异构MAS结构下的空天资源多阶段协同任务规划方法

李军; 李军; 钟志农; 景宁; 胡卫东

doi:10.7527/S1000-6893.2013.0284

航空学报 >

2013 , Vol. 34 >Issue 7: 1682 - 1697

DOI: https://doi.org/10.7527/S1000-6893.2013.0284

电子与控制

异构MAS结构下的空天资源多阶段协同任务规划方法

李军 ,
李军 ,
钟志农 ,
景宁 ,
胡卫东

展开

国防科学技术大学电子科学与工程学院, 湖南长沙 410073

李军,男,博士研究生。主要研究方向:空天协同规划,多智能体技术,传感器网络。Tel:0731-84574439,E-mail:lijun@nudt.edu.cn;李军,男,博士,教授。主要研究方向:卫星任务规划,地理信息系统。Tel:0731-84574439,E-mail:junli@nudt.edu.cn

收稿日期: 2012-08-27

修回日期: 2012-11-09

网络出版日期: 2012-11-29

基金资助

国家自然科学基金(61174159, 61101184)

收起

Space-air Resources Multi-phase Cooperation Task Planning Approach Based on Heterogeneous MAS Model

LI Jun ,
LI Jun ,
ZHONG Zhinong ,
JING Ning ,
HU Weidong

Expand

College of Electronic Science and Engineering, National University of Defense Technology, Changsha 410073, China

Received date: 2012-08-27

Revised date: 2012-11-09

Online published: 2012-11-29

Supported by

National Natural Science Foundation of China (61174159, 61101184)

Fold

摘要

利用空天资源的互补优势进行协同观测是对地观测领域的新趋势。为提高对地观测效益和多阶段观测任务的完成度,分析了空天资源协同观测任务规划问题中的观测资源异构性和多阶段观测任务分解方式的多样性。针对卫星和无人机的任务规划模型不一致的特点,建立了异构多智能体系统(MAS)多阶段协同任务规划模型,根据模型特点将问题求解分解为两个协商过程,并分别提出了基于市场模型的异构MAS多阶段协同任务规划算法和基于自适应"超级步"的资源Agent协同任务规划算法。最后,研究了该方法在空天资源联合观测中的应用情况,实验及分析结果表明该方法能够有效解决空天资源对地观测协同任务规划问题。

关键词： 空天协同; 遥感; 多智能体系统; 马尔可夫过程; 规划算法; 市场模型

本文引用格式

李军 , 李军 , 钟志农 , 景宁 , 胡卫东 . 异构MAS结构下的空天资源多阶段协同任务规划方法[J]. 航空学报, 2013 , 34(7) : 1682 -1697 . DOI: 10.7527/S1000-6893.2013.0284

Abstract

Coordinated observation of air and space assets is the trend of earth observation and it is expected to continue in the future. In order to increase the information gain of earth observation and improve the completion ratio of multi-phase missions, this paper analyzes the heterogeneity of observation resources and the diversity of decompositions for complex observation missions. Considering the differences between a satellite task planning model and an airplane task planning model, a heterogeneous multi-agent system (MAS) multi-phase cooperative planning model is constructed. Based on this model, the problem solving process is divided into two coordinated parts. A heterogeneous MAS multi-phase cooperative planning algorithm based on the market model, and a resource agent cooperative planning algorithm based on the adaptive "Super Step" theory are proposed. Finally, the above method is used to solve the joint observation problemof air and space assets. Experiment and analysis show that the proposed approach can solve the problem effectively.

Key words： space-air cooperation; remote sensing; multi-agent system; Markov process; scheduling algorithm; market model

参考文献

[1] Bröring A, Echterhoff J, Jirka S, et al. New generation sensor web enablement. Sensors, 2011, 11(3): 2652-2699.
[2] Wang C. Distributed cooperative task planning research of earth observing satellites based on agent. Changsha: College of Electronic Science and Engineering, National University of Defense Technology, 2012. (in Chinese) 王冲. 基于Agent的对地观测卫星分布式协同任务规划研究.长沙: 国防科学技术大学电子科学与工程学院, 2012.
[3] Horling B, Lesser V. A survey of multi-agent organizational paradigms. Knowledge Engineering Review, 2004, 19(4): 281-316.
[4] Badawy R, Hirsch B, Albayrak S. Agent-based coordination techniques for matching supply and demand in energy networks. Integrated Computer-Aided Engineering, 2010, 17(4): 373-382.
[5] de Jong S, Tuyls K, Verbeeck K. Fairness in multi-agent systems. Knowledge Engineering Review, 2008, 23(2): 153-180.
[6] Olfati-Saber R, Fax J A, Murray R M. Consensus and cooperation in networked multi-agent systems. Proceedings of the IEEE, 2007, 95(1): 215-233.
[7] Confessore G, Giordani S, Rismondo S. A market-based multi-agent system model for decentralized multi-project scheduling. Annals of Operations Research, 2003: 27-38.
[8] Dias M B, Zlot R, Kalra N, et al. Market-based multirobot coordination: a survey and analysis. Proceedings of the IEEE, 2006, 94(7): 1257-1270.
[9] Ma M H. Research on decomposition of earth observing satellite reconnaissance task and resource matching. Changsha: College of Information System and Management, National University of Defense Technology, 2010. (in Chinese) 马满好. 卫星成像侦察任务分解与资源匹配方法研究.长沙: 国防科学技术大学信息系统与管理学院, 2010.
[10] Goldman C V, Zilberstein S. Optimizing information exchange in cooperative multi-agent systems. Proceedings of the Second International Joint Conference on Autonomous Agents and Multiagent Systems, 2003: 137-144.
[11] Bernstein D S, Zilberstein S, Immerman N. The complexity of decentralized control of Markov decision processes. Uncertainty in Artificial Intelligence Proceedings, 2000: 32-7.
[12] Wu F. MAS planning approach based on game theory. Hefei: University of Science and Technology of China, 2011. (in Chinese) 吴锋. 基于决策理论的多智能体系统规划问题研究. 合肥: 中国科学技术大学, 2011.
[13] Merton R K. The Matthew effect in science. Science, 1968, 159(3810): 56-63.
[14] Merton R K. The Matthew effect in science, II: cumulative advantage and the symbolism of intellectual property. ISIS, 1988, 79(4): 606-623.
[15] Culler D E, Karp R M, Patterson D, et al. LogP: a practical model of parallel computation. Communications of the ACM, 1996, 39(11): 78-85.
[16] Labrou Y, Finin T, Peng Y. Agent communication languages: the current landscape. IEEE Intelligent Systems and their Applications, 1999, 14(2): 45-52.
[17] Beak S W, Han S M, Cho K R, et al. Development of a scheduling algorithm and GUI for autonomous satellite missions. Acta Astronautica, 2011, 68(7-8): 1396-1402.
[18] Barbulescu L, Howe A, Whitley D. AFSCN scheduling: How the problem and solution have evolved. Mathematical and Computer Modeling, 2006, 43(9-10): 1023-1037.
[19] Huo X H. Research on modeling and rolling optimization methods for multi-UCAV dynamic cooperative mission planning. Changsha: College of Mechatronics Engineering and Automation, National University of Defense Technology, 2007. (in Chinese) 霍霄华. 多UCAV 动态协同任务规划建模与滚动优化方法研究. 长沙:国防科学技术大学机电工程与自动化学院, 2007.
[20] Bellifemine F, Caire G, Greenwood D. Developing multi-agent systems with JADE. Chichester: John Wiley & Sons, Ltd., 2007: 1-114.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献