Command Control and Simulation >
Application of Deep Learning Technology in Military Field
Received date: 2019-08-21
Revised date: 2019-08-29
Online published: 2022-05-19
In order to sort out the difficulties in the application of deep learning technology in the military field and clarify the direction of deep learning in the application of public relations in the military field, this paper firstly summarizes the application status of deep learning technology in the military field from three aspects: target recognition, situation awareness and command decision-making, and then analyzes the difficulties and challenges in the application of deep learning technology in the military field. In the field of target recognition: deep learning technology for scarce cognitive samples, deep learning technology under uncertain information, its real-time and deep learning based on unmanned platform need to be broken through. In the field of situation awareness: the representation and mining technology of big data characteristics of battlefield situation based on deep learning, and the technology of battlefield situation understanding need to be broken through. In the field of command and decision-making: the solvability of deep learning needs to be improved, and the multi-entity collaborative decision-making technology and reasoning decision-making technology need to be improved. The research results can provide reference direction for the innovation and development of deep learning technology in the military field and engineering research.
LUO Rong , WANG Liang , XIAO Yu-jie , HE Yi , ZHAO Dong-feng . Application of Deep Learning Technology in Military Field[J]. Command Control and Simulation, 2020 , 42(1) : 1 -5 . DOI: 10.3969/j.issn.1673-3819.2020.01.001
| [1] |
|
| [2] |
|
| [3] |
|
| [4] |
|
| [5] |
|
| [6] |
|
| [7] |
|
| [8] |
|
| [9] |
潘浩. 基于深度学习的军事目标识别[D]. 杭州: 杭州电子科技大学, 2018.
|
| [10] |
冷鹏飞. 基于深度学习的雷达辐射源识别技术[D]. 扬州: 扬州船用电子仪器研究所, 2018.
|
| [11] |
宋达. 基于深度学习方法的水下目标识别技术研究[D]. 成都: 电子科技大学, 2018.
|
| [12] |
翟进有, 代冀阳, 王嘉琦. 深度残差网络的无人机多目标识别[J]. 图学学报, 2019, 40(1):158-164.
|
| [13] |
朱丰, 胡晓峰, 吴琳, 等. 基于深度学习的战场态势高级理解模拟方法[J]. 火力与指挥控制, 2018, 43(8):27-32.
|
| [14] |
廖鹰, 易卓, 胡晓峰. 基于深度学习的初级战场态势理解研究[J]. 指挥与控制学报, 2017, 3(3):67-71.
|
| [15] |
李高垒, 马耀飞. 基于深度网络的空战态势特征提取[J]. 系统仿真学报, 2017, 29(增刊1):98-112.
|
| [16] |
欧微, 柳少军, 贺筱媛. 基于时序特征编码的目标战术意图识别算法[J]. 指挥控制与仿真, 2016, 38(6):36-41.
|
| [17] |
荣明, 杨镜宇. 基于深度学习的战略威慑决策模型研究[J]. 指挥与控制学报, 2017, 3(1):44-47.
|
| [18] |
申生奇, 尹奇跃, 张俊格. 基于深度态势匹配的辅助指挥控制决策方法应用研究[C]. 第六届中国指挥控制大会论文集(上册), 2018:138-142.
|
| [19] |
周来, 靳晓伟, 郑益凯. 基于深度强化学习的作战辅助决策研究[J]. 空天防御, 2018, 1(1):31-35.
|
| [20] |
王壮, 李辉, 李晓辉. 基于深度强化学习的作战智能体研究[C]. 第六届中国指挥控制大会论文集(上册), 2018:32-36.
|
/
| 〈 |
|
〉 |