帮助 关于我们

返回检索结果

Learning Scalable Task Assignment with Imperative-Priori Conflict Resolution in Multi-UAV Adversarial Swarm Defense Problem

查看参考文献38篇

Zhao Zhixin 1,2   Chen Jie 1,2   Xin Bin 3,4 *   Li Li 1,2   Jiao Keming 1,2   Zheng Yifan 1,2  
文摘 The multi-UAV adversary swarm defense (MUASD) problem is to defend a static base against an adversary UAV swarm by a defensive UAV swarm. Decomposing the problem into task assignment and low-level interception strategies is a widely used approach. Learning-based approaches for task assignment are a promising direction. Existing studies on learning-based methods generally assume decentralized decision-making architecture, which is not beneficial for conflict resolution. In contrast, centralized decision-making architecture is beneficial for conflict resolution while it is often detrimental to scalability. To achieve scalability and conflict resolution simultaneously, inspired by a self-attention-based task assignment method for sensor target coverage problem, a scalable centralized assignment method based on self-attention mechanism together with a defender-attacker pairwise observation preprocessing (DAP-SelfAtt) is proposed. Then, an imperative-priori conflict resolution (IPCR) mechanism is proposed to achieve conflict-free assignment. Further, the IPCR mechanism is parallelized to enable efficient training. To validate the algorithm, a variant of proximal policy optimization algorithm (PPO) is employed for training in scenarios of various scales. The experimental results show that the proposed algorithm not only achieves conflict-free task assignment but also maintains scalability, and significantly improve the success rate of defense.
来源 Journal of Systems Science and Complexity ,2024,37(1):369-388 【核心库】
DOI 10.1007/s11424-024-4029-8
关键词 Conflict resolution ; reinforcement learning ; scalability ; task assignment
地址

1. School of Electronics and Information Engineering,Tongji University, Shanghai, 201804  

2. Shanghai Institute of Intelligent Science and Technology,Tongji University, Shanghai, 201804  

3. School of Automation,Beijing Institute of Technology, Beijing, 100081  

4. National Key Laboratory of Autonomous Intelligent Unmanned Systems, National Key Laboratory of Autonomous Intelligent Unmanned Systems, Beijing, 100081

语种 英文
文献类型 研究性论文
ISSN 1009-6124
学科 自动化技术、计算机技术;航空
基金 supported in part by the National Natural Science Foundation of China Basic Science Research Center Program ;  国家自然科学基金 ;  中国航空科学基金 ;  Shanghai Municipal Science and Technology Major Project ;  Chinese Academy of Engineering, Strategic Research and Consulting Program
文献收藏号 CSCD:7659317

参考文献 共 38 共2页

1.  He C. Leader-following formation tracking for multiple quadrotor helicopters over switching networks. Unmanned Systems,2023 CSCD被引 2 次    
2.  Liu Y. Quantized Formation Control of Heterogeneous Nonlinear Multi-Agent Systems with Switching Topology. Journal of Systems Science & Complexity,2023,36(6):2382-2397 CSCD被引 3 次    
3.  Gao Z Y. Fixed-Time Leader-Following Formation Control of Fully-Actuated Underwater Vehicles Without Velocity Measurements. Journal of Systems Science & Complexity,2022,35(2):559-585 CSCD被引 4 次    
4.  Liao J. UAV swarm formation reconfiguration control based on variable-stepsize MPC-APCMPIO algorithm. Science China Information Sciences,2023,66(11):212207 CSCD被引 3 次    
5.  Pang Z. Analysis of stealthy false data injection attacks against networked control systems: Three case studies. Journal of Systems Science & Complexity,2023,36(4):1407-1422 CSCD被引 4 次    
6.  Liu Y. A survey of multi-agent systems on distributed formation control. Unmanned Systems,2023 CSCD被引 2 次    
7.  Li N. Optimization of air defense system deployment against reconnaissance drone swarms. Complex System Modeling and Simulation,2023,3(2):102-117 CSCD被引 1 次    
8.  Zhou J. Adversarial swarm defense with decentralized swarm, Master's degre thesis,2021 CSCD被引 1 次    
9.  Jaderberg M. Human-level performance in 3D multiplayer games with population-based reinforcement learning. Science,2019,364:859-865 CSCD被引 52 次    
10.  Vinyals O. Grandmaster level in StarCraft II using multiagent reinforcement learning. Nature,2019,575:350-354 CSCD被引 189 次    
11.  Zhou Q. Intelligent anti-jamming communication for wireless sensor networks: A multi-agent reinforcement learning approach. IEEE Open Journal of the Communications Society,2021,2:775-784 CSCD被引 5 次    
12.  Wu T. Multi-agent deep reinforcement learning for urban traffic light control in vehicular networks. IEEE Transactions on Vehicular Technology,2020,69:8243-8256 CSCD被引 17 次    
13.  Chu T. Multi-agent deep reinforcement learning for large-scale traffic signal control. IEEE Transactions on Intelligent Transportation Systems,2020,21:1086-1095 CSCD被引 51 次    
14.  Huang L. A deep reinforcement learning-based method applied for solving multi-agent defense and attack problems. Expert Systems with Applications,2021,176:114896 CSCD被引 12 次    
15.  Pope A P. Hierarchical reinforcement learning for air combat at DARPA's AlphaDogfight trials. IEEE Transactions on Artificial Intelligence,2022,4(6):1-15 CSCD被引 1 次    
16.  Zhou W J. Hierarchical control of multi-agent reinforcement learning team in real-time strategy (RTS) games. Expert Systems with Applications,2021,186:115707 CSCD被引 2 次    
17.  Xing D. Offense-defense confrontation decision making for dynamic UAV swarm versus UAV swarm. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering,2019,233:5689-5702 CSCD被引 11 次    
18.  Lowe R. Multi-agent actor-critic for mixed cooperative-competitive environments. Advances in Neural Information Processing Systems,2017 CSCD被引 11 次    
19.  Sun Z. Multi-agent air combat with two-stage graph-attention communication. Neural Computing and Applications,2023,35:19765-19781 CSCD被引 2 次    
20.  Chen Y. Scalable and transferable reinforcement learning for multi-agent mixed cooperative-competitive environments based on hierarchical graph attention. Entropy,2022,24:563 CSCD被引 2 次    
引证文献 1 篇

1 闫循良 基于LSTM-DDPG的再入制导方法 系统工程与电子技术,2025,47(1):268-279
CSCD被引 0 次

显示所有1篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护：中国科学院文献情报中心
地址：北京中关村北四环西路33号 邮政编码：100190 联系电话：(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号