Creation of a Framework for an Empathy-Based Improvement of a Hybrid Working System

Abstract

Collaborative robotics is changing the way we work, making it safer, more efficient, and more productive, by merging human and robot strengths.The increasing utilization of hybrid working systems has led to a need for improved methods of operator stress detection and mitigation.This thesis proposes a framework for an empathy-based improvement of hybrid working systems.The framework uses galvanic skin response (GSR) measurements, captured with the physiological data sensor ''Empatica E4'', to detect moments of stress (MOS) in the operator.Subsequently, a stress-level, based on the number of MOS within a predefined duration, is estimated.Therefore, the framework's reactive mechanism adapts the collaborative robot's (cobot) manipulation speed and task allocation by sending the corresponding signals to the robot control.The aim of this adaptation is to reduce the operator's stress-level while maintaining or increasing productivity.The framework was evaluated with a platform for assembling a miniature robot.Results showed that the framework was able to effectively detect moments of stress and adapt the cobot's manipulation speed accordingly.The framework could be used to reduce operator stress and improve productivity in a variety of industrial applications.