Situational Awareness for Manufacturing Applications

Abstract

Collaboration between human workers and robotic assistants is seen as one way to increase both flexibility and efficiency in a production line environment. In this setup, human workers can be assigned tasks that require high perceptual ability, dexterity and judgement, supplemented by robotic assistants that can perform work of low (skill) value, such as fetching and delivering parts and tools. Key to such a strategy is the ability of the automated system to maintain total awareness of the states of all key players (humans, robots, machinery, parts) and take the necessary action to carry out the manufacturing while maintaining the safety of the human workers. We refer to this attribute as Situational Awareness, and in this paper present both an implementation and a case study in the form of a system that tracks the articulated 3D pose of a group of human workers in an enclosed area.