We present a computational cognitive model of novice and expert aviation pi
lot action planning called ADAPT that models performance in a dynamically c
hanging simulated flight environment. We perform rigorous tests of ADAPT's
predictive validity by comparing the performance of individual human pilots
to that of their respective models. Individual pilots were asked to execut
e a series of flight maneuvers using a flight simulator, and their eye fixa
tions and control movements were recorded in a time-synched database. Compu
tational models of each of the 25 individual pilots were constructed, and t
he individual models simulated execution of the same flight maneuvers perfo
rmed by the human pilots. The time-synched eye fixations and control moveme
nts of individual pilots and their respective models were compared, and rig
orous tests of ADAPT's predictive validity were performed. The model explai
ns and predicts a significant portion of pilot visual attention and control
movements during flight as a function of piloting expertise. Implications
for adaptive training systems are discussed.