J. KIMS Technol Search

CLOSE


J. KIMS Technol > Volume 23(4); 2020 > Article
제어·구동 부문
Journal of the Korea Institute of Military Science and Technology 2020;23(4):399-406.
DOI: https://doi.org/10.9766/KIMST.2020.23.4.399    Published online August 5, 2020.
Time-varying Proportional Navigation Guidance using Deep Reinforcement Learning
Hyeok-Joo Chae1, Daniel Lee1, Su-Jeong Park1, Han-Lim Choi1, Han-Sol Park2, Kyeong-Soo An2
1Department of Aerospace Engineering, Korea Advanced Institute of Science and Technology, Korea
2Avionics R&D Center, Hanwha Systems, Korea
심층 강화학습을 이용한 시변 비례 항법 유도 기법
채혁주1, 이단일1, 박수정1, 최한림1, 박한솔2, 안경수2
1한국과학기술원 항공우주공학과
2한화시스템㈜ 항공연구센터
Correspondence:  Han-Lim Choi,
Email: hanlimc@kaist.ac.kr
Received: 11 April 2020;   Revised: 29 May 2020;   Accepted: 26 June 2020;
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.
Key Words: Pursuit-Evasion Game, Proportional Navigation Guidance, Reinforcement Learning


ABOUT
ARTICLE CATEGORY

Browse all articles >

BROWSE ARTICLES
FOR CONTRIBUTORS
Editorial Office
160 Bugyuseong-daero 488beon-gil, Yuseong-gu, Daejeon 34060, Korea
Tel: +82-42-823-4603    Fax: +82-42-823-4605    E-mail: kimst@kimst.or.kr                

Copyright © 2021 by The Korea Institute of Military Science and Technology.

Developed in M2PI

Close layer
prev next