Adaptive Automation Based on Air Traffic Controller Decision-Making
Martijn IJtsma (Student TU Delft)
C Borst (TU Delft - Control & Simulation)
G.A. Mercado Velasco (TU Delft - Control & Simulation)
M Mulder (TU Delft - Control & Operations)
MM van Paassen (TU Delft - Control & Simulation)
More Info
expand_more
Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.
Abstract
Through smart scheduling and triggering of automation support, adaptive automation has the potential to balance air traffic controller workload. The challenge in the design of adaptive automation systems is to decide how and when the automation should provide support. This paper describes the design of a novel mechanism for adaptively invoking automation support. Whereas most adaptive automation support systems are reactive in that they invoke automation support after controller workload has increased, the aim of the designed mechanism is to proactively trigger automation support prior to workload increases. To do this, the mechanism assesses the quality of air traffic controller's decisions. The designed adaptive automation system has been tested in a human-in-the-loop experiment. Results indicate that the adaptive support helps to increase efficiency and safety as compared to manual control. However, lower triggering thresholds (resulting in more frequent automation intervention) increased the frustration level of participants (as measured with NASA TLX) and decreased acceptance of the support.