Research on Real-time CGF Maneuvering State Generation Method Based on Random Finite Set

doi:10.16182/j.issn1004731x.joss.24-0433

Abstract

Abstract:

With the rapid development of sensor networks and other technologies, the acquisition of measurement data in the real physical space has become easier. How to utilize the measurement data from the real battlefield space to improve the accuracy and credibility of CGF simulation is the key issue to realize the CGF simulation combining virtual and real. The method is studied of using real measurement data to generate CGF model maneuvering state data in real time, in order to realize the virtual-real synchronization and real-time mapping between the real battlefield and CGF simulation system, and to provide environmental inputs for the self-help planning decision-making behavior of CGF.A stochastic finite-set based modeling method for simulation and measurement models is given. A PHD/MIB(probability hypothesis density/multi-instance bernoulli) filter based CGF maneuvering state prediction correction method is designed, and an efficient real-time solver for the proposed state generation method is given by applying various techniques such as SMC, GPU and D-S evidence theory in a comprehensive way. The accuracy and effectiveness of the proposed method is verified by a case study of land operation simulation.

Key words: computer generated force(CGF), maneuver state generation, random finite set(RFS), situational awareness, D-S theory of evidence

CLC Number:

TP391.9

Zhang Xiaoyan, Li Ge, Wang Peng. Research on Real-time CGF Maneuvering State Generation Method Based on Random Finite Set[J]. Journal of System Simulation, 2025, 37(9): 2211-2224.

Figures/Tables 13

Fig. 1

Fig. 2

Fig. 3

Table 1

Experimental parameter configuration table

参数	参数值
网格地图边长/m	50
网格边长/m	0.2
粒子总数 $v$	$3 × 106$
新生粒子数量 $v b$	$3 × 105$
持续存在概率 $p S$	0.99
位置噪声的标准差 $σ p$ /(m $⋅$ s/T)	0.1
速度噪声的标准差 $σ v$ /(m $⋅$ s²/T)	1
新生粒子速度的标准差 $σ B, v$ /(m/s)	30
新生概率 $p B$	0.02
自由空间折扣因子 $α$	0.01
传感器视角/(°)	120
传感器分辨率/m	0.2
传感器测量误差标准差/m	0.5

Table 1

Table 2

Table 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

References 16

[1]	刘飞, 赖鹏, 陆营波, 等. 作战仿真混合实验方案设计研究[J]. 系统仿真学报, 2024, 36(3): 735-742.
	Liu Fei, Lai Peng, Lu Yingbo, et al. Research on Hybrid Experimental Scheme Design for Combat Simulation[J]. Journal of System Simulation, 2024, 36(3): 735-742.
[2]	孔晨妍, 崔鹏. 联合作战仿真实验设计方法研究[C]//第八届中国指挥控制大会论文集. 北京: 中国指挥与控制学会, 2020: 674-679.
	Kong Chenyan, Cui Peng. Research on Simulation Experiment Method in Joint Operations[C]//Proceedings of the 8th China Conference on Command and Control. Beijing: Chinese Institute of Command and Control, 2020: 674-679.
[3]	许凯, 曾云秀, 武万森, 等. 面向计算机生成兵力的意图识别行为建模框架[J]. 系统仿真学报, 2021, 33(10): 2344-2355.
	Xu Kai, Zeng Yunxiu, Wu Wansen, et al. Research on CGF-oriented Intention Recognition Behavioral Modeling Framework[J]. Journal of System Simulation, 2021, 33(10): 2344-2355.
[4]	周云. 支持动态数据驱动仿真的模型适应性研究[C]//2009年建模与仿真标准化年会论文集. 北京: 中国系统仿真学会, 2009: 75-78.
[5]	张琪, 曾俊杰, 许凯, 等. 基于机器学习的计算机生成兵力行为建模研究综述[J]. 系统仿真学报, 2021, 33(2): 280-287.
	Zhang Qi, Zeng Junjie, Xu Kai, et al. Behavior Modeling for Computer Generated Forces Based on Machine Learning[J]. Journal of System Simulation, 2021, 33(2): 280-287.
[6]	高昂, 段莉, 张国辉, 等. 计算机生成兵力行为建模发展现状[J]. 计算机工程与应用, 2019, 55(19): 43-51.
	Gao Ang, Duan Li, Zhang Guohui, et al. Development Status of Computer Generated Force Behavior Modeling[J]. Computer Engineering and Applications, 2019, 55(19): 43-51.
[7]	高昂, 董志明, 张国辉, 等. LVC训练系统中计算机生成兵力生成技术研究[J]. 系统仿真学报, 2021, 33(3): 745-752.
	Gao Ang, Dong Zhiming, Zhang Guohui, et al. Research on Generation Technology of Computer Generated Force in LVC Training System[J]. Journal of System Simulation, 2021, 33(3): 745-752.
[8]	王思卿, 乔勇军, 王力超. 面向模拟训练的CGF空中目标建模与仿真[J]. 中国电子科学研究院学报, 2019, 14(1): 61-66, 74.
	Wang Siqing, Qiao Yongjun, Wang Lichao. CGF Air Target Modeling and Simulation for Simulation Training[J]. Journal of China Academy of Electronics and Information Technology, 2019, 14(1): 61-66, 74.
[9]	王鹏, 杨妹, 祝建成, 等. 面向数字孪生的动态数据驱动建模与仿真方法[J]. 系统工程与电子技术, 2020, 42(12): 2779-2786.
	Wang Peng, Yang Mei, Zhu Jiancheng, et al. Dynamic Data Driven Modeling and Simulation Method for Digital Twin[J]. Systems Engineering and Electronics, 2020, 42(12): 2779-2786.
[10]	张翔, 李革, 王鹏. 基于动态数据驱动的反潜战仿真系统目标探测设计[J]. 系统工程与电子技术, 2018, 40(11): 2591-2597.
	Zhang Xiang, Li Ge, Wang Peng. Research on Target Detection in Anti-submarine Warfare Simulation System Based on DDDAS[J]. Systems Engineering and Electronics, 2018, 40(11): 2591-2597.
[11]	王鹏, 祝建成, 杨妹, 等. CPS中面向数字孪生的数据同化算法研究[C]//第21届中国系统仿真技术及其应用学术年会论文集. 昆明: 中国自动化学会系统仿真专业委员会, 2020: 281-286.
	Wang Peng, Zhu Jiancheng, Yang Mei, et al. Research on Digital Twin Oriented Data Assimilation Algorithm for Cyber Physical System[C]//Proceedings of 21st CCSSTA. Kunming: System Simulation Professional Committee of the Chinese Society of Automation, 2020: 281-286.
[12]	Mahler R P S. Statistical Multisource-multitarget Information Fusion[M]. Norwood: Artech House, Inc., 2007.
[13]	Mahler R P S. Multitarget Bayes Filtering via First-order Multitarget Moments[J]. IEEE Transactions on Aerospace and Electronic Systems, 2003, 39(4): 1152-1178.
[14]	高帆. 基于DS证据理论的数据融合关键技术研究[D]. 西安: 西安理工大学, 2023.
	Gao Fan. Research on Data Fusion Technology Based on DS Evidence Theory[D]. Xi'an: Xi'an University of Technology, 2023.
[15]	Nuss Dominik, Wilking Benjamin, Wiest Jürgen, et al. Decision-free True Positive Estimation with Grid Maps for Multi-object Tracking[C]//16th International IEEE Conference on Intelligent Transportation Systems (ITSC 2013). Piscataway: IEEE, 2013: 28-34.
[16]	Ristic Branko. Particle Filters for Random Set Models[M]. New York: Springer New York, 2013: 38.

实体序号	正视宽度/m	起始位置/m	速度/(m/s)
1	2.7	(17,20)	(10,0)
2	3.5	(36.4,31.8)	(7,9)
3	3.8	(8.2,23.8)	(-9,-6)
4	2.8	(42,45)	(-15,0)
5	2.0	(45,10)	(-6,4)
6	2.0	(6.8,43.6)	(9,-7)

实体编号	预测值/m	实际值/m
1	(23.00, 20.00)	(22.87, 20.16)
2	(40.60, 37.20)	(40.48, 37.42)
3	(2.80, 20.20)	(2.83, 20.33)
4	(33.00, 45.00)	(33.07, 45.29)
5	(40.20, 11.20)	(40.16, 11.31)
6	(12.20, 39.40)	(12.07, 39.61)