Capturing Mental Workload Through Physiological Sensors in Human–Robot Collaboration: A Systematic Literature Review

Abstract

Featured Application: The results of this study on mental workload have potential applications in developing adaptive robots that enhance safety and efficiency in human–robot collaboration within industrial settings. Human–robot collaboration (HRC) is increasingly prevalent across various industries, promising to boost productivity, efficiency, and safety. As robotics technology advances and takes on more complex tasks traditionally performed by humans, the nature of work and the demands on workers are evolving. This shift emphasizes the need to critically integrate human factors into these interactions, as the effectiveness and safety of these systems are highly dependent on how workers cooperate with and understand robots. A significant challenge in this domain is the lack of a consensus on the most efficient way to operationalize and assess mental workload, which is crucial for optimizing HRC. In this systematic literature review, we analyze the different psychophysiological measures that can reliably capture and differentiate varying degrees of mental workload in different HRC settings. The findings highlight the crucial need for standardized methodologies in workload assessment to enhance HRC models. Ultimately, this work aims to guide both theorists and practitioners in creating more sophisticated, safe, and efficient HRC frameworks by providing a comprehensive overview of the existing literature and pointing out areas for further study.