 23 runs (78% success rate). The grasping action was conducted within constraints placed on the position and orientation of the RoMan with respect to the table of target objects. The Statistical approach of a ‘deterministic’ design and the use of odds ratio analysis were applied to the task at hand.

BibTeX

@conference{Hurwith-2018-122799,
author = {Arnon Hurwitz and Marshal Childers and Andrew Dornbush and Dhruv Mauria Saxena and Maxim Likhachev and Craig Lennon},
title = {An experiment to evaluate robotic grasping of occluded objects},
booktitle = {Proceedings of SPIE Unmanned Systems Technology XX},
year = {2018},
month = {May},
volume = {10640},
}