Learning the Task Management Space of an Aircraft Approach Model
Joseph Krall, Tim Menzies, Misty Davies · 2015
Validating models of airspace operations is a particu-lar challenge. These models are often aimed at finding and exploring safety violations, and aim to be accurate representations of real-world behavior. However, the rules governing the behavior are quite complex: non-linear physics, operational modes, human behavior, and stochastic environmental concerns all determine the re-sponses of the system. In order to quantify uncertainty in the model (and by extension, risk in the real world), one recently successful methodology has been to de-velop a response surface replacement for the original model, and to learn the behavior of the system from the response surface. In this paper, we present a study on aircraft runway approaches as modeled in Geor-gia Tech’s Work Models that Compute (WMC) simu-lation. We use a new learner, Genetic-Active Learning for Search-Based Software Engineering (GALE) to dis-cover the Pareto frontiers defined by cognitive struc-tures. These cognitive structures organize the prioriti-zation and assignment of tasks of each pilot during ap-proaches. We discuss the benefits of our approach, and also discuss future work necessary to enable uncertainty quantification. The Motivation—Complexity in Aerospace Complexity that works is built of modules that work perfectly, layered one over the other. –Kevin Kelly The current complexity of the National Airspace System (NAS) causes consternation. At one level within the NAS, each airplane is an intricate piece of machinery with both mechanical and electrical linkages between its many com-ponents. Engineers and operators must constantly decide which components and interactions within the airplane can be neglected. As one example, the algorithms that control the heading of aircraft are usually based on linearized ver-sions of the actual (very nonlinear) dynamics of the aircraft in its environment. (Blakelock 1991) At another level within the NAS, each airplane must in-teract with other airplanes and the environment. For in-stance, weather can cause simple disruptions to the flow Copyright c 2013, Association for the Advancement of Artificial