Michele Mingardi


Year: 2019

Supervisor: Luciano Gamberini

Co-supervisor: Patrik Pluchino, Davide Bacchin

Graduate student: Michele Mingardi

Industry 4.0, also known as the Fourth Industrial Revolution, refers to the ongoing transformation in the manufacturing and industrial sectors, driven by advancements in digital technology, automation, data exchange, and artificial intelligence. It is a concept that emerged in Germany and has since become a global phenomenon, influencing various industries worldwide. In Industry 4.0, where human-robot interaction plays a crucial role, assessing the cognitive load and mental fatigue experienced by human operators is essential. Monitoring these aspects helps ensure the well-being and safety of human workers and optimize the overall efficiency of the human-robot collaborative environment.
Among the physiological indices commonly used for the assessment of cognitive load and mental fatigue are heart rate (HR), heart rate variability (HRV), electroencephalography (EEG), metrics related to eye behaviors (e.g., pupil dilation, duration and frequency of fixations and blinks), functional near-infrared spectroscopy (fNIRS), and skin conductance response (SCR). In addition to these measures, subjective rating scales (e.g., NASA-TLX) and task performance metrics (e.g., accuracy, response time, and error rates) are considered. It’s important to note that no single index provides a comprehensive picture of cognitive load and mental fatigue. Often, a combination of various physiological and subjective measures is used to obtain a more accurate and complete assessment. Moreover, individual differences and contextual factors should be taken into account when interpreting the results.
This project aims to investigate some of these cognitive load indices during the execution of an assembly task in a controlled context and explore the interaction between these indices and the type of task (easy vs. difficult).

The present experimental study aims to examine potential variations in the level of cognitive load (MWL), reflected by modulations in eye behavior, due to changes in task difficulty. The experimental design is a repeated-measures design with two factors: single task (i.e., assembly/screwing) vs. dual task (i.e., assembly/screwing + backward counting). In addition to physiological measures, task performance metrics such as accuracy, response time, and error rates were evaluated, along with the subjective perception of mental workload through the administration of questionnaires (i.e., NASA-TLX).

Despite being emphasized that the construct of MWL is not easily circumscribable and that the variability in the meaning of the measures due to the specificity of each human being should be carefully considered, nevertheless, some of the analyzed physiological indices have been able to differentiate between a difficult task and an easier one. Subjective measures (effort perception, frustration, and decreased self-efficacy) and behavioral measures (performance decline) support this distinction. Identifying which index is a better predictor of performance, depending on task characteristics, information processing stage, and level of automation, could be a further step towards a “Human-centered” technology, where the outcome of the production process is guaranteed by the best level of collaboration among system elements, be they human operators or robots.


Mingardi, M., Pluchino, P., Bacchin, D., Rossato, C., & Gamberini, L. (2020). Assessment of implicit and explicit measures of mental workload in working situations: implications for industry 4.0. Applied Sciences10(18), 6416.

© Copyright 2023 Human Technology Lab - All Rights Reserved.