Teaching grasping points using natural movements

Abstract

A common strategy to teach a robot certain skills involves demonstration. While the demonstrations are best made by directly manipulating the robot, in hazardous conditions the only choice is teleoperation. Even though haptic devices offer fairly good results, using natural movements would give a better feeling of control.

Leap Motion sensor (Leap Motion Inc., USA) is a device that detects hands and it can be used to control the robot arm in a more natural way. In this work, a system that will control the WAM arm (Barret Technology Inc., USA) using the Leap Motion sensor will be explained. Later this system will be tested in order to grasp a polo shirt which will be used to train grasping points on the shirt.