Augmented Cognition using Real-time EEG-based Adaptive Strategies for Air Traffic Control

Abstract

Future air traffic systems aim at increasing both the capacity and safety of the system, necessitating the development of new metrics and advisory tools for controllers’ workload in real-time. Psychophysiologi-cal data such as Electroencephalography (EEG) are used to contrast and validate subjective assessments and workload indices. EEG used within augmented cognition systems form situation awareness advisory tools that are able to provide real-time feedback to air-traffic control supervisors and planners. This aug-mented cognition system and experiments using the system with air traffic controllers are presented. Traf-fic indicators are used in conjunction with EEG-driven cognitive indicators to adapt the traffic in real-time through Computational Red Teaming (CRT) based adaptive control mechanisms. The metrics, measures, and adaptive control mechanisms are described and evaluated. The best mechanism to improve system ef-ficacy was found when the system allowed for real-time adaptation of traffic based on engagement met-rics driven from the EEG data.