Research on System and Application Framework of Tactical Wargaming Simulation Driven by AI4S

doi:10.16182/j.issn1004731x.joss.24-1039

Abstract

Abstract:

Tactical wargaming simulation, as a crucial tool for combat analysis, simulation training, and equipment demonstration and test, has become a significant means for generating combat effectiveness. Integrating AI into simulation not only enhances simulation efficiency but also diminishes reliance on humans. To assist professionals engaged in tactical wargaming simulation in mastering AI application methods, fostering a systematic mindset, and understanding evolving trends, this paper provided a concise overview of the principles behind AI for science (AI4S). Subsequently, it conducted an analysis of AI4S's application effectiveness in tactical wargaming simulation, established an AI4S-driven wargaming simulation system, and elucidated its composition, relationships, and architecture. It centered on the scope and framework of application, with a case of AI4S-driven land wargaming deduction and command training presented.

Key words: AI for Science(AI4S), tactical wargaming simulation, system composition, application framework

CLC Number:

TP391.9

Liu Dayong, Guo Qisheng, Dong Zhiming, Qiu Xuehuan, Liu Zhuoli. Research on System and Application Framework of Tactical Wargaming Simulation Driven by AI4S[J]. Journal of System Simulation, 2026, 38(2): 387-398.

Figures/Tables 14

Table 1

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Table 2

Experimental factors and levels

序号	因子	符号	因子水平
1	红方兵力编成	$C r e d$	编成 $C A$ ：3坦克+3步兵编成 $C B$ ：2坦克+4步兵编成 $C C$ ：1坦克+5步兵
2	红方兵力的配置	$L r e d$	布局 $L A$ ：分散配置布局 $L B$ ：动态配置
3	红方火力分配策略	$F r e d$	方案 $F A$ ：尽远拦截方案 $F B$ ：近距精打
4	蓝方夺控策略	$S b l u e$	策略 $S A$ ：要点随机游走策略 $S B$ ：优先打击对方策略 $S C$ ：优先占领要点

Table 2

Fig. 8

Fig. 9

Table 3

Four experimental subjects (Blue's strategy SB)

科目	$C r e d$	$L r e d$	$F r e d$	说明
P1	$C A$	$L A$	$F A$	坦克多，重点使用远程火力
P2	$C C$	$L A$	$F A$	步兵多，重点使用远程火力
P3	$C A$	$L A$	$F B$	坦克多，重点使用近程火力
P4	$C C$	$L A$	$F B$	步兵多，重点使用近程火力

Table 3

Fig. 10

Fig. 11

References 8

[1]	王飞跃, 缪青海. 人工智能驱动的科学研究新范式: 从AI4S到智能科学[J]. 中国科学院院刊, 2023, 38(4): 536-540.
[2]	孙坦, 张智雄, 周力虹, 等. 人工智能驱动的第五科研范式(AI4S)变革与观察[J]. 农业图书情报学报, 2023, 35(10): 4-32.
	Sun Tan, Zhang Zhixiong, Zhou Lihong, et al. The Transformation and Observations of AI for Science (AI4S) Driven by Artificial Intelligence[J]. Journal of Library and Information Science in Agriculture, 2023, 35(10): 4-32.
[3]	Miao Qinghai, Huang Min, Yisheng Lü, et al. Parallel Learning Between Science for AI and AI for Science: A Brief Overview and Perspective[C]//2022 Australian & New Zealand Control Conference (ANZCC). Piscataway: IEEE, 2022: 171-175.
[4]	陈怡. 可精准预测蛋白质结构的人工智能模型AlphaFold2开源: 《自然》曾称"它将改变一切!"[N]. 上海科技报, 2021-08-04(003).
[5]	王飞跃, 缪青海, 张军平, 等. 探讨AI for Science的影响与意义:现状与展望[J]. 智能科学与技术学报, 2023, 5(1): 1-6.
	Wang Feiyue, Miao Qinghai, Zhang Junping, et al. The DAOs to AI for Science by DeSci: The State of the Art and Perspective[J]. Chinese Journal of Intelligent Science and Technology, 2023, 5(1): 1-6.
[6]	徐忠富, 杨文, 熊杰. 美军联合红旗军演研究[J]. 指挥控制与仿真, 2014, 36(3): 137-142.
	Xu Zhongfu, Yang Wen, Xiong Jie. Research on Joint Red Flag Exercises of the US Army[J]. Command Control & Simulation, 2014, 36(3): 137-142.
[7]	杜国红. 美军作战概念开发特点及启示[J]. 国防科技, 2020, 41(4): 52-57.
	Du Guohong. The Characteristics of the Development of US Army Operational Concept and Its Implications[J]. National Defense Technology, 2020, 41(4): 52-57.
[8]	章乐贵, 陈希亮, 曹雷, 等. 智能蓝军作战行为模型构建技术研究[J]. 国防科技, 2022, 43(1): 14-20.
	Zhang Legui, Chen Xiliang, Cao Lei, et al. Model for the Operational Behavior of the Intelligent Blue Army of China[J]. National Defense Technology, 2022, 43(1): 14-20.

视角	AI4S赋能的博弈对抗仿真	传统战术仿真
对模型和系统开发人员要求	不高，主要是要求熟练掌握人工智能辅助建模、辅助实验的方法	较高，要熟练掌握相关建模与仿真的原理、技术、方法，要求会编写程序
建模时间成本	较低，随着建模方法和技术的提升，建模时间越来越短，效率越来越高	较高，从概念模型、数学模型到程序模型，都需要人员手动按部就班进行
仿真实验设计、准备、实施效率	较高	相对较低
仿真实验实施成本	根据需要，仿真加速比可以设置得非常高，因此时间成本低	受操控人员熟练程度和水平的限制，一般仿真倍速较低，因此时间成本高
对实验推演人员操作技能要求	很低，随着建模水平的提升，智能体可完成OODA所有环节	较高，整个OODA环中前3个环由人来完成
对人员的依赖	较低，智能体智能水平越高，人参与程度越低	较高，红蓝双方所有兵力需要人来控制

[1]	Dong Zhiming, Hu Zhongqi, Dai Haoran, Gao Jiancheng. An Automated Generation Method for Combat Simulation Scenarios Based on Large Language Models [J]. Journal of System Simulation, 2026, 38(5): 1129-1145.
[2]	Li Xiaonan, Chao Tao, Ma Ping, Yang Ming, Wang Yuxuan. Robust Identification of Black-box Nonlinear SSM Using Expectation-maximization [J]. Journal of System Simulation, 2026, 38(5): 1146-1158.
[3]	Liu Yingang, Ma Ming, Zhang Ronghua. Dynamic Task Planning for Wargaming Based on Large Language Models [J]. Journal of System Simulation, 2026, 38(5): 1187-1204.
[4]	Su Hongjia, Zhang Cheng, Liu Fei. SoS Effectiveness Evaluation Method Based on Fuzzy Functional Dependency Network Analysis [J]. Journal of System Simulation, 2026, 38(5): 1224-1238.
[5]	Mei Huawei, Yang Penghui, Yu Yang. Ultra-short-term Photovoltaic Power Prediction Based on Improved PatchTST Considering Data Drift [J]. Journal of System Simulation, 2026, 38(5): 1239-1254.
[6]	Li Quan, Su Peng, Wan Haiying, Zhang Chengxi, He Zhijian, Ni Yiyang, Zhao Zhonggai, Liu Fei. Modeling of Penicillin Fermentation Process Based on a Multi-stage LHS-EPRCC Method [J]. Journal of System Simulation, 2026, 38(5): 1255-1276.
[7]	Zhou Zicong, Zeng Junjie, Hu Yue, Zhu Zhengqiu, Yin Quanjun. Multi-agent Reinforcement Learning Method for Wargame Simulation Based on Suboptimal Demonstration Guidance [J]. Journal of System Simulation, 2026, 38(5): 1277-1289.
[8]	Shi Min, Guo Shisheng, Wang Suqin, Li Zhaoxin, Zhu Dengming. Annotation-free 6-DoF Grasp Detection Method Integrating Physical and Geometric Priors [J]. Journal of System Simulation, 2026, 38(5): 1290-1302.
[9]	Jiang Yanji, Xiao Xingyi, Dong Hao, Yu Miao, Huang Jinshan, Liu Daqian, Fei Bowen. Detection Method for 3D Lanes Based on Graph Relationship Optimization Integrating Point and Lane Features [J]. Journal of System Simulation, 2026, 38(5): 1303-1319.
[10]	Zhang Xin, Zhang Ping, Zhang Chen, Liu Wei, Han Boyang. Research on Calculation Model of Excavation Resistance Under Heterogeneous Soil Conditions [J]. Journal of System Simulation, 2026, 38(5): 1320-1332.
[11]	Wang Wei, Liu Dong, Cui Xinhao, Li Bo, Xiao Yiyong, Ren Yi. Multi-level Digital Model of Dynamic Earned Value Management for Complex Engineering Projects and Its Applications [J]. Journal of System Simulation, 2026, 38(5): 1350-1364.
[12]	Peng Lijun, Su Tingqi, Liu Peijin, He Lin, Zhou Xiewu, Zhang Minxin. Detection Method for Laboratory PPE Compliance Wearing Based on Human Key Points [J]. Journal of System Simulation, 2026, 38(5): 1365-1382.
[13]	Teng Jing, Tong Wencong, Zhang Zhongjie, Yao Xing, Li Junxian. Automatic Speed Guidance Method and Simulation Evaluation for Trams at Intersections [J]. Journal of System Simulation, 2026, 38(5): 1426-1439.
[14]	Jiang Shengchao, Pei Yunqing, Zhai Hongying, Wu Guojian, Gao Fang. Power Flow Calculation Based on Block-encoded Adiabatic Quantum Newton-Raphson Method [J]. Journal of System Simulation, 2026, 38(5): 1453-1465.
[15]	Qin Lang, Xie Jiacheng, Qiao Xiaojun, Wang Xuewen, Xiao Zhijie. Robot Trajectory Planning and Adjustment Method for Abnormal Pose of Actuator [J]. Journal of System Simulation, 2026, 38(5): 1466-1483.