摘要
LVC训练是实战化条件下装备体系对抗训练的一种有效手段,针对LVC训练系统中,计算机生成兵力难以满足训练需求问题,明确LVC训练与LVC训练系统概念,按照模型与系统的结构组成关系阐述了逻辑靶场实体配置、指挥实体、战斗实体3个不同层次模型相应的建模技术需求。针对具体需求,提出基于复杂网络的逻辑靶场虚实实体配置、基于深度强化学习的分队战术决策建模、基于动态贝叶斯网、遗传神经网络的战术行为参数矫正建模4种计算机生成兵力生成技术。
LVC training system of the combat equipment under the condition of confrontation is an effective means of training,aiming at the problem that in LVC training system,computer generated forces are difficult to meet the demand of training problems.The concept of LVC training and LVC training system is clarified,according to the relationship between model and system structure,the corresponding modeling technology requirements of three different hierarchical models,namely logical range entity configuration,command entity and combat entity,are expounded.According to the specific requirements,four computer-generated force generation methods are proposed,namely,logical target range virtual and real entity configuration based on complex network,unit tactical decision modeling based on deep reinforcement learning,tactical behavior parameter correction modeling based on dynamic bayesian network and genetic neural network.
作者
高昂
董志明
张国辉
梁涛
郭齐胜
Gao Ang;Dong Zhiming;Zhang Guohui;Liang Tao;Guo Qisheng(Army Armored Force Academy Drill and Training Center,Beijing 100072,China;Department of Management,Shandong University of Technology,Zibo 255000,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第3期745-752,共8页
Journal of System Simulation
基金
军队科研计划(41405030302,41401020301)。
关键词
计算机生成兵力
LVC训练
复杂网络
深度强化学习
动态贝叶斯网络
遗传神经网络
computer generated forces
LVC training
complex networks
deep reinforcement learning
dynamic bayesian network
genetic neural network
作者简介
第一作者:高昂(1988-),男,博士生,助理讲师,研究方向为装备作战与保障仿真。E-mail:gaoang370829@sohu.com。
