The field of human–robot collaboration (HRC) still lacks research studies regarding the evaluation of mental workload (MWL) through objective measurement to assess the mental state of operators in assembly tasks. This research study presents a comparative neuroergonomic analysis to evaluate the mental workload and productivity in three laboratory experimental conditions: in the first, the participant assembles a component without the intervention of the robot (standard scenario); in the second scenario, the participant performs the same activity in collaboration with the robot (collaborative scenario); in the third scenario, the participant is fully guided in the task in collaboration with the robot (collaborative guided scenario) through a system of guiding labels according to Poka-Yoke principles. The assessment of participants’ mental workload is shown through combinative analysis of subjective (NASA TLX) and objective (electroencephalogram—EEG). Objective MWL was assessed as the power waves ratio β/α (Beta—stress indicator, Alpha—relaxation indicator). Furthermore, the research used observational measurements to calculate the productivity index in terms of accurately assembled components across the three scenarios. Through ANOVA RM, mental workload significantly decreased in the activities involving the cobot. Also, an increase in productivity was observed shifting from the manual scenario to the cobot-assisted one (18.4%), and to the collaborative guided scenarios supported by Poka-Yoke principles (33.87%).

Despite significant advancements in Electroencephalography (EEG)-based Mental Workload (MWL) assessment facilitated by deep learning, challenges such as subject-independent MWL estimation persist. Addressing this challenge is crucial for the widespread adoption of the technology in practical, real-world settings. It could facilitate the deployment of neuroadaptive systems across various users without the need for individual calibration, significantly reducing setup time and complexity, and enhancing the scalability. This study explores subject-independent MWL estimation under realistic conditions of a typical assembly line workplace, as opposed to the idealized settings typical of existing research. We employed a convolutional neural network (CNN) to classify 10s EEG segments into two MWL categories, based on different complexity of visual instructions for manual assembly. The results in subject-dependent and subject-independent cases were compared. The findings reveal only a marginal decrease in classification accuracy when transitioning from subject-dependent (92.2 ^% ) to subject-independent scenarios (90.8%). The study demonstrates the feasibility of using deep learning models for EEG-based MWL estimation under realistic conditions, paving the way for broader applications of this technology across diverse industrial environments.

The main aim of this research paper is to improve the effectiveness of production processes through ergonomic optimization of industrial workstations where workers perform repetitive, monotonous assembly tasks. The study analyzes the impact of applying ergonomic and lean principles, standard of “the golden zone standard” in the design of assembly workstations on participants’ brain activity and productivity, as well as on the quality of the final products in traditional (non-ergonomic) and ergonomic scenario. The results indicated significant differences in brain activity patterns between the two scenarios, revealing higher levels of mental workload during assembly tasks in the non-ergonomic scenario for all participants. Furthermore, improvements in production processes were observed, including increased productivity; specifically, the average mental workload was reduced by approximately 35% in the ergonomic scenario, accompanied by an approximately 5% increase in productivity and an approximately 8% reduction in working time. The obtained results provide a foundation for improving the design of assembly workstations in industrial environments, as well as contributing to a broader understanding of the importance of ergonomics in the optimization of industrial processes.

In the modern contemporary environment, simultaneous monitoring of physical and mental strain is very important in order to improve ergonomic conditions and the health of workers. This research paper presents a multimodal approach to assessing the physical and mental strain of workers during assembly activities. The proposed model combines the RULA (Rapid Upper Limb Assessment) method for assessing ergonomic risk and the EEG (electroencephalography) method for evaluating mental strain. Through an experimental study conducted on a sample of 7 subjects, the implications of assuming certain body postures on the physical and cognitive state of the subjects were analyzed. The results indicated a significant association between the adoption of non-physiological and non-ergonomic body postures and increased mental effort, which indicates the need for an integrated assessment when designing ergonomic workplaces. The results obtained showed that the application of ergonomic principles contributes to the reduction of physical and mental strain. The results also confirm that high levels of physical strain lead to changes in the brain activity of the subjects that correspond to increased mental effort. The proposed approach can serve as a basis for the development of advanced systems for monitoring and optimizing worker performance and well-being.

Up to 60 percentages of realized costs in warehouses can be attributed to the collection of ordered products. As the use of robots expands, the research aims to reduce operating costs and make robots more efficient in warehouses. In this regard, it is necessary to optimize the robot's path in the warehouse. The emphasis is on Autonomous Mobile agents, a type of intelligent vehicle that can perceive its environment. Autonomous Mobile Robot path planning is formulated as a Travelling Salesman Problem. In the paper, the goal of Travelling Salesman Problem is to minimize travel distance. Due to the problem’s complexity, the robot’s path was planned using a Genetic Algorithm. The optimal path is determined in the warehouse where certain products need to be loaded and delivered for further transport.

Operations managers and engineers in the automotive industry confront the key challenge in ensuring the reliability of the manufacturing process. To accurately classify failure modes, this study proposed a novel Multi-Criteria Decision-Making (MCDM) model integrated with Single-Valued Neutrosophic Sets (SVNSs) for operations management to prioritize actions in eliminating failure modes that had the greatest impact on the concerned reliability. The identification and evaluation of failure modes were grounded in the conventional Failure Mode and Effect Analysis (FMEA), while the relative importance of risk factors (RFs) was expressed through predefined linguistic terms modelled with the SVNSs. The assessment of these risk factors was formulated as a fuzzy group decision-making problem and the fuzzy weight vector was derived from the Order Weighted Averaging (OWA) operator. Failure rankings were conducted through a modified version of the Elimination and Choice Translating Reality (ELECTRE) method; being tested and validated with real-world data from an automotive company, the proposed FMEA-ELECTRE model could inspire stakeholders in various industries to explore this scientific contribution further.