A novel non-intrusive mental workload evaluation concept in human-robot collaboration

Abstract

The integration of Human-Robot Collaboration (HRC) in industrial robotics introduces challenges, particularly in adapting manufacturing environments to work seamlessly with collaborative robots. A key objective in HRC system optimization is enhancing human acceptance of these robots and improving productivity. Traditionally, the assessment of human mental workload in these settings relies on methods like EEG, fNIRS, and heart rate monitoring, which require direct physical contact and can be impractical in manufacturing environments. To address these issues, we propose an innovative and non-intrusive method that employs cameras to measure mental workload. This technique involves capturing video footage of human operators on the shop floor, focusing specifically on facial expressions. Advanced AI algorithms analyse these videos to predict heart rate ranges, which are then used to estimate mental workload levels in real time. This approach not only circumvents the need for direct contact with measurement devices but also enhances privacy and data security through privacy computing measures. Our proposed method was tested in an HRC experiment to provide preliminary validation. This pioneering use of non-intrusive AI-based vision techniques for real-time mental workload assessment represents a significant advancement in managing human factors in industrial HRC settings.