Detection of Pilot Errors in Data by Combining Task Modeling and Model Checking

摘要

In this paper we show a consistent approach of using Hierarchical Task Analysis together with model checking to identify pilot errors during the interaction with cockpit automation systems in aircraft. Task analysis is used to model flight procedures which describe how to operate a specific system in a particular situation. Afterwards model checking is used to identify deviations from these procedures in empirical simulator data. We envision applying this method to automatically detect pilot errors during flight tests or pilot training.