Transactions of Nanjing University of Aeronautics & Astronautics
Autonomous Conflict Resolution (AutoCR) Based on Improved Multi-agent Reinforcement Learning
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
Conflict resolution （CR） is a fundamental component of air traffic management， where recent progress in artificial intelligence has led to the effective application of deep reinforcement learning （DRL） techniques to enhance CR strategies. However， existing DRL models applied to CR are often limited to simple scenarios. This approach frequently leads to the neglect of the high risks associated with multiple intersections in the high-density and multi-airport system terminal area （MAS-TMA）， and suffers from poor interpretability. This paper addresses the aforementioned gap by introducing an improved multi-agent DRL model that adopted to autonomous CR （AutoCR） within MAS-TMA. Specifically， dynamic weather conditions are incorporated into the state space to enhance adaptability. In the action space， the flight intent is considered and transformed into optimal maneuvers according to overload， thus improving interpretability. On these bases， the deep Q-network （DQN） algorithm is further improved to address the AutoCR problem in MAS-TMA. Simulation experiments conducted in the “Guangdong-Hong Kong-Macao” greater bay area （GBA） MAS-TMA demonstrate the effectiveness of the proposed method， successfully resolving over eight potential conflicts and performing robustly across various air traffic densities.
Keywords:
Project Supported:
This work was supported by the Postgraduate Research & Practice Innovation Program of Jiangsu Province （No.KYCX25_0621）， and the Foundation of Interdisciplinary Innovation Fund for Doctoral Students of Nanjing University of Aeronautics and Astronautics（No.KXKCXJJ202507）.
Clc Number:
V355
Articles
Mobile website
