DC Field | Value | Language |
---|---|---|
dc.contributor.author | 채혁주 | ko |
dc.contributor.author | 이단일 | ko |
dc.contributor.author | 박수정 | ko |
dc.contributor.author | 최한림 | ko |
dc.contributor.author | 박한솔 | ko |
dc.contributor.author | 안경수 | ko |
dc.date.accessioned | 2021-03-08T08:50:11Z | - |
dc.date.available | 2021-03-08T08:50:11Z | - |
dc.date.created | 2021-03-03 | - |
dc.date.created | 2021-03-03 | - |
dc.date.issued | 2020-08 | - |
dc.identifier.citation | 한국군사과학기술학회지, v.23, no.4, pp.399 - 406 | - |
dc.identifier.issn | 1598-9127 | - |
dc.identifier.uri | http://hdl.handle.net/10203/281390 | - |
dc.description.abstract | In this paper, we propose a time-varying proportional navigation guidance law that determines the proportional navigation gain in real-time according to the operating situation. When intercepting a target, an unidentified evasion strategy causes a loss of optimality. To compensate for this problem, proper proportional navigation gain is derived at every time step by solving an optimal control problem with the inferred evader's strategy. Recently, deep reinforcement learning algorithms are introduced to deal with complex optimal control problem efficiently. We adapt the actor-critic method to build a proportional navigation gain network and the network is trained by the Proximal Policy Optimization(PPO) algorithm to learn an evasion strategy of the target. Numerical experiments show the effectiveness and optimality of the proposed method. | - |
dc.language | Korean | - |
dc.publisher | 한국군사과학기술학회 | - |
dc.title | 심층 강화학습을 이용한 시변 비례 항법 유도 기법 | - |
dc.title.alternative | Time-varying Proportional Navigation Guidance using Deep Reinforcement Learning | - |
dc.type | Article | - |
dc.type.rims | ART | - |
dc.citation.volume | 23 | - |
dc.citation.issue | 4 | - |
dc.citation.beginningpage | 399 | - |
dc.citation.endingpage | 406 | - |
dc.citation.publicationname | 한국군사과학기술학회지 | - |
dc.identifier.kciid | ART002613153 | - |
dc.contributor.localauthor | 최한림 | - |
dc.contributor.nonIdAuthor | 박수정 | - |
dc.contributor.nonIdAuthor | 박한솔 | - |
dc.contributor.nonIdAuthor | 안경수 | - |
dc.description.isOpenAccess | N | - |
dc.subject.keywordAuthor | Pursuit-Evasion Game(추격-회피 게임) | - |
dc.subject.keywordAuthor | Proportional Navigation Guidance(비례 항법 유도) | - |
dc.subject.keywordAuthor | Reinforcement Learning(강화학습) | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.