一种基于改进行为树的智能对手行为模拟技术

doi:10.16182/j.issn1004731x.joss.24-0364

系统仿真学报 ›› 2024, Vol. 36 ›› Issue (9): 1995-2003.doi: 10.16182/j.issn1004731x.joss.24-0364

• 专栏 • 上一篇

一种基于改进行为树的智能对手行为模拟技术

周芳¹, 范波², 刘小毅¹, 丁一珊², 张宁馨¹, 邵亚超², 翟小玉²

^1.中国电子科技集团公司第二十八研究所信息系统工程全国重点实验室, 江苏南京 210007
^2.军科科学院国防科技创新研究院, 北京 100071

收稿日期:2024-04-09 修回日期:2024-06-03 出版日期:2024-09-15 发布日期:2024-09-30
通讯作者: 丁一珊
第一作者简介:周芳(1982-)，男，研究员，博士，研究方向为系统仿真试验与评估。

An Intelligent Adversaries Behavior Simulation Technology Based on Improved Behavior Trees

Zhou Fang¹, Fan Bo², Liu Xiaoyi¹, DingYishan ², Zhang Ningxin¹, Shao Yachao², Zhai Xiaoyu²

^1.Information System Engineering National Important Laboratory, the 28th Research Institute of China Electronics Technology Group Corporation, Nanjing 210007, China
^2.National Innovation Institute of Defense Technology, Academy of Military Science, Beijing 100071, China

Received:2024-04-09 Revised:2024-06-03 Online:2024-09-15 Published:2024-09-30
Contact: DingYishan

摘要/Abstract

摘要：

为解决智能算法/智能平台/智能系统智能化能力测试评估需高水平的智能对手模拟问题，提出了基于改进行为树的智能对手行为模拟技术。设计了行为控制、作战任务、行为动作、执行为4类行为树节点，建立了机动、侦察预警、指挥决策、火力打击和电子干扰5类原子行为动作和参数，给出了打击目标选择、武器发射、来袭武器判断等5类原子条件；提出了智能对手行为模拟系统组成，包括行为规则编辑器与行为规则引擎，建立了对手行为模拟运行流程。结合边境区域空地协同对抗典型应用场景，仿真结果表明模拟的智能对手行为能够支持智能化能力评估。

关键词: 智能对抗, 行为树, 对手行为模拟, 规则引擎, 智能试验

Abstract:

Intelligent algorithm/intelligent platform/intelligent system intelligence capability testing and evaluation need to solve high-level intelligent opponent simulation problems, an intelligent opponent behavior simulation technology based on improved behavior tree is proposed. Four types of behavior tress nodes are designed, including behavior control, combat tasks, behavior actions, and execution condition node. Five atomic behavior actions and parameters are established, including maneuver, reconnaissance and early warning, command and decision-making, firepower strike, and electronic interference node. Five atomic condition nodes are provided, including target selection, weapon launch,and incoming weapon judgment node. The intelligent adversarial behavior simulation system is designed, including a behavior rule editor and a behavior rule engine. The adversaries behavior simulation execution process is established. Considering the typical application scenarios of air ground collaborative confrontation in border areas, the simulation results indicate that the simulated intelligent opponent behavior can support the evaluation of intelligent capabilities.

Key words: intelligent adversarial, behavior tree, adversaries behavior simulation, rule engine, intelligence experiment

中图分类号:

TP391.9

周芳,范波,刘小毅等 . 一种基于改进行为树的智能对手行为模拟技术[J]. 系统仿真学报, 2024, 36(9): 1995-2003.

Zhou Fang,Fan Bo,Liu Xiaoyi,et al . An Intelligent Adversaries Behavior Simulation Technology Based on Improved Behavior Trees[J]. Journal of System Simulation, 2024, 36(9): 1995-2003.

图/表 11

图1

图2

图3

图4

图5

图6

图7

图8

图9

图10

表1

参考文献 18

1	Toubman A, Poppinga G, Roessingh J J, et al. Modeling CGF Behavior with Machine Learning Techniques: Requirements and Future Directions[C]//2015 Interservice/Industry Training, Simulation, and Education Conference. Orlando: I/ITSEC, 2015: 2637-2647.
2	Li Ni, Hou Yancheng, Gong Guanghong. A Study on the Behavior Modeling Method of Helicopter Force[C]//Modeling, Design and Simulation of Systems. Singapore: Springer Singapore, 2017: 405-416.
3	Zhang Qi, Sun Lin, Jiao Peng, et al. Combining Behavior Trees with MAXQ Learning to Facilitate CGFs Behavior Modeling[C]//2017 4th International Conference on Systems and Informatics (ICSAI). Piscataway: IEEE, 2017: 525-531.
4	Fang Jun, Yan Wenjun, Fang Wei. Air Combat Strategies of CGF Based on Q-learning and Behavior Tree[C]//2017 International Conference on Electrical Engineering and Automation Control (ICEEAC 2017). Lancaster: DEStech Publications, Inc., 2017: 187-192.
5	Iovino Matteo, Scukins Edvards, Styrud Jonathan, et al. A Survey of Behavior Trees in Robotics and AI[J]. Robotics and Autonomous Systems, 2022, 154: 104096.
6	Zhu Xianwen. Behavior Tree Design of Intelligent Behavior of Non-player Character (NPC) Based on Unity3D[J]. Journal of Intelligent & Fuzzy Systems, 2019, 37(5): 6071-6079.
7	Kamrani Farzad, Luotsinen Linus J, Rikke Amilde Løvlid. Learning Objective Agent Behavior Using a Data-driven Modeling Approach[C]//2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC). Piscataway: IEEE, 2016: 2175-2181.
8	Anon. Constructive Machine-learning Battles with Adversary Tactics(COMBAT)[EB/OL]. (2021-12-14) [2022-09-01]. .
9	Toubman A. Calculated Moves: Generating Air Combat Behaviour[D]. Leiden: Leiden University, 2020.
10	Berthling-Hansen Gabriel, Morch Eivind, Rikke Amilde Løvlid, et al. Automating Behaviour Tree Generation for Simulating Troop Movements (Poster)[C]//2018 IEEE Conference on Cognitive and Computational Aspects of Situation Management (CogSIMA). Piscataway: IEEE, 2018: 147-153.
11	董倩, 纪梦琪, 朱一凡, 等. 空中作战决策行为树建模与仿真[J]. 指挥控制与仿真, 2019, 41(1): 12-19.
	Dong Qian, Ji Mengqi, Zhu Yifan, et al. Behavioral Tree Modeling and Simulation for Air Operations Decision[J]. Command Control & Simulation, 2019, 41(1): 12-19.
12	方君, 闫文君, 邓向阳, 等. 基于Q-学习和行为树的CGF空战行为决策[J]. 计算机与现代化, 2017(5): 37-39, 44.
	Fang Jun, Yan Wenjun, Deng Xiangyang, et al. Air Bat Strategies of CGF Based on Q-learning and Behavior Tree[J]. Computer and Modernization, 2017(5): 37-39, 44.
13	付延昌. 基于行为树的CGF行为建模研究[D]. 长沙: 国防科学技术大学, 2016.
	Fu Yanchang. Research on CGF Behavior Model Based on Behavior Tree[D]. Changsha: National University of Defense Technology, 2016.
14	王成飞, 董亚卓, 苏千叶, 等. 海战仿真中的智能对抗行为建模方法研究[J]. 指挥控制与仿真, 2022, 44(1): 79-85.
	Wang Chengfei, Dong Yazhuo, Su Qianye, et al. Research on Modeling Method of Intelligent Confrontation Behavior in Naval Battle Simulation[J]. Command Control & Simulation, 2022, 44(1): 79-85.
15	张俊峰, 薛青, 张扬, 等. 融合行为树和势力图的作战决策建模方法[J]. 计算机仿真, 2021, 38(10): 5-8, 77.
	Zhang Junfeng, Xue Qing, Zhang Yang, et al. Combat Decision-making Modeling Method Based on Behavior Tree and Influence Map[J]. Computer Simulation, 2021, 38(10): 5-8, 77.
16	吴云超, 傅琛, 张宁馨. 面向数字孪生战场的智能体建模框架构建[J]. 指挥信息系统与技术, 2022, 13(4): 19-25, 31.
	Wu Yunchao, Fu Chen, Zhang Ningxin. Construction of Agent Modeling Framework for Digital Twin Battlefield[J]. Command Information System and Technology, 2022, 13(4): 19-25, 31.
17	陈希亮, 李清伟, 孙彧. 基于博弈对抗的空战智能决策关键技术[J]. 指挥信息系统与技术, 2021, 12(2): 1-6.
	Chen Xiliang, Li Qingwei, Sun Yu. Key Technologies for Air Combat Intelligent Decision Based on Game Confrontation[J]. Command Information System and Technology, 2021, 12(2): 1-6.
18	张阳, 司光亚, 王艳正, 等. 无人蜂群电磁作战行动建模与仿真[J]. 系统工程与电子技术, 2023, 45(7): 2121-2130.
	Zhang Yang, Si Guangya, Wang Yanzheng, et al. Modeling and Simulation of UAVs Swarm Electromagnetic Operation[J]. Systems Engineering and Electronics, 2023, 45(7): 2121-2130.

参数	红方	蓝方
空中兵力总数	1 606	8
空中毁伤兵力数	179	0
地面兵力总数	45	130
地面毁伤兵力数	0	105
战损率	0.117	0.807

[1]	马悦, 吴琳, 郭圣明. 作战任务分配建模及求解方法研究[J]. 系统仿真学报, 2023, 35(4): 887-898.
[2]	刘兆鹏, 徐新海, 袁博文, 张金璐. 一种多分辨率仿真模型构建方法[J]. 系统仿真学报, 2023, 35(1): 202-211.
[3]	段现银, 张灿, 朱泽润, 孙朝阳, 蒋国璋, 向峰. 逆解多目标优化的六自由度机械手轨迹规划[J]. 系统仿真学报, 2021, 33(9): 2128-2137.
[4]	杨杰, 张琪, 曾俊杰, 尹全军. 进化行为树方法研究综述[J]. 系统仿真学报, 2021, 33(10): 2315-2322.
[5]	徐文胜, 武博, 蒋坚鸿. 武器装备虚拟维修训练系统行为树设计与实现[J]. 系统仿真学报, 2018, 30(7): 2722-2728.

一种基于改进行为树的智能对手行为模拟技术

An Intelligent Adversaries Behavior Simulation Technology Based on Improved Behavior Trees

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献 18

相关文章 5

编辑推荐

Metrics

本文评价