Please use this identifier to cite or link to this item:
Title: Modelling aircraft priority assignment by air traffic controllers during taxiing conflicts using machine learning
Authors: Vidurveer, Duggal
Keywords: Engineering::Aeronautical engineering::Aircraft
Engineering::Aeronautical engineering::Aviation
Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2022
Publisher: Nanyang Technological University
Source: Vidurveer, D. (2022). Modelling aircraft priority assignment by air traffic controllers during taxiing conflicts using machine learning. Final Year Project (FYP), Nanyang Technological University, Singapore.
Abstract: To cope with the rise in overall air traveller count, the structure of many airports is becoming increasingly more complex which has led to an increase in conflicts between taxiing aircraft. The conflicts are typically resolved by altering the path of one of the aircraft or making it wait or slow down. While automated tools have been used to perform conflict resolution, either in real-time or during the path planning stage, the decision on which aircraft should be given higher priority by the algorithm and continue on its path during conflicts is largely based on assumptions. The priority assignment method affects every conflict resolution decision made by the algorithm and hence has a significant impact on the operational efficiency of the airport. In reality, the decision made by an air traffic controller (ATC) on which aircraft to give higher priority is based on a multitude of factors and thus simple rules such as First Come First Serve (FCFS) are not practical. To tackle this problem, we propose a machine learning based framework to assign aircraft priority during taxiing conflicts that learns from actual ATC behaviour. We identify instances where an ATC deliberately makes an aircraft slow down to prevent a conflict with another aircraft and then use a Random Forest that can mimic how an ATC makes such a decision. Results show that the model is able to mimic ATC behaviour with an accuracy of 88.9% and can thus be an effective framework to use for priority assignment in path- planning and conflict resolution methods. Further analysis of the results shows that aircraft features such as unimpeded time difference, distance to destination, distance from start and speed are the major considerations which affect the ATC’s decision.
Schools: School of Mechanical and Aerospace Engineering 
Research Centres: Air Traffic Management Research Institute 
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:MAE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.18 MBAdobe PDFView/Open

Page view(s)

Updated on Feb 28, 2024

Download(s) 50

Updated on Feb 28, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.