Integrating Mental Workload Management in advanced Human-Machine Interaction: the development process of the Proof-Of-Concept to refine the concept

The research aims to investigate the impact of automation-induced mental workload (MWL) on worker performance and well-being. By leveraging AI techniques, it seeks to develop proactive strategies for managing MWL and optimizing human-machine collaboration in transformative factories. Drawing inspiration from Design Thinking, the development process involves creating a Proof-of-Concept (PoC) for an AI-based tool capable of real-time MWL assessment, prediction, and countermeasure suggestion. The PoC framework delineates three stages: real-time MWL assessment, prediction, and countermeasure suggestion. Data collection involves subjective, objective, and scenario-based metrics, including EEG signals and NASA Task Load Index ratings. The experimental protocol includes individual calibration sessions and workload assessments to validate the PoC's feasibility. The research presents a pioneering PoC for AI-driven MWL management, offering real-time insights and interventions to enhance operator performance and well-being. The study advocates for continued collaboration and innovation to address the multifaceted challenges of MWL management in automated environments.