Real-Time Predictive Control of an UR5 Robotic Arm Through Human Upper Limb Motion Tracking

Abstract

This paper reports the authors' initial results on developing a real-time teleoperation system for an Universal Robots robotic arm through human motion capture with a visualization utility built on the Blender Game Engine open-source platform. A linear explicit model predictive robot controller (EMPC) is implemented for online generation of optimal robot trajectories matching operator's wrist position and orientation, whilst adhering to the robot's constraints. The EMPC proved to be superior to open-loop and naive PID controllers in terms of accuracy and safety.