Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지

UAS Automatic Control Parameter Tuning System using Machine Learning Module

기계학습 알고리즘을 이용한 UAS 제어계수 실시간 자동 조정 시스템

  • 문미선 (한국항공대학교 컴퓨터공학과) ;
  • 송강 (한국항공대학교 컴퓨터공학과) ;
  • 송동호 (한국항공대학교 컴퓨터공학과)
  • Received : 2010.10.11
  • Accepted : 2010.12.30
  • Published : 2010.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

A automatic flight control system(AFCS) of UAS needs to control its flight path along target path exactly as adjusts flight coefficient itself depending on static or dynamic changes of airplane's features such as type, size or weight. In this paper, we propose system which tunes control gain autonomously depending on change of airplane's feature in flight as adding MLM(Machine Learning Module) on AFCS. MLM is designed with Linear Regression algorithm and Reinforcement Learning and it includes EvM(Evaluation Module) which evaluates learned control gain from MLM and verified system. This system is tested on beaver FDC simulator and we present its analysed result.

무인기의 자동 비행 제어 시스템은 기체의 형태, 크기, 무게 등의 정적 및 동적 변화에 따라 스스로 비행계수를 조정하여 목표 비행궤적을 정확히 따라가도록 제어할 필요가 있다. 본 논문에서는 PID 제어 기법을 이용하는 비행제어시스템에 기계학습모듈(MLM)을 추가하여 기체의 특성 변화에 따라 제어계수를 비행중 실시간 자동으로 조정하는 시스템을 제안한다. MLM은 선형회귀분석과 보정학습을 이용하여 설계되었으며 MLM을 통해 학습된 제어계수의 적합성을 평가하는 평가모듈(EvM)을 함께 모델링 하였다. 이 시스템은 FDC 비버 시뮬레이터를 기반으로 실험하였으며 그 결과를 분석 제시하였다.

Keywords

References

  1. B. C. Kuo, Automatic Control System 5Edition, 1991.
  2. L. N.Long, S. D. Hanford, O. Janrathitikarn, G. L. Sinsley and J. A. Miller, "A Review of Intelligent System Software for Autonomous." Proc. of the 2007 IEEE Symposium on Computational Intelligence in Security and Defense Application, 2007.
  3. M. Pearce, R. Arkin and A. Ram, "The Learning of Reactive Control Parameters Through Genetic Algorithm," Proc. of the 1992 IEEE/RSJ Intl. Conf. on Intelligent Robots and System, Raleigh, July, 1992.
  4. C. Ko, T. Lee, H. Fan and C. Wu, "Genetic Auto-Tuning And Rule Reduction of Fuzzy PID Controllers," 2006 IEEE Intl. Conf. on System, Man, and Cybernetics. October. 2006.
  5. Y. Abe, M. Konosho, J. Imai, R. Hasagawa, M. Watanabe and H. Kamiio, "PID Gain Tuning Method for Oil Refining Controller based on Neural Networks," Proc. of the Second Intl. Conf. on Innovative Computing, Information and Control, 2007.
  6. C. Lin and C. S. George Lee, "Reinforcement Structure/Parameter Learning for Neural-Network-Based Fuzzy Logic Control System", IEEE Trans. on Fuzzy System, vol. 2, no. 1, February, 1994.
  7. J. Lu, O. Ling and J. Zhang, "Lateral Control Law Design for Helicopter Using Radial Basis Function Neural Network," Proc of the IEEE Intl. Conf. of Automation and Logistic, August. 2007.
  8. R. C. Nelson, Flight Stability and Automatic Control Second Edition, TMcGraw-Hill higher Education. 1998.
  9. 장성욱, 이진걸, "The Self-Tuning PID Control Based on Real-Time Adaptive Learning Evolutionary Algorithm," 대한기계학회논문집, 2008.
  10. FDC 1.2 - A SIMULINK Toolbox for Flight Dynamics and Control Analysis
  11. I. H, Witten and E. Frand, DATA MINING Practical Machine Learning Tools and Techniques Second Edition, Morgan Kaufmann Publishers, 2005.
  12. D. C. Montgomery, E. A. Pech and G. G. Vining, Introduction to Linear Regresson Analysis Fourth Edition, Wiley Interscience. 2006,
  13. S. Russell and P. Norvig, Artificial Intelligence A Modem Approach Second Edition, Prentice Hall. 2002.