基于改进行为树的作战计划建模方法

doi:10.12305/j.issn.1001-506X.2023.04.19

摘要/Abstract

摘要：

针对网状结构作战计划模型存在调整效率低的问题, 提出一种基于改进行为树的作战计划建模方法。该方法在传统行为树的基础上, 通过扩充三层黑板结构实现模型内部节点之间的信息交互; 通过组合运用行为树相关组件构建作战任务及任务关系树状结构模型; 针对作战计划执行的特点, 改进行为树执行逻辑规则, 得到作战计划行为树模型。最后, 通过攻防对抗作战仿真实验进行了验证, 实验结果表明所提方法具有良好的可行性和动态调整性。

关键词: 作战计划, 行为树, 黑板结构, 动态调整

Abstract:

Aiming at the problems of low adjustment efficiency acquired by operational plan model of network structure, a modeling method of operational plan based on improved behavior tree is proposed. Based on the traditional behavior tree, the method realizes the information interaction between the internal nodes of the model by expanding the three-layer blackboard structure. By combining and using behavior tree related components, a tree structure model of operational task and task relationships is constructed. According to the characteristics of the execution of the operational plan, the execution syntax of the behavior tree is improved, and the operational plan behavior tree model is obtained. Finally, it is verified by the simulation experiment of offense and defense confrontation. The experimental results show that the proposed method has good feasibility and dynamic adjustment.

Key words: operational plan, behavior tree, blackboard structure, dynamic adjustment

中图分类号:

E211

袁博文, 刘东波, 刘兆鹏, 李雅楠. 基于改进行为树的作战计划建模方法[J]. 系统工程与电子技术, 2023, 45(4): 1111-1120.

Bowen YUAN, Dongbo LIU, Zhaopeng LIU, Yanan LI. Modeling method of operational plan based on improved behavior tree[J]. Systems Engineering and Electronics, 2023, 45(4): 1111-1120.

图/表 17

图1

图2

图3

图4

图5

图6

图7

图8

表1

表2

表3

图9

图10

图11

图12

图13

表4

参考文献 30

1	朱旋, 江泽强, 陈睿. 基于UML的联合作战方案计划可视化视图建模[J]. 指挥与控制学报, 2018, 4 (1): 73- 82. doi: 10.3969/j.issn.2096-0204.2018.01.0073
	ZHU X , JIANG Z Q , CHEN R . Modeling for joint operation planning visualization views based on UML[J]. Journal of Command and Control, 2018, 4 (1): 73- 82. doi: 10.3969/j.issn.2096-0204.2018.01.0073
2	United States Department of Defense. Core plan representation(CPR)[EB/OL]. [2022-01-23]. http://reliant.teknowledge.com/CPR2/.
3	POLYAK S, TATE A. Planning intiative: Shared planning and activity representation-SPAR version 0.2: request for comments[EB/OL]. [2019-3-23]. http://www.aiai.ed.ac.uk/~arpi/spar/spar-doc02.html.
4	United States Department of Defense. Joint publication 5-0: joint planning[EB/OL]. [2022-01-23]. http://www.dtic.mil/doctrine/jel/new_pubs/jp5_0.pdf.
5	毛翔, 杨晓波. 美军联合作战行动筹划及计划制定流程[M]. 北京: 军事科学出版社, 2017.
	MAO X , YANG X B . US joint operations planning and planning process[M]. Beijing: Military Science Press, 2017.
6	程恺, 陈刚, 尹成祥, 等. 作战行动序列核心本体建模及其推理方法[J]. 系统工程与电子技术, 2018, 40 (4): 805- 814.
	CHENG K , CHEN G , YIN C X , et al. Core ontology modeling and reasoning method for course of action[J]. Systems Engineering and Electronics, 2018, 40 (4): 805- 814.
7	MUNOZ P , KARKHANIS P . Modeling objects with uncertain behaviors[J]. Journal of Object Technology, 2021, 20 (3): 8.
8	FU C , LIU J H , WANG S D . Building SysML model graph to support the system model reuse[J]. IEEE Access, 2021, 9, 132374- 132389. doi: 10.1109/ACCESS.2021.3115165
9	SISO-STD-007-2008. Standard for military scenario definition language (MSDL)[S]. USA: Simulation Interoperability Standards Organization, 2008.
10	王锐. 基于网络计划图的联合作战方案建模与分析[D]. 长沙: 国防科技大学, 2018.
	WANG R. Modeling and analysis of joint operations based on network planning diagram[D]. Changsha: National University of Defense Technology, 2018.
11	GEORGIEVSKI I , AIELLO M . HTN planning: overview, comparison, and beyond[J]. Artificial Intelligence, 2015, 222, 124- 156. doi: 10.1016/j.artint.2015.02.002
12	XU X , YANG M , LI G . Adaptive CGF commander behavior modeling through HTN guided monte carlo tree search[J]. Journal of Systems Science and Systems Engineering, 2018, 27 (2): 231- 249. doi: 10.1007/s11518-018-5366-8
13	ZHOU J F , RENIERS G . Petri-net based simulation analysis for emergency response to multiple simultaneous large-scale Fires[J]. Journal of Loss Prevention in the Process Industries, 2016, 40, 554- 56. doi: 10.1016/j.jlp.2016.01.026
14	JIN X , WU F H . Autonomous intelligent decision-making system for humanoid soccer robots based on timed petri network[J]. Basic & Clinical Pharmacology & Toxicology, 2020, 127 (5): 126- 127.
15	DAN Y , OUSSAMA K , WANG S G . Computation of minimal siphons in Petri nets using problem partitioning approaches[J]. IEEE/CAA Journal of Automatica Sinica, 2022, 9 (2): 329- 338. doi: 10.1109/JAS.2021.1004326
16	MUKHERJEE K , RAY A . State splitting and merging in probabilistic finite state automata for signal representation and analysis[J]. Signal Processing, 2014, 104, 105- 119. doi: 10.1016/j.sigpro.2014.03.045
17	FERNANDEZ-ISABL , PEIXOTO P , DIEGO I M , et al. Combining dynamic finite state machines and text-based similarities to represent human behavior[J]. Engineering Applications of Artificial Intelligence, 2019, 85, 504- 516. doi: 10.1016/j.engappai.2019.07.006
18	FALZON L . Using Bayesian network analysis to support centre of gravity analysis in military planning[J]. European Journal of Operational Research, 2004, 170 (2): 629- 643.
19	JING L T , MA J F , XIE J , et al. A conceptual design decision approach by integrating rough Bayesian network and game theory under uncertain behavior selections[J]. Expert Systems With Applications, 2022, 202, 117108. doi: 10.1016/j.eswa.2022.117108
20	KIDD M . Applying Bayesian belief networks as a tool for structuring and evaluating the planning of nanval operations[J]. Military Operations Research, 2002, 7 (4): 25- 34. doi: 10.5711/morj.7.4.25
21	PUGA G F, GOMEZ-MARTIN M A, DIAZ-AGUDO B, et al. Dynamic expansion of behavior trees[C]//Proc. of the Artificial Intelligence and Interactive Digital Entertainment Conference, 2008: 22-24.
22	YANNICK F , BOUCHARD B , BOUCHARD K , et al. Modeling, learning, and simulating human activities of daily living with behavior trees[J]. Knowledge and Information Systems, 2020, 62 (10): 3881- 3910. doi: 10.1007/s10115-020-01476-x
23	RYAN M , HOWARD J . Behavior trees for modelling artificial intelligence in games: a tutorial[J]. The Computer Games Journal, 2017, 6 (3): 171- 184. doi: 10.1007/s40869-017-0040-9
24	WODECKI A. Influence of artificial intelligence on activities and competitiveness of an organization[M]. Artificial Intelligence in Value Creation. Springer, 2019, 10(3): 133-246.
25	ABIYEV R H , AKKAYA N , AYTAC E , et al. Robot soccer control using behavior trees and fuzzy logic[J]. Procedia Computer Science, 2016, 102 (C): 477- 484.
26	雷明剑, 于淼, 鲁赢. 作战任务协同过程形式化表达方法[J]. 装备学院学报, 2016, 27 (4): 96- 101.
	LEI M J , YU M , LU Y . Formalization description methods for operational coordination process[J]. Journal of Equipment Academy, 2016, 27 (4): 96- 101.
27	潘明聪, 贺毅辉, 徐伟, 等. 不确定性作战任务形式化描述方法[J]. 指挥控制与仿真, 2014, 36 (3): 28- 31.
	PAN M C , HE Y H , XU W , et al. Formal description for task allocation under uncertain environment[J]. Command Control and Simulation, 2014, 36 (3): 28- 31.
28	程恺, 车军辉, 张宏军, 等. 作战任务的形式化描述及其过程表示方法[J]. 指挥控制与仿真, 2012, 34 (1): 15- 19.
	CHENG K , CHE J H , ZHANG H J , et al. Formal description of operational task and its process expression[J]. Command Control and Simulation, 2012, 34 (1): 15- 19.
29	JIANG H B , LI S , LIN C , et al. Research on distributed target assignment based on dynamic allocation auction algorithm[J]. Journal of Physics: Conference Series, 2019, 1419 (1): 12001- 12011. doi: 10.1088/1742-6596/1419/1/012001
30	DUAN X J . A novel hybrid auction algorithm for multi-UAVs dynamic task assignment[J]. IEEE Access, 2020, 8, 86207- 86222.

阵营	武器装备	部署地	数量
红方	指挥所C	Area-1	1
红方	远程防空武器系统A1	Area-1	1
红方	近程防空武器系统A2	Area-1	1
红方	雷达站L	Area-1	1
红方	机场J-1	Area-1	1
红方	机场J-2	Area-2	1
红方	Y型预警机	J-1	2
红方	M1型战斗机	J-1	12
红方	M2型战斗机	J-2	16
红方	D型电子战飞机	J-2	8
红方	H1型驱逐舰	Area-1附近	2
红方	H2型巡洋舰	Area-1附近	2
蓝方	机场J-3	Area-3	1
蓝方	S1型驱逐舰	Area-4	2
蓝方	S2型巡洋舰	Area-4	2
蓝方	S3型航母	Area-4	1
蓝方	F1型战斗机	J-3	14
蓝方	R型侦察无人机	J-3	2
蓝方	F2型舰载战斗机	S3型航母	18
蓝方	E型预警机	S3型航母	2

计划序号	计划名称
1	高价值目标优先打击
2	最小损失摧毁Area-1
3	最短时间摧毁Area-1
4	均衡兵力任务分配

作战阶段	任务代号	任务说明	执行力量	作战阶段	任务代号	任务说明	执行力量
1	T1	预警机巡逻预警	Y_1	2	T13	Y型预警机区域探测	Y_2
1	T2	M1型战斗机为预警机Y_1护航	M1_1, M1_2	2	T14	M2型战斗机为预警机Y_1护航	M2_1, M2_2
1	T3	M1型战斗机区域巡逻	M1_3, M1_4	2	T15	M2型战斗机为预警机Y_2护航	M2_3, M2_4
1	T4	M1型战斗机区域巡逻	M1_5, M1_6	2	T16	M1型战斗机对空拦截作战范围敌方飞机	M1_1, M1_2, M1_3, M1_4
1	T5	M1型战斗机区域巡逻	M1_9, M1_10	2	T17	M1型战斗机对空拦截作战范围敌方飞机	M1_5, M1_6, M1_7, M1_8
1	T6	H1型驱逐舰对海空搜索警戒	H1_1, H1_2	2	T18	M1型战斗机对空拦截作战范围敌方飞机	M1_9, M1_10, M1_11, M1_12
1	T7	H2型巡洋舰海空搜索警戒	H2_1, H2_2	2	T19	D型电子战飞机支援M1型战斗机执行电子干扰任务	D_1
2	T8	远程防空武器系统A1自主防空拦截	A1	2	T20	D型电子战飞机支援M1型战斗机执行电子干扰任务	D_2
2	T9	近程防空武器系统A2自主防空拦截	A2	2	T21	D型电子战飞机支援M1型战斗机执行电子干扰任务	D_3
2	T10	H1型驱逐舰自主防空拦截	H1_1, H1_2	2	T22	M2型战斗机机动组成双机编队对敌方飞机进行拦截	M2_5, M2_6, …, M2_16
2	T11	H2型巡洋舰自主防空拦截	H2_1, H2_2	2	T23	D型电子战飞机支援M2型战斗机执行电子干扰任务	D_4, D_5, …, D_8
2	T12	Y型预警机区域探测	Y_1	-	-	-	-

模型	作战节点	逻辑节点	连接线
作战计划行为树	+2	+4	+8
作战网络图	+8	+5	+16

[1]	焦志强, 张杰勇, 姚佩阳, 王勋, 何宜超. 基于分层结构的C4ISR服务部署分布式演化方法[J]. 系统工程与电子技术, 2021, 43(6): 1572-1585.
[2]	程恺, 陈刚, 尹成祥, 康睿智, 康兴挡. 作战行动序列核心本体建模及其推理方法[J]. 系统工程与电子技术, 2018, 40(4): 805-814.
[3]	吴瑞杰, 孙鹏, 孙昱. 分布式任务计划动态调整模型及算法[J]. 系统工程与电子技术, 2017, 39(2): 322-328.
[4]	陈业华, 王浩, 宋之杰. 基于效用风险熵的突发事件应急方案动态调整[J]. 系统工程与电子技术, 2016, 38(9): 2093-2098.
[5]	张萌萌, 陈洪辉, 罗爱民, 刘俊先. 基于动态调整的C4ISR系统结构灵活性分析[J]. 系统工程与电子技术, 2016, 38(3): 563-568.
[6]	钱猛，刘忠，姚莉，张维明. 作战计划的本体建模研究[J]. Journal of Systems Engineering and Electronics, 2010, 32(5): 994-1000.