The primary objective of this study is to incorporate the deep reinforcement learning (DRL) technique in conflict detection and resolution (CD&R) control strategies to generate an optimised trajectory for air traffic controllers as reference, in order to improve efficiency and reduce the amount of heading angle change. A DRL environment which can be applied to CD&R agent training is developed. The agent receives the current state of multiple aircrafts in a sector and generates an action to change the heading angle of an aircraft to avoid conflict. A K-Control Actor-Critic algorithm is proposed to limit the number of control times and a two-dimensional continuous action selection policy is utilised. The simulation results show the feasibility of DRL applied in CD&R and there is an obvious advantage in computational efficiency.
Deep reinforcement learning based conflict detection and resolution in air traffic control
IET Intelligent Transport Systems ; 13 , 6 ; 1041-1047
2019-02-21
7 pages
Article (Journal)
Electronic Resource
English
k-control actor-critic algorithm , conflict detection and resolution control , optimised trajectory , aircraft control , continuous action selection , learning (artificial intelligence) , aircraft heading angle , trajectory optimisation (aerospace) , multi-agent systems , CD&R control , multiple aircrafts , air traffic control , deep reinforcement learning
Metadata by IET is licensed under CC BY 3.0
Deep reinforcement learning based conflict detection and resolution in air traffic control
Wiley | 2019
|Conflict resolution strategy based on deep reinforcement learning for air traffic management
BASE | 2023
|Conflict resolution strategy based on deep reinforcement learning for air traffic management
DOAJ | 2023
|