Skip to content

Atlas / Learn / Papers / 20060022173

NASA NTRS · Conference Paper

Using Neural Networks to Explore Air Traffic Controller Workload

Published 2019-07-12 From Ames Research Center 4 authors
Read paper (PDF) ↗ View on NASA NTRS ↗

Attribution

This is the abstract and citation. Full text lives at NASA NTRS — we link out rather than host. All credit to the authors and Ames Research Center.

Abstract

Verbatim from NASA NTRS. Not paraphrased, not summarized.

When a new system, concept, or tool is proposed in the aviation domain, one concern is the impact that this will have on operator workload. As an experience, workload is difficult to measure in a way that will allow comparison of proposed systems with those already in existence. Chatterji and Sridhar (2001) suggested a method by which airspace parameters can be translated into workload ratings, using a neural network. This approach was employed, and modified to accept input from a non-real time airspace simulation model. The following sections describe the preparations and testing work that will enable comparison of a future airspace concept with a current day baseline in terms of workload levels.

Authors

  • Martin, Lynne NASA Ames Research Center
  • Kozon, Thomas NASA Ames Research Center
  • Verma, Savita NASA Ames Research Center
  • Lozito, Sandra C. NASA Ames Research Center

Citation: Martin, Lynne, Kozon, Thomas, Verma, Savita , et al. (2019). Using Neural Networks to Explore Air Traffic Controller Workload. Ames Research Center. NASA NTRS ID 20060022173. https://ntrs.nasa.gov/citations/20060022173 ↗