Concept of an Intuitive Human-Robot-Collaboration via Motion Tracking and Augmented Reality

Abstract

Human-cobot interaction is one of the main aspects of the 4 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> industrial revolution. One goal of current robotic research is to enhance safety and efficiency by designing the collaboration in a more intuitive way. The following work introduces two concepts to improve human-cobot collaboration on the basis of deep learning and augmented reality to achieve a more efficient and pleasant working environment. The first concept uses meta learning and Gaussian process to predict the movement of the human worker. The second concept enables the worker to see the next assembly step of the robotic arm via augmented reality.