Loading...

Adaptive Maneuvers for Aircraft Conflict Resolution Using Learning Theory

Mamizadeh, Zahra | 2022

137 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 55335 (45)
  4. University: Sharif University of Technology
  5. Department: Aerospace Engineering
  6. Advisor(s): Malaek, Mohammad Bagher
  7. Abstract:
  8. The problem of detection and resolution of aircraft collisions is very important due to the increasing demand for flights. Many algorithms have been developed in the past to increase automation in air traffic management and reduce the workload of air traffic controllers. These algorithms either have difficulty in generalizing to real problems or have high computational costs and do not correspond to the reality of the actual maneuvering characteristics of the aircraft performance. The aim of present study is to obtain dynamic maneuvers that are adaptive with reality and also optimal in terms of utilizing the capacity of flight sectors, so we propose Deep Reinforcement Learning(DRL) based on PPO algorithm including DNN such as Actor and Critic networks. To address multiple encountered airplanes and to adapt with ATCs approach in solving the conflicts, we classify the encountering situations into four regions according to the ICAO. Also, resolution maneuvers are based on Rules of Air of ICAO. In each category the nearest aircraft is known as the intruder. In order to validate the proposed algorithm, various types of interference in the continuous environment are simulated. The simulation results show that the types of pairwise and multiple aircraft conflicts are solved with the least deviation from the predefined trajectory and the aircrafts return to their predefined trajectory after the conflicts are solved. In addition, the proposed approach demonstrates its excellent adaptability to unknown complex environments with various encountered airplane.

  9. Keywords:
  10. Collision Avoidance ; Deep Reinforcement Learning ; Crash Avoidance Maneuver ; Actor-Critic Model ; Conflict Detection ; Conflict Resolution ; Airplane Dynamic Maneuver

 Digital Object List

 Bookmark

No TOC