A multivariate fusion collision detection method for dynamic operations of human-robot collaboration systems

Abstract

Real-time human-robot collision detection is crucial for ensuring the safety of operators during human-robot collaboration(HRC) and for improving the efficiency of such collaboration. It plays an important role in promoting the development of intelligent manufacturing. To address this issue, our team developed a multi-faceted collision detection system using eXtended Reality (XR) technology, specifically designed for complex and dynamic human-robot collaborative operations. The system integrates three different methods: a Virtual Reality (VR) detection method that enables robots to better perceive and detect human operators. An Augmented Reality (AR) detection method that enhances the operator’s perception of the robot. And a fusion detection and evaluation method. This detection and evaluation method assesses the effectiveness of collaboration by analyzing key performance indicators, such as real-time distance between human and robot, changes in the operator’s Heart Rate(HR), and overall task completion time. Through empirical research on the human-robot collaborative assembly task of T-series spiral bevel gear reducers, the effectiveness of the innovative method is verified. The research results show that this method significantly improves safety and operational efficiency, providing a novel solution detection in industrial manufacturing environments.