Seamless Human–Robot Collaborative Assembly Using Artificial Intelligence and Wearable Devices

Abstract

Seamless human–robot collaboration requires the equipping of robots with cognitive capabilities that enable their awareness of the environment, as well as the actions that take place inside the assembly cell. This paper proposes an AI-based system comprised of three modules that can capture the operator and environment status and process status, identify the tasks that are being executed by the operator using vision-based machine learning, and provide customized operator support from the robot side for shared tasks, automatically adapting to the operator’s needs and preferences. Moreover, the proposed system is able to assess the ergonomics in human–robot shared tasks and adapt the robot pose to improve ergonomics using a heuristics-based search algorithm. An industrial case study derived from the elevator manufacturing sector using a high payload collaborative robot is presented to demonstrate that collaboration efficiency can be enhanced through the use of the discussed system.

Ergonomics and Human Factors as a Requirement to Implement Safer Collaborative Robotic Workstations: A Literature Review

“…Figure 2 shows the number of articles per country. Our results allow us to say that the country where more studies have been developed in this field is Italy [1,12,[27][28][29][30][31][32][33], followed by the USA [8,34], United Kingdom [18,35], France [11,31], and Greece [22,36]. In the rest of the countries, only one study per country was found.…”

“…Regarding the year of publication, our study shows that the oldest paper presented in this review dates to 2013 [31] (Figure 3). Moreover, the largest number of studies found have been published in 2021 [11,12,19,22,27,32,33,37,38]. These two findings point ou that E&HF as a requirement in HRC systems is an emergent/recent research topic.…”

“…Another finding from our study is related to the ergonomics domain, namely physical or cognitive, and related to its ergonomic application, if offline or online (Figure 5). Sixteen [1,4,7,8,13,17,19,22,[27][28][29][30][31]36,37,40] of nineteen studies are related to physical ergonomics, while only six [11,32,34,35] are related to cognitive ergonomics. Regarding its application, only studies related to physical ergonomics presented an online application [1,12,18,22,33,38,40].…”

“…Sixteen [1,4,7,8,13,17,19,22,[27][28][29][30][31]36,37,40] of nineteen studies are related to physical ergonomics, while only six [11,32,34,35] are related to cognitive ergonomics. Regarding its application, only studies related to physical ergonomics presented an online application [1,12,18,22,33,38,40]. These studies, in which an online application was implemented, aim for workers' postural improvement by modifying the Cobot's behaviour to bring the human operator to a more ergonomic body configuration.…”

“…These instruments deal with an emerging issue: the worker assessment in dynamic environments. In addition to dealing with the improvement of the operator posture, these applications also care to provide the robot with the cognitive ability to communicate with the operator in real-time and make a job a true collaboration [22]. Ranavolo et al [5] performed a literature review to investigate the need for revising the standards for human ergonomics and biomechanical risk assessment.…”