基于概率图的作战任务智能规划方法

doi:10.3969/j.issn.1001-506X.2020.12.16

系统工程与电子技术 ›› 2020, Vol. 42 ›› Issue (12): 2795-2801.doi: 10.3969/j.issn.1001-506X.2020.12.16

基于概率图的作战任务智能规划方法

王泊涵^1,²(), 吴超²(), 柯文俊^2,^3,⁴(), 郑恺之^3,⁴(), 付修锋²(), 江山²()

1. 国防科技大学系统工程学院, 湖南长沙 410073
2. 北京计算机技术及应用研究所, 北京 100854
3. 中国科学院计算技术研究所, 北京 100190
4. 中国科学院大学计算机学院, 北京 100049

收稿日期:2020-01-12 出版日期:2020-12-01 发布日期:2020-11-27
作者简介:王泊涵(1987-),男,高级工程师,博士研究生,主要研究方向为系统工程、人工智能、云计算。E-mail:cnpeking@qq.com|吴超(1981-),男,高级工程师,硕士,主要研究方向为计算数学、软件工程。E-mail:837247904@qq.com|柯文俊(1990-),男,高级工程师,博士研究生,主要研究方向为自然语言处理。E-mail:kewenjun2191@163.com|郑恺之(1996-),男,硕士研究生,主要研究方向为人工智能。E-mail:zkzwin@126.com|付修锋(1985-),男,高级工程师,硕士,主要研究方向为软件测试、软件工程。E-mail:fenger_casic@126.com|江山(1994-),男,工程师,硕士,主要研究方向为人工智能、软件工程。E-mail:619575254@qq.com
基金资助:
装备发展部预先研究项目(31510010501)

Intelligent planning method of combat mission based on probability graph

Bohan WANG^1,²(), Chao WU²(), Wenjun KE^2,^3,⁴(), Kaizhi ZHENG^3,⁴(), Xiufeng FU²(), Shan JIANG²()

1. College of Systems Engineering, National University of Defense Technology, Changsha 410073, China
2. Beijing Institute of Computer Technology and Application, Beijing 100854, China
3. Institute of Computing Technology, Chinese Academy of Sciences, Beijing 100190, China
4. College of Computer Science, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2020-01-12 Online:2020-12-01 Published:2020-11-27

摘要/Abstract

摘要：

针对人工调配作战资源及规划方案效率低下的问题，本文提出一种基于概率图的作战任务智能规划方法，通过统计分析判定任务间因果关系，采用GNN抽取任务中的关键事件构建概率图并计算任务规划方案成功的概率，进而基于时间序列方法预测战场态势变化，实现辅助指挥员智能决策。最后，本文在某联合登岛案例中开展了方法验证，结果表明，所提出的方法可成功实现任务规划并具有可解释性，可实现对战场态势变化的预测和快速响应，在战场上为军队提供强有力的支持。

关键词: 战场态势, 可解释性, 概率图, GNN, 时间序列预测

Abstract:

In view of the low efficiency of manual allocation of combat resources and planning scheme, an intelligent planning method of combat tasks is proposed based on probability graph. The causality between tasks is determined by statistical analysis, and the key events in the task are extracted by using graph neural network (GNN) to construct probability diagram and calculate the success probability of mission planning scheme. Then, the change of battlefield situation can be predicted and the commander can be assisted to achieve intelligent decision based on the time series method. Finally, the method verification is carried out in a joint landing case. The results show that the proposed method can realize the mission planning successfully with interpretability, the prediction and rapid response of the battlefield situation changes, and provide strong support for the army in the battlefield.

Key words: battlefield situation, interpretability, probability graph, graph neural network (GNN), time series prediction

中图分类号:

TP181

王泊涵, 吴超, 柯文俊, 郑恺之, 付修锋, 江山. 基于概率图的作战任务智能规划方法[J]. 系统工程与电子技术, 2020, 42(12): 2795-2801.

Bohan WANG, Chao WU, Wenjun KE, Kaizhi ZHENG, Xiufeng FU, Shan JIANG. Intelligent planning method of combat mission based on probability graph[J]. Systems Engineering and Electronics, 2020, 42(12): 2795-2801.

图/表 9

图1

表1

图2

图3

图4

图5

表2

图6

图7

参考文献 30

1	杜思良, 韩家启, 张永亮, 等. 陆军战术级作战任务智能规划技术研究[J]. 舰船电子工程, 2018, 38 (12): 30- 34.
	DU S L , HAN J Q , ZHANG Y L , et al. Research on intelligent operational task planning for army tatical forces[J]. Ship Electronic Engineering, 2018, 38 (12): 30- 34.
2	LAI Y H, LAI S H. Emotion-preserving representation learning via generative adversarial network for multi-view facial expression recognition[C]//Proc.of the IEEE 13th International Conference on Automatic Face & Gesture Recognition, 2018: 263-270.
3	HORVITZ E J , BREESE J S , HENRION M . Decision theory in expert systems and artificial intelligence[J]. International Journal of Approximate Reasoning, 1988, 2 (3): 247- 302. doi: 10.1016/0888-613X(88)90120-X
4	ELIE R, RICHARD C, ALBERT D. User profile matching in social networks[C]//Proc.of the 13th International Conference on Network-Based Information Systems, 2010: 297-304.
5	CHEN L C , PAPANDREOU G , KOKKINOS I , et al. DeepLab: semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs[J]. IEEE Trans.on Pattern Analysis & Machine Intelligence, 2018, 40 (4): 834- 848.
6	SCARSELLI F , GORI M , TSOI A C , et al. The graph neural network model[J]. IEEE Trans.on Neural Networks, 2009, 20 (1): 61- 80.
7	COHEN P R , KAISER E C , BUCHANAN M C , et al. Sketch-thru-plan: a multimodal interface for command and control[J]. Communications of the ACM, 2013, 58 (4): 56- 65.
8	SCHIELZETH H . Simple means to improve the interpretability of regression coefficients[J]. Methods in Ecology & Evolution, 2010, 1 (2): 103- 113.
9	PENG T, XU R, ZHAO F Y. Variable durative actions based mission planning for the approach phase of small body explorer[C]//Proc.of the 3rd International Conference on Intelligent Control and Information Processing, 2012: 114-119.
10	JOSÉ A G , ANTONIO S . Probabilistic graphical models[J]. International Journal of Intelligent Systems, 2003, 18 (2): 149- 151. doi: 10.1002/int.10081
11	BHARDWAJ S, WANG W P, VATTIKONDA R, et al. Predictive modeling of the NBTI effect for reliable design[C]//Proc.of the IEEE Custom Integrated Circuits Conference, 2006: 189-192.
12	LIN A C , LI J , MA Z Y . On learning and learned data representation by capsule networks[J]. IEEE Access, 2019, 7, 50808- 50822. doi: 10.1109/ACCESS.2019.2911622
13	DING M Z, CHEN Y H, BRESSLER L, et al. Granger causality: basic theory and application to neuroscience[EB/OL].[2020-01-07].https://doi.org/10.1002/9783527609970. ch17, 2006.
14	SHIVAKUMAR N , JANNINK J , WIDOM J . Per-user profile replication in mobile environments: algorithms, analysis, and simulation results[J]. Mobile Networks & Applications, 1997, 2 (2): 129- 140.
15	OLLILA E . On the circularity of a complex random variable[J]. IEEE Signal Processing Letters, 2019, 15 (1): 841- 844.
16	BAHLMANN C, BURKHARDT H. Measuring HMM similarity with the Bayes probability of error andits application to online handwriting recognition[C]//Proc.of the International Conference on Document Analysis & Recognition: Seattle, 2001: 406-411.
17	MIHALJEVIC B , BIELZA C , LARRANAGA P . Bnclassify: learning Bayesian network classifiers[J]. The R Journal, 2019, 10 (2): 455- 468.
18	HUELSENBECK J P , RONQUIST F . MRBAYES: Bayesian inference of phylogenetic trees[J]. Bioinformatics, 2001, 17 (8): 754- 755. doi: 10.1093/bioinformatics/17.8.754
19	OLAIZOLA N , VALENCIANO F . Dominance of weighted nested split graph networks in connections models[J]. International Journal of Game Theory, 2020, 49, 75- 96. doi: 10.1007/s00182-019-00676-2
20	THOMANN A , GRIEBE M , EBERT M , et al. Aberrant brain structural large-scale connectome in Crohn's disease[J]. Journal of Crohns & Colitis, 2019, 1 (13): 279- 280.
21	CHEN J R , LI Z K . Common fixed-points for Banach operator pairs in best approximation[J]. Journal of Mathematical Analysis and Applications, 2007, 336 (2): 1466- 1475. doi: 10.1016/j.jmaa.2007.01.064
22	ZHU Y, CHEN J. Studies on genetic multilayer feedforward neural networks and the development of GMNN[C]//Proc.of the International Conference on Systems, Man, and Cybernetics, 1999: 401-406.
23	SUTTON R S , BARTO A G . Reinforcement Learning[J]. A Bradford Book, 1998, 15 (7): 665- 685.
24	WANG Y C , LI M T , PAN Z C , et al. Pulsar candidate classification with deep convolutional neural networks[J]. Research in Astronomy and Astrophysics, 2019, 19 (9): 133- 142. doi: 10.1088/1674-4527/19/9/133
25	TABARI N , BISWAS P , PRANEETH B , et al. Causality analysis of twitter sentiments and stock market returns[J]. Association for Computational Linguistics, 2018, 18 (5): 11- 19.
26	ZHANG S, LIU X, XIAO J. On geometric features for skeleton-based action recognition using multilayer LSTM networks[C]//Proc.of the Applications of Computer Vision, 2017: 148-157.
27	SHI X, CHEN Z, WANG H, et al. Convolutional LSTM network: a machine learning approach for precipitation nowcasting[C]//Proc.of the 28th International Conference on Neural Information Processing Systems, 2015: 802-810.
28	RAMKUMAR N, PRAKASH S, KUMAR S A, et al. Prediction of liver cancer using conditional probability Bayes theorem[C]//Proc.of the International Conference on Computer Communication and Informatics, 2017.
29	ELSTON R C , LANGE K . The prior probability of autosomal linkage[J]. Annals of Human Genetics, 1975, 38 (3): 341- 350. doi: 10.1111/j.1469-1809.1975.tb00619.x
30	LEE V J , OW S , HEAH H , et al. Elimination of malaria risk through integrated combination strategies in a tropical military training island[J]. American Journal of Tropical Medicine & Hygiene, 2010, 82 (6): 1024- 1029.

序号	元素	含义
1	对象	感兴趣的目标事物
2	谓语	感兴趣的对象特征,可以是正向的也可以是负向的
3	初始态	整个系统初始的状态
4	目标细节	想要达到的目的
5	动作	改变整个系统状态的方式

动作	联合登岛	相似案例	聚类结果
动作1	北滩夺取	登岛部队登陆	夺取陆地权
动作2	防御地空导弹攻击	炮兵火力打击	夺取制空权
动作3	北滩火力支援	火箭炮兵群射击	分支作战线路防御

[1]	王宁, 李哲, 梁晓龙, 王玉冰, 侯岳奇. 通信距离受限条件下的无人机集群协同区域搜索[J]. 系统工程与电子技术, 2022, 44(5): 1615-1625.
[2]	田睿, 董绪荣. 小波分解与Prophet框架融合的电离层VTEC预报模型[J]. 系统工程与电子技术, 2021, 43(3): 610-622.
[3]	黄杰, 孙伟, 高渝. 双属性概率图优化的无人机集群协同目标搜索[J]. 系统工程与电子技术, 2020, 42(1): 118-127.
[4]	范庚，马登武，吴明辉，孟上. 电子系统状态时间序列预测的优化相关向量机方法[J]. 系统工程与电子技术, 2013, 35(9): 2011-2015.
[5]	张磊，李行善，于劲松，万九卿. 基于关联向量机回归的故障预测算法[J]. Journal of Systems Engineering and Electronics, 2010, 32(7): 1540-1543.
[6]	蒋宏, 任章. 一种基于SGNN网络的模糊图像融合算法[J]. Journal of Systems Engineering and Electronics, 2009, 31(2): 452-455.

基于概率图的作战任务智能规划方法

Intelligent planning method of combat mission based on probability graph

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 9

参考文献 30

相关文章 6

编辑推荐

Metrics

本文评价