Mobile Manipulation in Domestic Environments Using A Low Degree of Freedom Manipulator

Abstract

We present a mobile manipulation system used by the Georgia Tech team in the RoboCup@Home 2010 competition. An overview of the system is provided, including the approach taken for manipulation, SLAM, object detection, object recognition, and system integration. We focus on our manipulation strategy, which utilizes a low-degree of freedom manipulator and makes use of the robot’s differential drive as part of the manipulation strategy. Empirical results demonstrating our platform’s ability to detect and grasp a variety of tabletop objects are presented.