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

  • 제25권6호
  • /
  • Pages.637-647
  • /
  • 2022
  • /
  • 1598-9127(pISSN)
  • /
  • 2636-0640(eISSN)
한국군사과학기술학회 (The Korea Institute of Military Science and Technology)
권호 표지
DOI QR코드

DOI QR Code

공대공 전투 모의를 위한 규칙기반 AI 교전 모델 개발

The Development of Rule-based AI Engagement Model for Air-to-Air Combat Simulation

  • 이민석 (국방과학연구소 항공기술연구원) ;
  • 오지현 (국방과학연구소 항공기술연구원) ;
  • 김천영 (국방과학연구소 항공기술연구원) ;
  • 배정호 (국방과학연구소 국방인공지능센터) ;
  • 김용덕 (국방과학연구소 국방인공지능센터) ;
  • 지철규 (국방과학연구소 항공기술연구원)
  • Minseok, Lee (Aerospace Technology Research Institute, Agency for Defense Development) ;
  • Jihyun, Oh (Aerospace Technology Research Institute, Agency for Defense Development) ;
  • Cheonyoung, Kim (Aerospace Technology Research Institute, Agency for Defense Development) ;
  • Jungho, Bae (Defense AI Center, Agency for Defense Development) ;
  • Yongduk, Kim (Defense AI Center, Agency for Defense Development) ;
  • Cheolkyu, Jee (Aerospace Technology Research Institute, Agency for Defense Development)
  • 투고 : 2022.09.29
  • 심사 : 2022.11.29
  • 발행 : 2022.12.05
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Since the concept of Manned-UnManned Teaming(MUM-T) and Unmanned Aircraft System(UAS) can efficiently respond to rapidly changing battle space, many studies are being conducted as key components of the mosaic warfare environment. In this paper, we propose a rule-based AI engagement model based on Basic Fighter Maneuver(BFM) capable of Within-Visual-Range(WVR) air-to-air combat and a simulation environment in which human pilots can participate. In order to develop a rule-based AI engagement model that can pilot a fighter with a 6-DOF dynamics model, tactical manuals and human pilot experience were configured as knowledge specifications and modeled as a behavior tree structure. Based on this, we improved the shortcomings of existing air combat models. The proposed model not only showed a 100 % winning rate in engagement with human pilots, but also visualized decision-making processes such as tactical situations and maneuvering behaviors in real time. We expect that the results of this research will serve as a basis for development of various AI-based engagement models and simulators for human pilot training and embedded software test platform for fighter.

키워드

참고문헌

  1. Cheongyoung Kim, Jihyun Oh, Yong-Duk Kim, JungHo Bae, Monyeol Kim, SungHo Kim, "A Design of a Rule-based AI Fighter Pilot and Virtual Engagement Model for Air Combat Simulation," SASE 2020, Fall Conference.
  2. Jihyun Oh, Cheonyoung Kim, Sunghwan Ro, Woochang Choi, Yong-duk Kim, "Air-to-air BFM Engagement Simulator for AI Engagement Model," KIMST Annual Conference Proceedings, 2022.
  3. Byungho Jung, Seunghoon Yoo, Hogyun Hong, Jihyun Oh, Hyunju Seol, "A Study on the Autonomous Function of Unmanned Aircraft for MUM-T," KSAS Fall Conference Proceedings, pp. 455-456, 2021.
  4. Jang, S, "Study of Intelligent Pilot Model Based on Basic Fighter Maneuvering for Air Combat Simulation," Doctoral Dissertation, Department of AE, Inha Univ., 2012.
  5. B, Clark, D, Patt, H, Schramm, "Mosaic Warfare Exploiting Artificial Intelligence and Autonomous Systems to Implement Decision-Centric Operations," CSBA, Feb, 2020.
  6. M. Gunzinger, C. Rehberg, L. Autenried, "Five Priorities for the Air Force's Future Combat Air Force," CSBA, 2020.
  7. D. Javorsek, "Air Combat Evolution," DARPA/STO, May 2019.
  8. Cordon, O., Herrera, F., Gomide, F., Hoffmann, F., & Magdalena, L., "Ten Years of Genetic Fuzzy Systems: Current Framework and New Trends," In Proceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference(Cat. No. 01TH8569), Vol. 3, pp. 1241-1246, IEEE, 2001, July.
  9. Berndt, Jon, "JSBSim: An Open Source Flight Dynamics Model in C++," AIAA Modeling and Simulation Technologies Conference and Exhibit, 2004.
  10. Burgin, George H., Lawrence J. Fogel, and J. Price Phelps, "An Adaptive Maneuvering Logic Computer Program for the Simulation of One-on-One Air-toAir Combat," Volume 1: General Description, No. NASA-CR-2582, NASA, 1975.
  11. Burgin, George H., and L. B. Sidor, "Rule-based Air Combat Simulation," No. H-1501, 1988.
  12. Kahneman, Daniel, and Amos Tversky, "The Simulation Heuristic," Stanford Univ CA Dept of Psychology, 1981.
  13. Lazarus, Earl, "The Application of Value-Driven Decision-Making in Air Combat Simulation," 1997 IEEE International Conference on Systems, Man, and Cybernetics, Computational Cybernetics and Simulation, Vol. 3, IEEE, 1997.
  14. Holland, J. H., Booker, L. B., Colombetti, M., Dorigo, M., Goldberg, D. E., Forrest, S., ... & Wilson, S. W., "What is a Learning Classifier System?," In International Workshop on Learning Classifier Systems, pp. 3-32, Springer, Berlin, Heidelberg, 1999, July.
  15. Kaelbling, Leslie Pack, Michael L. Littman, and Andrew W. Moore, "Reinforcement Learning: A Survey," Journal of Artificial Intelligence Research 4, pp. 237-285, 1996. https://doi.org/10.1613/jair.301
  16. Kukreti, Sarthak R., Manish Kumar, and Kelly Cohen, "Genetic Fuzzy based Target GeoLocalization Using Unmanned Aerial Systems for Firefighting Applications," 2018 AIAA Information Systems-AIAA Infotech@ Aerospace, 2136, 2018.
  17. Sathyan, Anoop, Nicholas D. Ernest, and Kelly Cohen, "An Efficient Genetic Fuzzy Approach to UAV Swarm Routing," Unmanned Systems 4.02, pp. 117-127, 2016. https://doi.org/10.1142/S2301385016500011
  18. Sathyan, Anoop, Kelly Cohen, and Ou Ma, "Genetic Fuzzy based Scalable System of Distributed Robots for a Collaborative Task," Frontiers in Robotics and AI 7, 601243, 2020. https://doi.org/10.3389/frobt.2020.601243
  19. Ernest, N., Carroll, D., Schumacher, C., Clark, M., Cohen, K., & Lee, G., "Genetic Fuzzy based Artificial Intelligence for Unmanned Combat Aerial Vehicle Control in Simulated Air Combat Missions," Journal of Defense Management, 6(1), pp. 2167-0374, 2016.
  20. Xiaoteng Ma, Li Xia, and Qianchuan Zhao, "AirCombat Strategy Using Deep Q-Learning," 2018 CAC.
  21. Bogdan Vlahov, Eric Squires, Laura Strickland, and Charles Pippin, "On Developing a UAV PursuitEvation Policy Using Reinforcement Learning," 2018 17th ICMLA.
  22. Nicholas Ernest, Kelly Cohen, Elad Kivelevitch, Corey Schumacher and David Casbeer, "Genetic Fuzzy Trees and their Application Towards Autonomous Training and Control of a Squadron of Unmanned Combat Aerial Vehicles," Unmanned Systems, Vol. 3, No. 3, pp. 185-204, 2015.
  23. Akabari S., Mejhaj M. B., Nikravesh S. K., "Fuzzy Modeling of Offensive Maneuvers in an Air-to-Air Combat," Proc. of the Computational Intelligence, Theory and Applications, pp. 171-184, 2005.
  24. Nelson Ramirez Lopez and Rafal Zbikowski, "Effectiveness of Autonomous Decision Making for Unmanned Combat Aerial Vehicles in Dogfight Engagements," Journal of Guidance, Control, and Dynamics, Vol. 41, No. 4, April 2018.
  25. Dong-Il You and Hyunchul Shim, "Design of an Autonomoous Air Combat Guidance Law using a Virtual Pursuit Point for UCAV," J. of The Korean Society for Aeronautical and Space Sciences, Vol. 42 No. 3, pp. 199-212, 2014. https://doi.org/10.5139/JKSAS.2014.42.3.199