CASIA OpenIR  > 综合信息系统研究中心
Research on Autonomous Maneuvering Decision of UCAV Based on Deep Reinforcement Learning
Zhang, Yesheng1,2; Zu, Wei1; Gao, Yang1; Chang, Hongxing1
2018-06
会议名称The 30th Chinese Control and Decision Conference
会议录名称CCDC2018
卷号1
页码230-235
会议日期June 9-11, 2018
会议地点Shenyang, China
出版地Singapore
会议主办者东北大学
出版者IEEE Industrial Electronics (IE) Chapter, Singapore
摘要
In order to improve the intelligent level of UCAV in one-to-one air combat, an autonomous maneuvering decision algorithm based on deep reinforcement learning is proposed. UCAV learns strategies by sensing the environment, performing maneuvering actions, and getting feedback. In this way, we can avoid the limitations of existing theories and human operations. Firstly an environment is modeled to simulate the real-time situation of air combat. Then a situation assessment method based on Energy-Maneuverability theory is utilized to design the reward functions. Finally model based on deep reinforcement learning is created for UCAV to learn strategies to gain the advantage for the opponent.
关键词Air Combat Autonomous Maneuvering Decision Deep Reinforcement Learning
学科领域Autonomous Control
URL查看原文
收录类别EI
语种英语
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/20920
专题综合信息系统研究中心
通讯作者Zhang, Yesheng
作者单位1.Institute of Automation, Chinese Academy of Sciences
2.University of Chinese Academy of Sciences
推荐引用方式
GB/T 7714
Zhang, Yesheng,Zu, Wei,Gao, Yang,et al. Research on Autonomous Maneuvering Decision of UCAV Based on Deep Reinforcement Learning[C]. Singapore:IEEE Industrial Electronics (IE) Chapter, Singapore,2018:230-235.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Research on Autonomo(1271KB)会议论文 开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Zhang, Yesheng]的文章
[Zu, Wei]的文章
[Gao, Yang]的文章
百度学术
百度学术中相似的文章
[Zhang, Yesheng]的文章
[Zu, Wei]的文章
[Gao, Yang]的文章
必应学术
必应学术中相似的文章
[Zhang, Yesheng]的文章
[Zu, Wei]的文章
[Gao, Yang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Research on Autonomous Maneuvering Decision of UCAV Based on Deep Reinforcement Learning.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。