Conference Agenda

Work-related musculoskeletal disorders remain widespread and costly, while traditional ergonomic assessment methods are limited by subjectivity, time demands, and sparse temporal sampling. Inertial Measurement Unit (IMU)-based motion capture offers a scalable solution for continuous monitoring, although professional systems are often too expensive for widespread use. This study investigates the suitability of an affordable IMU system, Perception Neuron 3 (PN), for objective ergonomic risk assessment. A dedicated algorithmic pipeline was developed to extract upper-limb kinematics and automatically compute OCRA indices and the Revised NIOSH Lifting Equation. The evaluation followed a two-step approach: laboratory tests compared PN with a professional reference system (Xsens MVN Awinda), while industrial tests benchmarked algorithm-derived outputs against expert ergonomic assessments. Results show a high correlation between PN and Xsens for joint angles and NIOSH geometric parameters, with discrepancies remaining within acceptable ranges for ergonomic applications. On-field comparisons reveal systematic differences between automated and observational assessments, mainly due to continuous kinematic measurement versus visual estimation, as well as interobserver variability in manual procedures. Overall, the findings support the feasibility of using affordable IMU systems for automated ergonomic evaluation in industrial environments, while highlighting the need for further refinement and validation for full integration into ergonomic assessment workflows.

Air Traffic Controllers (ATCOs) constantly work under critical and stressful conditions as they are requested to maintain a high level of alertness and situation awareness to manage air traffic safely. The recent increase in air traffic has directly impacted ATCOs tasks by increasing the volume of traffic to be managed. Consequently, controllers perceive higher fatigue and cognitive load, intensifying the Human Factors challenges intrinsic to the profession. In this context, the aim of this work is to provide a comprehensive approach to Human Factors in the domain of Air Traffic Control and to examine the diverse evaluation methodologies available aiming at designing a standardized evaluation plan for Human Factors Assessments. A streamlined pipeline workflow is proposed, consisting of five assessment modules: objective definition, context and task analysis, metrics modules, data collection and analysis. The metrics modules step in the methodology enables adaptability by allowing modular integration of specific human performance metrics. The aspects regarding human performance considered include workload, situation awareness, system usability, human error and systems design.

Traditional craftsmanship often works for prolonged hours in restrictive envi-ronments where ergonomic standards are frequently overlooked. Despite high job satisfaction, craftsmen face significant physical risks due to non-standardized rest hours, hand tools and non-uniform lighting. This study ad-dresses a critical literature gap by conducting comprehensive visual and postur-al risk analysis within independent workshops. Following an initial workplace assessment questionnaire, postural risks were quantified using the Rapid Upper Limb Assessment (RULA) framework based on real-world cases. To minimize musculoskeletal risks and optimize visual performance, illumination measure-ments were also considered. Based on these findings, optimized workstation layouts that align workshop orientation with available light sources and improve tool accessibility are proposed. The results demonstrate that high job satisfac-tion often masks underlying physical strain, highlighting the urgent need for de-tailed ergonomic studies for craftsmen. This study presents a framework for im-proving health and safety that can be adopted in similar work environments such as tailoring and custom shoemaking workshops.

Quantitative ergonomic assessment in real workplaces requires

portable methods capable of reconstructing workers’ movements

without substantially constraining task execution. This study presents

a pilot wearable-driven workflow for subject-specific whole-body musculoskeletal

modelling within OpenSim. A custom model was developed by

integrating validated trunk (FBLS), upper-limb (ARM41), and lowerlimb

(GAIT2354) components. Kinematic data were acquired from 10

healthy participants using the Xsens MVN Awinda system during three

manual material handling tasks: symmetric lifting, asymmetric lifting,

and overhead lifting. A reduced set of 44 virtual markers was defined,

and the weights of 32 biomechanically relevant markers were optimized

through a multi-stage particle swarm optimization procedure. Scaling

was successfully completed for all participants in both N-pose and T-pose

configurations. The N-pose yielded a lower optimization cost (0.1162 vs.

0.1236) and lower mean RMS marker error (2.74 vs. 2.92 cm). Joint-level

comparison with native Xsens kinematics showed the highest agreement

during symmetric lifting, with shoulder correlation up to R = 0.919,

whereas agreement decreased during more complex overhead movements.

These findings support the workflow as a preliminary kinematic foundation

for future wearable-based ergonomic assessment.

The transition toward Industry 5.0 is promoting the adoption of human-centered manufacturing approaches aimed at balancing automation efficiency with operator well-being and social sustainability. In this context, the present study investigates the impact of alternative semi-automated workstation layouts on both physical and cognitive ergonomics within a heat exchanger production system. Three operational configurations were analyzed and compared with previous manual and semi-automated solutions. Physical ergonomics was assessed through motion-capture-based RULA analysis using the Xsens MVN Awinda system, while cognitive ergonomics was evaluated through physiological stress monitoring based on heart rate, RR interval, and electrodermal activity acquired using an Empatica EmbracePlus wearable device. Results showed that the integration of conveyor-based fixtures and dedicated support stations significantly reduced biomechanical exposure, particularly by minimizing manual handling and trunk flexion. However, the reduction of physical workload was partially associated with increased supervisory and attentional demands, especially in the most automated configuration. The study demonstrates that collaborative automation primarily redistributes operator workload between physical and cognitive dimensions rather than eliminating it. The proposed human-centered design approach provides useful insights for the development of sustainable and ergonomically optimized Industry 5.0 manufacturing systems.

The assessment of Mental Workload (MWL) is a key re-

quirement in Industry 5.0 environments, where operators engage in in-

creasingly complex cognitive tasks. This paper presents a real-time, fully

causal eye-tracking-based framework for continuous MWL feature gener-

ation, relying exclusively on gaze and pupillometry signals from a wear-

able device. The framework integrates subject-specific baseline normal-

isation, online artefact handling, and sliding-window aggregation into a

modular pipeline under strict causality constraints, without offline post-

processing or additional sensors. Eleven features capturing pupil dynam-

ics, baseline-relative variations, temporal derivatives, and spatial gaze de-

scriptors are generated at 1 Hz. Evaluated on N = 13 quasi-independent

recordings through a modified n-back paradigm with five progressively

demanding sessions, the pipeline achieved a median feature acceptance

rate of 99.1% (IQR 99.1-99.2%) across 65 sessions. A Friedman test on

N = 12 subjects (independent observations) revealed a significant ses-

sion effect (χ2(4) = 14.53, p = 0.006, Kendall’s W = 0.30), reflecting

sensitivity to progressive cognitive demand. The proposed framework

provides a scalable and non-invasive approach for MWL feature gener-

ation, combining literature-grounded causal integration with wearable-

only deployability, supporting integration into adaptive human-machine

systems within Industry 5.0 contexts.