Graph Reinforcement Learning for Multi-Aircraft Conflict Resolution
文献类型：期刊论文
| 作者 | Li, Yumeng1; Zhang, Yunhe1; Guo, Tong1; Liu, Yu2,3 ; Lv, Yisheng4; Du, Wenbo1
|
| 刊名 | IEEE TRANSACTIONS ON INTELLIGENT VEHICLES
 |
| 出版日期 | 2024-03-01 |
| 卷号 | 9期号:3页码:4529-4540 |
| 关键词 | Aircraft Air traffic control Decision making Atmospheric modeling Intelligent vehicles Scalability Reinforcement learning Conflict resolution graph reinforcement learning air traffic management |
| ISSN号 | 2379-8858 |
| DOI | 10.1109/TIV.2024.3364652 |
| 通讯作者 | Du, Wenbo(wenbodu@buaa.edu.cn) |
| 英文摘要 | The escalating density of airspace has led to sharply increased conflicts between aircraft. Efficient and scalable conflict resolution methods are crucial to mitigate collision risks. Existing learning-based methods become less effective as the scale of aircraft increases due to their redundant information representations. In this paper, to accommodate the increased airspace density, a novel graph reinforcement learning (GRL) method is presented to efficiently learn deconfliction strategies. A time-evolving conflict graph is exploited to represent the local state of individual aircraft and the global spatiotemporal relationships between them. Equipped with the conflict graph, GRL can efficiently learn deconfliction strategies by selectively aggregating aircraft state information through a multi-head attention-boosted graph neural network. Furthermore, a temporal regularization mechanism is proposed to enhance learning stability in highly dynamic environments. Comprehensive experimental studies have been conducted on an OpenAI Gym-based flight simulator. Compared with the existing state-of-the-art learning-based methods, the results demonstrate that GRL can save much training time while achieving significantly better deconfliction strategies in terms of safety and efficiency metrics. In addition, GRL has a strong power of scalability and robustness with increasing aircraft scale. |
| WOS关键词 | DYNAMIC ENVIRONMENTS ; AVOIDANCE ; VEHICLE |
| 资助项目 | National Key R&D Program of China |
| WOS研究方向 | Computer Science ; Engineering ; Transportation |
| 语种 | 英语 |
| WOS记录号 | WOS:001214544700016 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Key R&D Program of China |
| 源URL | [http://ir.ia.ac.cn/handle/173211/58385]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队 |
| 通讯作者 | Du, Wenbo |
| 作者单位 | 1.Beihang Univ, Sch Elect & Informat Engn, Beijing 100191, Peoples R China 2.Naval Aviat Univ, Inst Informat Fus, Yantai 264001, Peoples R China 3.Tsinghua Univ, Dept Elect Engn, Beijing 100083, Peoples R China 4.Chinese Acad Sci, Inst Automat, Beijing 100045, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Yumeng,Zhang, Yunhe,Guo, Tong,et al. Graph Reinforcement Learning for Multi-Aircraft Conflict Resolution[J]. IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,2024,9(3):4529-4540. |
| APA | Li, Yumeng,Zhang, Yunhe,Guo, Tong,Liu, Yu,Lv, Yisheng,&Du, Wenbo.(2024).Graph Reinforcement Learning for Multi-Aircraft Conflict Resolution.IEEE TRANSACTIONS ON INTELLIGENT VEHICLES,9(3),4529-4540. |
| MLA | Li, Yumeng,et al."Graph Reinforcement Learning for Multi-Aircraft Conflict Resolution".IEEE TRANSACTIONS ON INTELLIGENT VEHICLES 9.3(2024):4529-4540. |
入库方式： OAI收割
来源：自动化研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。