Applications to Safe Human–Robot Interaction

Abstract

In this chapter we address the scenario of safe human–robot interaction in the industrial production environment. For example, in car manufacturing, industrial production processes are characterised by either fully automatic production sequences carried out solely by industrial robots or fully manual assembly steps where only humans work together on the same task. Close collaboration between humans and industrial robots is very limited and usually not possible due to safety concerns. Industrial production processes may increase their efficiency by establishing a close collaboration of humans and machines exploiting their unique capabilities, which requires sophisticated techniques for human–robot interaction. In this context, the recognition of interactions between humans and industrial robots requires vision methods for three-dimensional pose estimation and tracking of the motion of human body parts based on three-dimensional scene analysis. We begin with an overview of gesture recognition methods in the general context of human–robot interaction and provide an overview of vision-based safe human–robot interaction. We evaluate the performance of the three-dimensional approach to the detection and tracking of objects in point clouds described in Chap. 1 in a typical industrial production environment. The introduced methods for three-dimensional detection, pose estimation, and tracking of human body parts and recognition of their actions are evaluated in similar scenarios.