DOI QR코드

DOI QR Code

Case of Implementation of Automatic Planning for SAF

SAF를 위한 자동계획기법 구현 사례

  • Received : 2014.10.21
  • Accepted : 2014.11.25
  • Published : 2014.12.31

Abstract

Our Automatic Replanning enables simulation entities to execute goal oriented behavior planning by dynamic behavior linking. Existing methods especially in Semi-Automated Forces (SAF) are mainly executing strict plans which are given at initial stage, thus they are not effective to cope with contingencies especially in a human in the loop simulation where humans interrupt. Moreover, those usually suffer from explosion of behavior combination in attempt to describe all possible countermeasures, and such combinations may be prone to being inconsistent to the situations. Our method generates behavior sequence in which behavior are linked from the goal in the manner of back-propagation. Each behavior has tags of pre/post-conditions. The tags are linked dynamically according to a certain contingency. The method is being applied to a national defense research project to show feasibility.

본 연구는 모의개체로 하여금 동적행위연결을 통한 목적지향 행위계획을 수행토록 하는 기법의 구현사례로서 재계획기법을 소개한다. 기존의 행위처리기법, 특히 Semi-Automated Forces (SAF)에서는 모의 초기에 주어진 정해진 계획을 단순히 수행하는 수준에서 크게 벗어나지 않는다. 따라서 인간의 판단 같은 예측불허 상황이 발생하는 (Human in the loop) 모의에서 기존 기법은 상황대처에 미흡하다. 또한 그러한 기법은 돌발상황 대응을 위한 광범위한 경우의 수를 고려하다보면 행위조합 폭증 문제를 겪을 수 있으며, 그러한 조합이 상황에 부합하지 않을 수 있다. 재계획기법은 역전파(back-propagation)를 활용, 목표달성을 위해 필요한 행위들을 검색, 연계하는 자동계획기법 구현사례이다. 이 기법은 행위에 태그(pre/post-conditions)를 부여, 동적으로 행위들을 연결한다. 본 논문은 기법의 실효성 입증을 위해 국방분야의 연구과제에 적용된 성과를 소개한다.

Keywords

References

  1. A. Ozaki, et. al,, "Design and Implementation of Parallel and Distributed Wargame Simulation System," in Proc. of IEICE/IEEE Joint Special Issue on Autonomous Decentralized Systems and Systems Assurance, vol. E84-D, pp. 1376-1384, 2001.
  2. P. Pearce, et. al., "The Wargame Infrastructure and Simulation Environment (Wise)," in Proc. of 7th International Conference of Knowledge-Based Intelligence Information and Engineering Systems, 2003. Oxford, UK.
  3. D. Fu, R. Jensen, et. al., "Specifying the Behavior of Computer-Generated Forces without programming," in Proc. of the 2003 Winter Simulation Conference, pp. 969-975, 2003.
  4. H. K. Park, et. al., "Development of The Distributed Real-Time Wargame Simulation Using TMO Model," Proc. of the 98 Korea Society for Simulation conference. pp. 13-22, 1998.
  5. S. B. Banks, "An Approach to Enhance Human Behavior Modeling for Computer-Generated Actors," in Proc. of the 4th International SIMTECT Conference, pp. 199-204, 1999. Melbourne, Australia.
  6. D. S. Nau, "Current Trends in Automated Planning," AI Magazine, vol. 28, no. 4, pp. 43-58, 2007.
  7. J. Kim, D. Choi, "Implementation of Goal Oriented Behavior Planning, Re-planning for SAF," Interservice/ Industry Training, Simulation, and Education Conference, 2013.
  8. Daehoe Choi, Sanmin Lee, Sung Hoon Jung, "A Goal Oriented Action Planning and Replanning method of Computer Generated Forces in War Game," Proc. of KIIS Conference 2012, Vol. 22. No. 2.
  9. K. Erol, "Hierarchical Task Network Planning: Formalization, Analysis, and Implementation," Phd thesis, Dept. of C.S., Univ. of Maryland, College Park, MD, 1996.
  10. B. Kosko, Neural Networks and Fuzzy Systems. A Dynamical Systems Approach to Machine Intelligence. Prentice-Hall, 1992.
  11. J. Orkin, "Applying Goal-Oriented Action Planning to Games," in AI Game Programming Wisdom 2, pp. 217-228, 2003. Charles River Media.
  12. E. Long, "Enhanced npc behavior using goal oriented action planning," 2007.
  13. Han-ha Yoo, Kyung-eun Cho, and Ky-hyun Um, "A Cooperation Strategy of Multi-agents in Real-Time Dynamic.