Skip to main content
Towards Industry 5.0 and wearables device adoption in industry

Towards Industry 5.0 and wearables device adoption in industry

The digital representation of production systems is getting very relevant in the last decade. Nowadays there are countless examples of machinery and process monitoring solutions to monitor machines, processes and factories, including Digital Twins (DTs) [1]. However, the continuously evolving needs of manufacturing end-users require also to represent humans in the digital world, including their intents, behaviours and conditions, realising the so-called Human Digital Twins (HDTs) [2]

Wearable devices (also referred to as wearables) play a fundamental role when HDTs are applied to monitoring applications. Indeed, the raising of advanced, precise, and low-cost sensors on-boarded on wearables enable the collection and processing of human physiological data to support analytics in a variety of applications [3]. Wearables are a category of electronic devices that can be worn as accessories, embedded in clothing, or even implanted in humans’ bodies. Wearables are crucial to enable the Industry 5.0 paradigm, which revolves around the concepts of HDTs and Human-Cyber-Physical systems to facilitate human-machine cooperation.

Different types of wearables are available in the market, including smartwatches, smart clothing, and smart glasses, on-boarding different sensors to fulfil different needs, e.g., fitness assistants, health monitoring, GPS/sport tracking. Bringing wearables to manufacturing production systems opens to several opportunities: (i) tracking and monitoring operators’ performance, behaviours and conditions; (ii) supporting operator activities through innovative interfaces and support systems. For example, physiological data from wearables has been used for the estimation of workers’ exertion and mental stress, enabling the adaptation of collaborative robots’ behaviour [4].

In STAR, SUPSI is developing an AI-based solution to estimate the physical fatigue exertion of workers based on physiological data and operators’ characteristics. Dealing with this goal, one of the challenges faced by the research team was:

“Which is the best wearable to be applied in an industrial context for human fatigue detection?”

The large wearables market makes it difficult to immediately identify the devices best suited for a specific industrial application. This challenge is recurrent in almost all the projects where researchers, industrial experts, and companies embrace I5.0, where the demand for technology selection methods and approaches is increasing. However, common practices and guidelines are still lacking.

As a result of the STAR project, SUPSI’s research team proposed a methodology for selecting wearables suitable for I5.0 applications, which is very easy to adopt thanks to its practicality and business-oriented approach.

The methodology has been presented by Elias Montini at ETFA 2022 in Stuttgart during the special session “Industry 5.0 – Augmenting the Human Worker in Balanced Automation Systems” organised by Tamás Ruppert (University of Pannonia), and David Romero (Tecnológico de Monterrey).


[1] G. Mylonas, A. Kalogeras, G. Kalogeras, C. Anagnostopoulos, C. Alexakos, and L. Mu˜noz, “Digital twins from smart manufacturing to smart cities: A survey,” IEEE Access, vol. 9, pp. 143 222–143 249, 2021.

[2] E. Montini, N. Bonomi, F. Daniele, A. Bettoni, P. Pedrazzoli, E. Carpanzano, and P. Rocco, “The human-digital twin in the manufacturing industry: Current perspectives and a glimpse of future,” in Trusted Artificial Intelligence in Manufacturing: A Review of the Emerging Wave of Ethical and Human Centric AI Technologies for Smart Production,J. Soldatos and D. Kyriazis, Eds. Now Publishers, 2021, ch. 7.

[3] E. Montini, A. Bettoni, M. Ciavotta, E. Carpanzano, and P. Pedrazzoli, “A meta-model for modular composition of tailored human digital twins in production,” Procedia CIRP, vol. 104, pp. 689–695, 2021.

[4] A. Bettoni, E. Montini, M. Righi, V. Villani, R. Tsvetanov, S. Borgia, C. Secchi, and E. Carpanzano, “Mutualistic and adaptive human-machine collaboration based on machine learning in an injection moulding manufacturing line,” Procedia CIRP, vol. 93, pp. 395–400, 2020, 53rd CIRP Conference on Manufacturing Systems 2020.


By: Vincenzo Cutrona, Elias Montini (SPS lab @ SUPSI)