摘要
未来兵棋推演将面对更加复杂的战争体系,需要广泛应用人工智能技术来弥补人的不足,这是下一代兵棋系统模型引擎研发必须考虑的因素。结合长期兵棋系统研发和运用经验,提出了下一代兵棋模型引擎的框架雏形,针对结构和计算复杂度问题讨论了体系解耦方法,研究了基于数字孪生的人机融合架构,探索了可以降低模型开发门槛、提升效率的建模技术手段,提出了支持机器学习的引擎机制,并针对分布式硬件环境提供了软硬一体化设计思路。
Aiming at the more and more complex war systems,widely used artificial intelligence technology is needed to make up the human deficiencies in future wargame deduction,which is necessary for the next generation wargame system model engine.To address these challenges,a framework prototype of the next generation wargame model engine based on the experience of the long-term development and application is proposed.The decoupling method for the complexity of structure and computation is researched.The human-computer integration architecture on digital twinning technology is studied.Some new modeling techniques which the threshold of model development is reduced and the efficiency is improved are explored.The engine mechanism is provided to support the machine learning,and to achieve the integrated design for distributed hardware environment.
作者
唐宇波
沈弼龙
师磊
易星
Tang Yubo;Shen Bilong;Shi Lei;Yi Xing(College of Joint Operation,National Defense University,Beijing 100091,China;Institute of Software Chinese Academy of Sciences,Beijing 100190,China;Graduate School,National Defense University,Beijing 100091,China)
出处
《系统仿真学报》
CAS
CSCD
北大核心
2021年第9期2025-2036,共12页
Journal of System Simulation
