다종 장사정포 공격에 대한 강화학습 기반의 동적 무기할당
Reinforcement Learning-based Dynamic Weapon Assignment to Multi-Caliber Long-Range Artillery Attacks
1
조회
0
다운로드
5
인용
0
참고문헌
키워드
초록
North Korea continues to upgrade and display its long-range rocket launchers to emphasize its military strength. Recently Republic of Korea kicked off the development of anti-artillery interception system similar to Israel’s “Iron Dome”, designed to protect against North Korea’s arsenal of long-range rockets. The system may not work smoothly without the function assigning interceptors to incoming various-caliber artillery rockets. We view the assignment task as a dynamic weapon target assignment (DWTA) problem. DWTA is a multistage decision process in which decision in a stage affects decision processes and its results in the subsequent stages. We represent the DWTA problem as a Markov decision process (MDP). Distance from Seoul to North Korea’s multiple rocket launchers positioned near the border, limits the processing time of the model solver within only a few second. It is impossible to compute the exact optimal solution within the allowed time interval due to the curse of dimensionality inherently in MDP model of practical DWTA problem. We apply two reinforcement-based algorithms to get the approximate solution of the MDP model within the time limit. To check the quality of the approximate solution, we adopt Shoot-Shoot-Look(SSL) policy as a baseline. Simulation results showed that both algorithms provide better solution than the solution from the baseline strategy.
Abstract
North Korea continues to upgrade and display its long-range rocket launchers to emphasize its military strength. Recently Republic of Korea kicked off the development of anti-artillery interception system similar to Israel’s “Iron Dome”, designed to protect against North Korea’s arsenal of long-range rockets. The system may not work smoothly without the function assigning interceptors to incoming various-caliber artillery rockets. We view the assignment task as a dynamic weapon target assignment (DWTA) problem. DWTA is a multistage decision process in which decision in a stage affects decision processes and its results in the subsequent stages. We represent the DWTA problem as a Markov decision process (MDP). Distance from Seoul to North Korea’s multiple rocket launchers positioned near the border, limits the processing time of the model solver within only a few second. It is impossible to compute the exact optimal solution within the allowed time interval due to the curse of dimensionality inherently in MDP model of practical DWTA problem. We apply two reinforcement-based algorithms to get the approximate solution of the MDP model within the time limit. To check the quality of the approximate solution, we adopt Shoot-Shoot-Look(SSL) policy as a baseline. Simulation results showed that both algorithms provide better solution than the solution from the baseline strategy.
참고문헌 (26)
- Bertsekas, D, "Missile Defense and Interceptor Allocation by Neuro-Dynamic Programming", IEEE Transactions on Systems, Man, and Cybernetics, Part A: Systems and Humans, 30(1), pp.42~51 (2000)
- Bertsekas, D. P, "Approximate Policy Iteration: A Survey and Some New Methods", Journal of Control Theory and Applications, 9, pp.310~335 (2011)
- Bertsekas, D.P, "Dynamic Programming and Optimal Control: Approximate Dynamic Programming" (2012), Athena Scientific
- 차영호, "표적 할당 및 사격순서결정문제를 위한 최적해 알고리즘 연구", 한국산업경영시스템학회지, 42(1), pp.143~150 (2019), 한국산업경영시스템학회[DOI]
- Choi, B.W, "A Study on the Flight Trajectory Prediction Method of Ballistic Missiles", 2020 Autumn Conference on Journal of Korean Society of Systems Engineering, pp.131~140 (2020)
- "Chosun Media"[URL]
- Davis, M. T, "Approximate Dynamic Programming for Missile Defense Interceptor Fire Control", European Journal of Operational Research, 259, pp.873~886 (2017)
- 홍동욱, "탄도미사일 궤적 시뮬레이션 모델을 이용한방어영역 산출 및 응용", 한국군사과학기술학회지, 21(4), pp.551~561 (2018), 한국군사과학기술학회[DOI]
- Hosein, P.A, "A Class of Dynamic Nonlinar Resource Allocation Problems", Ph. D, pp.1989
- 임준성, "다대다 대응 위협평가 및 무기할당 알고리즘 연구: 탄도미사일 및 장사정포 위협을 중심으로", 한국산업경영시스템학회지, 44(4), pp.43~52 (2021), 한국산업경영시스템학회
- 장준건, "자산기반 무기할당 문제의 선형 근사 모형", 한국산업경영시스템학회지, 38(3), pp.108~116 (2015), 한국산업경영시스템학회
- 정신기, "방공교전에서의 동적 무기-표적 할당을 위한 Rolling-Horizon 스케줄링 알고리즘", 대한산업공학회지, 46(1), pp.11~24 (2020), 대한산업공학회[DOI]
- 김정훈, "양자화 유전자알고리즘을 이용한 무기할당", 한국산업경영시스템학회지, 40(4), pp.260~267 (2017), 한국산업경영시스템학회
- 김태구, "장사정포 요격체계 구성요소 배치에 따른 효과 분석", 한국산업경영시스템학회지, 45(1), pp.41~52 (2022), 한국산업경영시스템학회
- 이창석, "근사적 동적계획을 활용한 요격통제 및 동시교전 효과분석", 한국항공우주학회지, 50(4), pp.287~295 (2022), 한국항공우주학회[DOI]
- Lee, Z. J, "An Immunity Based Ant Colony Optimization Algorithm for Solving Weapon-Target Assignment Problem", Applied Soft Computing, 2(1), pp.39~47 (2002)
- McKenna, R. S, "Approximate Dynamic Programming for the Military Inventory Routing Problem", Annals of Operational Research, 288(1), pp.391~416 (2020)
- Ministry of National Defense, "2020 Defense White Paper" (2020), Ministry of National Defense
- Naeem, H, "An Optimal Dynamic Threat Evaluation and Weapon Scheduling Technique", Knowledge-Based Systems, 23(4), pp.337~342 (2010)
- Powell, W. B, "Approximate Dynamic Programming:Solving the Curse of Dimensionality, Second Edition" (2011), John Wiley & Sons
- Powell, W. B, "Perspectives of Approximate Dynamic Programming", Annals of Operations Research, 13(2), pp.1~38 (2012)
- Rempel, M, "A Review of Approximate Dynamic Programming Applications within Military Operations Research", Operational Research Perspectives, 8, pp.100204~ (2021)
- 신민규, "평균 필드 게임 기반의 강화학습을 통한 무기-표적 할당", 한국군사과학기술학회지, 23(4), pp.337~345 (2020), 한국군사과학기술학회
- Summers, D. S, "An Approximate Dynamic Programming for Comparing Firing Policies in a Networked Air Defense Environment", Computers & Operations Research, 117, pp.104890~ (2020)
- "Yonhapnews"[URL]
- 유병천, "탄도미사일의 비행궤적 예측 방법 연구 - 탄종별 비행경로각과 사거리를 중심으로 -", 시스템엔지니어링학술지, 16(2), pp.131~140 (2020), 한국시스템엔지니어링학회[DOI]