한국군사과학기술학회지 (Journal of the Korea Institute of Military Science and Technology)

  • 제25권6호
  • /
  • Pages.617-627
  • /
  • 2022
  • /
  • 1598-9127(pISSN)
  • /
  • 2636-0640(eISSN)
한국군사과학기술학회 (The Korea Institute of Military Science and Technology)
권호 표지
DOI QR코드

DOI QR Code

해군분석모델용 AI-CGF를 위한 시나리오 생성 모델 설계(I): 진화학습

Design of Scenario Creation Model for AI-CGF based on Naval Operations, Resources Analysis Model(I): Evolutionary Learning

  • 김현근 (한국항공대학교 대학원 컴퓨터공학과) ;
  • 강정석 (한국항공대학교 대학원 컴퓨터공학과) ;
  • 박강문 (한국교통대학교 전자공학과) ;
  • 김재우 (주식회사 아레스 신기술연구단) ;
  • 김장현 (주식회사 아레스 신기술연구단) ;
  • 박범준 (해군 전력분석시험평가단) ;
  • 지승도 (한국항공대학교 소프트웨어학과)
  • Hyun-geun, Kim (Department of Computer Science, Graduate School, Korea Aerospace University) ;
  • Jung-seok, Gang (Department of Computer Science, Graduate School, Korea Aerospace University) ;
  • Kang-moon, Park (Dept. of Electronic Engineering, Korea National University of Transportation) ;
  • Jae-U, Kim (New Technology Research Group, Ares Co., Ltd.) ;
  • Jang-hyun, Kim (New Technology Research Group, Ares Co., Ltd.) ;
  • Bum-joon, Park (Naval Force Analysis Test Evaluation Group) ;
  • Sung-do, Chi (Department of Software, Korea Aerospace University)
  • 투고 : 2022.07.05
  • 심사 : 2022.11.25
  • 발행 : 2022.12.05
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Military training is an essential item for the fundamental problem of war. However, there has always been a problem that many resources are consumed, causing spatial and environmental pollution. The concepts of defense modeling and simulation and CGF(Computer Generated Force) using computer technology began to appear to improve this problem. The Naval Operations, Resources Analysis Model(NORAM) developed by the Republic of Korea Navy is also a DEVS(Discrete Event Simulation)-based naval virtual force analysis model. The current NORAM is a battle experiment conducted by an operator, and parameter values such as maneuver and armament operation for individual objects for each situation are evaluated. In spite of our research conducted evolutionary, supervised, reinforcement learning, in this paper, we introduce our design of a scenario creation model based on evolutionary learning using genetic algorithms. For verification, the NORAM is loaded with our model to analyze wartime engagements. Human-level tactical scenario creation capability is secured by automatically generating enemy tactical scenarios for human-designed Blue Army tactical scenarios.

키워드

참고문헌

  1. Jong-Ho Lee, "The Theory and Practice for Modeling and Simulation as a Transformation Enabler for Efficient Defense Management," 2005.
  2. US Department of Defense, "Modeling and Simulation(M&S) Master Plan, Under Secretary and Defense for Acquisition and Technology," 1995.
  3. Wittman Jr, Robert L., and Cynthia T. Harrison, "OneSAF: A Product Line Approach to Simulation Development," MITRE CORP ORLANDO FL, 2001.
  4. S. Lee, et al., "Development of a Vulnerability Assessment Model for Naval Ships on a Theater Engagement Analysis," Journal of the Korea Society for Simulation(JKSS), Vol. 30, No. 1, pp. 1-9, 2021.
  5. Zeigler, Bernard P., "DEVS Representation of Dynamical Systems: Event-based Intelligent Control," Proceedings of the IEEE 77.1, pp. 72-80, 1989. https://doi.org/10.1109/5.21071
  6. Holland, John H., "Genetic Algorithms and the Optimal Allocation of Trials," SIAM Journal on Computing 2.2, pp. 88-105, 1973. https://doi.org/10.1137/0202009
  7. You, Yong-Jun, Sung-Do Chi, and Jae-Ick Kim, "Simulation-Based Tactics Generation for Warship Combat Using the Genetic Algorithm," IEICE TRANSACTIONS on Information and Systems 94.12, pp. 2533-2536, 2011.
  8. Park, Kang-Moon, Donghoon Shin, and Sung-Do Chi, "Modified Neural Architecture Search(NAS) Using the Chromosome Non-Disjunction," Applied Sciences 11.18, p. 8628, 2021.
  9. Mooney, Christopher Z., Monte Carlo Simulation, No. 116, Sage, 1997.
  10. Justesen, Niels, and Sebastian Risi, "Continual Online Evolutionary Planning for In-Game Build Order Adaptation in StarCraft," Proceedings of the Genetic and Evolutionary Computation Conference, 2017.
  11. Revello, Timothy E., and Robert McCartney. "Generating War Game Strategies Using a Genetic Algorithm," Proceedings of the 2002 Congress on Evolutionary Computation, CEC'02(Cat. No. 02TH8600), Vol. 2, IEEE, 2002.
  12. Jung, Chan-Ho, et al., "Multi-Platform Warship M&S System Using the Hierarchical Multi-Agent System," Journal of the Korea Society for Simulation, Vol. 18, No. 4, pp. 117-125, 2009. https://doi.org/10.9709/JKSS.2009.18.4.117
  13. Chi, Sung-Do, et al., "Design of No-human-in-theLoop Battleship Warfare M&S System applied to the Korea Yellow Sea Warfare Case using Agentbased Modeling," Journal of the Korea Society for Simulation, Vol. 17, No. 2, pp. 49-61, 2008.
  14. Hyun-geun Kim, Jung-seok Gang, Kang-moon Park, Jae-U Kim, Jang-hyun Kim, Bum-soon Park, and Sung-do Chi, "Design of Scenario Creation Model for AI-CGF based on Naval Operations, Resources Analsys Model(I): Evolutionary Learning," KIMST (on Proceeding).