Assessing the Impact of Exoskeleton Systems on Worker Trust during Repetitive Construction Tasks: A Trust Detection Framework Integrating Physiological Signals and Artificial Intelligence

The construction industry frequently exposes workers to repetitive and physically demanding tasks, increasing their risk of developing work-related musculoskeletal disorders (WMSDs). Powered exoskeletons have emerged as potential solutions to mitigate these risks, providing physical support and promoting ergonomic postures. However, the successful adoption of these technology hinges on workers’ trust, which is influenced by various psychophysiological factors. To bridge this gap, this study aims to assess the impact of back-support exoskeletons (BSE) on workers’ trust level during common construction tasks. To accomplish this, a physiologically based trust level assessment framework was developed. This framework used wearable biosensors to capture the physiological signals of workers and applied advanced signal processing techniques, robust feature extraction methods, and an optimized ensemble learning approach to estimate the trust level of workers while wearing powered exoskeleton. Results revealed a significant reduction in trust levels when using the exoskeleton for material handling tasks, with average scores decreasing from 2.67 ± 0.16 to 2.08 ± 0.27, representing a 24.84% decline. The findings can aid in the design and implementation of exoskeletons in the construction industry.