Real-time adaptive automation for performance enhancement of operators in a human-machine system

This paper presents a new framework for studies into the on-line monitoring and adaptive control of psychophysiological markers relating to human operators working under stress. The starting point of this framework is the assessment of compromised operator functional state (OFS) using physiological and behavioral markers of strain. A fuzzy model linking Heart-Rate Variability (HRV) and Task Load Index (TLI) with the operators' optimal performance has been elicited and validated via a series of real-time experiments involving process control tasks simulated on an AutomationEnhanced Cabin Air Management System (AUTOCAMS). The model predicts the possibility that AUTOCAMS will drift to an abnormality because of the operator's poor level of mental control, as a result of fatigue from exhausting workload. The elicited model has been used as the basis for an on-line control system, whereby the model predictions which indicate whether the actual system is in error, or not, have been used by a handcrafted fuzzy decision-maker to modify the level of automation which the system may operate under. Preliminary results showed that the system was partially effective for most of the operators tested, but there were large individual differences.