CONFLICT RESOLUTION STRATEGY BASED ON DEEP REINFORCEMENT LEARNING FOR AIR TRAFFIC MANAGEMENT
Aviation · 19.10.2023 · 27 (3) · 177-186
DOI: 10.3846/aviation.2023.19720 ↗Kurz gefasst
Fachartikel in der Zeitschrift Aviation, erschienen am 19.10.2023. Verfasst von Dong Sui und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 33 Literaturangaben.
Abstract (Originalsprache)
With the continuous increase in flight flows, the flight conflict risk in the airspace has increased. Aiming at the problem of conflict resolution in actual operation, this paper proposes a tactical conflict resolution strategy based on Deep Reinforcement Learning. The process of the controllers resolving conflicts is modelled as the Markov Decision Process. The Deep Q Network algorithm trains the agent and obtains the resolution strategy. The agent uses the command of altitude adjustment, speed adjustment, or heading adjustment to resolve a conflict, and the design of the reward function fully considers the air traffic control regulations. Finally, simulation experiments were performed to verify the feasibility of the strategy given by the conflict resolution model, and the experimental results were statistically analyzed. The results show that the conflict resolution strategy based on Deep Reinforcement Learning closely reflected actual operations regarding flight safety and conflict resolution rules.
Zitieren
APA
Sui, D., Ma, C., & Dong, J. (2023). CONFLICT RESOLUTION STRATEGY BASED ON DEEP REINFORCEMENT LEARNING FOR AIR TRAFFIC MANAGEMENT. Aviation, 27(3), 177-186. https://doi.org/10.3846/aviation.2023.19720
Vancouver
Sui D, Ma C, Dong J. CONFLICT RESOLUTION STRATEGY BASED ON DEEP REINFORCEMENT LEARNING FOR AIR TRAFFIC MANAGEMENT. Aviation. 2023;27(3):177-186. doi:10.3846/aviation.2023.19720
BibTeX
@article{Sui2023,
author = {Sui, Dong and Ma, Chenyu and Dong, Jintao},
title = {CONFLICT RESOLUTION STRATEGY BASED ON DEEP REINFORCEMENT LEARNING FOR AIR TRAFFIC MANAGEMENT},
journal = {Aviation},
year = {2023},
volume = {27},
number = {3},
pages = {177--186},
doi = {10.3846/aviation.2023.19720}
}
EUVIMED