Low-cost Scalable People Tracking System for Human-Robot Collaboration in Industrial Environment

Abstract

Human-robot collaboration is one of the key elements in the Industry 4.0 revolution, aiming to a close and direct collaboration between robots and human workers to reach higher productivity and improved ergonomics. The first step toward such kind of collaboration in the industrial context is the removal of physical safety barriers usually surrounding standard robotic cells, so that human workers can approach and directly collaborate with robots. Anyway, human safety must be granted avoiding possible collisions with the robot. In this work, we propose the use of a people tracking algorithm to monitor people moving around a robot manipulator and recognize when a person is too close to the robot while performing a task. The system is implemented by a camera network system positioned around the robot workspace, and thoroughly evaluated in different industry-like settings in terms of both tracking accuracy and detection delay.