多无人机协同空战任务规划仿真系统  

The multi-UAV cooperative air combat task planning simulation system

作　　者：王国强[1,2,3] 陈宇轩 马滢滢 蒋儒浩 王浩丞 罗贺 WANG Guoqiang;CHEN Yuxuan;MA Yingying;JIANG Ruhao;WANG Haocheng;LUO He(School of Management,Hefei University of Technology,Hefei 230009,China;Key Laboratory of Process Optimization and Intelligent Decision-Making,Hefei 230009,China;Intelligent Interconnected Systems Laboratory of Anhui Province,Hefei 230009,China)

机构地区：[1]合肥工业大学管理学院,合肥230009 [2]过程优化与智能决策教育部重点实验室,合肥230009 [3]智能互联系统安徽省实验室,合肥230009

出　　处：《兵器装备工程学报》2023年第9期1-10,共10页Journal of Ordnance Equipment Engineering

基　　金：国家自然科学基金项目(71871079,72271076,71971075,71671059)。

摘　　要：面向多无人机协同空战任务规划方法性能验证的需求,开发了一种基于VR-Forces仿真引擎的多无人机协同空战任务规划仿真系统,对该仿真系统的总体架构、红方子系统、蓝方子系统、白方子系统和强化学习算法训练子系统进行了设计。对算法库、强化学习算法训练和人机交互等关键技术提出了针对性的解决方案,提升了该仿真系统的稳定性、可扩展性和功能性。利用该仿真系统对多无人机协同空战目标分配、重决策算法等典型任务规划方法进行了测试和仿真实验。结果表明,所开发的仿真系统可以很好地支持多无人机协同空战任务规划方法的测试和验证。To verify the performance of multi-UAV cooperative air combat task planning method,a multi-UAV cooperative air combat task planning simulation system based on the VR-Forces simulation engine is developed in this paper.The architecture,red-side subsystem,blue-side subsystem,white-side subsystem,and reinforcement learning algorithm training subsystem of the simulation system are designed.To improve the stability,scalability,and functionality of the simulation system,key technologies such as algorithm library,reinforcement learning algorithm training,and human-computer interaction are proposed.On this basis,the simulation system is developed.Finally,the developed simulation system is used to test and verify the typical task planning methods,such as multi-UAV cooperative air combat target allocation and the redecision algorithm.The results show that the developed simulation system can support the testing and verification of the multi-UAV cooperative air combat task planning method.

关 键 词：VR-Forces 多无人机协同空战 任务规划 算法库 强化学习算法训练 人机交互 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]