A PD-Fuzzy Controller Design of 2 D.O.F. Wheeled Mobile Robot Using Genetic and Immune Algorithm

유전 및 면역 알고리즘을 이용한 2자유도 구륜 이동 로봇에 대한 PD-Fuzzy 제어기 설계

  • Kim, Sung-Hoe (Dept.of Electronics Engineering, Kyunghee University) ;
  • Kim, Ki-Yeoul (Dept.of Electronics Engineering, Kyunghee University) ;
  • Lim, Ho (Dept.of Electronics Engineering, Kyunghee University) ;
  • Park, Chong-Kug (Dept.of Electronics Engineering, Kyunghee University)
  • 김성회 (경희대학교 전자공학과) ;
  • 김기열 (경희대학교 전자공학과) ;
  • 임호 (경희대학교 전자공학과) ;
  • 박종국 (경희대학교 전자공학과)
  • Published : 2000.09.01

Abstract

It is not so easy to control the wheeled mobile robot because of some causes like non-holonomic constraints. To overcome these problems, a controller that PD system is combined with fuzzy process is composed of several steps that have each separate algorithm and niche search algorithm and immune algorithm is applied partly. Output term set is changed by search that is performed to get optimal elements and then the rule base is also reformed. The fitness for the altered system is estimated and the surplus elements are removed. After the adjustment of output term set and rule base is finished, input and output membership functions is tuned.

구륜 이동 로봇(Wheeled Mobile Robot)은 제어기 설계에 있어 Nonholonomic Constraints등에 의해 많은 어려움을 지닌다. 본 논문에서는 구륜 이동 로봇의 제어를 위해 PD와 퍼지 시스템이 결합된 제어기가 설계되며, 유전알고리즘에 기초되어 최적 퍼지시스템이 형성된다. 시스템의 최적화 과정은 독립적으로 수행되는 여러 단계들로 이루어지며, 각 단계마다 다른 형식의 알고리즘이 적용되며 효율적 탐색을 위해 Niche알고리즘 및 면역 알고리즘이 결합되어 적용된다. 각 출력용어집합은 최적의 원소들을 얻기 위해 수행되는 탐색에 의해 그 구성이 변화되며, 변화된 출력용어집합의 구성 원소와 관계된 규칙기반이 동시에 조절된다. 출력용어집합의 추가된 원소들 및 조절된 규칙에 대한 적합성이 평가되고 제어 성능의 향상에 기여하지 못한 부분들은 제거된다. 출력변수의 용어집합 및 규칙에 대한 반복적 조절 과정이 완료된 후, 입력 소속함수들에 대한 조정이 제약조건을 가지고 수행되며, 진화연산에 의한 출력소속함수들에 대한 조정이 수행된다.

Keywords

References

  1. C.samson and K.Ait-Abderrahim, 'Feedback control of nonholonomic wheeled cart in cartesian space', Proc. 1991 int. Conf. Robot Auto., pp. 1136-1141, Apr. 1991 https://doi.org/10.1109/ROBOT.1991.131748
  2. Y. Zhao, 'Theoretical and Experimental Studies of Mobile Robot Navigation', Ph.D. thesis, the University of Michigan, 1991
  3. J. Barraquand and J. C. Latomber, 'On nonholonomic mobile robots and optimal a mneuvering', 1th Int. Conf. Intelligence Conf., Albany, NY., 1989 https://doi.org/10.1109/ISIC.1989.238696
  4. George J. Klir and Bo Yuan, Fuzzy Sets and Fuzzy Logic Theory and Applications Prentice-Hall, 1995
  5. D.Driankov and H.Hcllendoomand M. Heinfrank, An Introduction To Fuzzy Controll, Springer, New York, 1996
  6. Madan M. Gupta and Naresh K.Sinha, Intelligent Control Systems, IEEE Press, 1996
  7. J-S. R. JANG and T-C. SUN, Neuro-Fuzzy and Softcomputing, Prentice Hall, 1997
  8. Gregory V. TAN and Xiheng HU, 'On Design Fuzzy Controller using Genetic Algorithm', in Proc., 5th IEEE Int. Conf. Fuzzy System, pp. 905-911, 1996
  9. J. L. Castro, 'How many rules are necessary to get a good fuzzy controller for controll problem?', in Proc., 6th IEEE Int. Conf. Fuzzy System, pp. 749-754, 1997 https://doi.org/10.1109/FUZZY.1997.622804
  10. J. Qiu, Mochael Walters. 'Learning of Membership Function of Fuzzy Behaviours for a Mobile Robot Control System', in Proc., the 1997 lEEE/RSJ International Conference on Intelligent Robot and Systems, pp. 772-777, 1997 https://doi.org/10.1109/IROS.1997.655098
  11. Chin-chih Hsu, Shin-ichi Yamada, Hideji Fujikawa. Koichiro Shida, 'A Multi-Operator Self-Tuning Genetic Algorithm for Fuzzy Control Rule optimization', in Proc., 5th IEEE Int. Conf. Fussy System, pp. 842-847, 1996 https://doi.org/10.1109/IECON.1996.565987
  12. Lin. C. T., 'Neural Fuzzy Control Systems with Structure and Parameter Learning', Fuzzy Set Syst. vol 70, pp183-212, 1995 https://doi.org/10.1016/0165-0114(94)00216-T
  13. Nauck, D., and R.Kruse.. 'A fuzzy neural network learning fuzzy control rules and membership functions by error back propagation.' Proc. IEEE Int. Conf. Newral Networks, vol 2, pp. 1022-1027, 1993 https://doi.org/10.1109/ICNN.1993.298698
  14. Joao Pedro Pedroso, 'Niche Application in Vechile Routing'. Proceedings of the IEEE international Conference on Evolutionay Computation, pp. 177-182, 1998 https://doi.org/10.1109/ICEC.1998.699497
  15. A. Ishiguro, Y.Watanabe and Y.Uchikawa:Dynamic Behavior Arbitration of Autonomous Mobile Robots Using Immune Networks, Proc. of ICEC'95, vol. 2. pp. 722-727, 1995 https://doi.org/10.1109/ICEC.1995.487474
  16. YongOug Chung and Chong-Kug Park, 'Position, Orientation, and Velocity Feedback Control Algorithm for Differential Mobile Robot' Jurnal of The Korea Institute of electromatics and Electronics, vol 34s, pp.657-690, 1997
  17. Sung-Hoe Kim, Chong-Kug Park, Flumio Harashima, 'Adaptive Fuzzy Controller Design for Trajectory Tracking of a 2 D.O.F. Wheeled Mobile Robot Using Genetic Algorithm', in Proc., IEEE/RSJ Int. Conf. Intelligent Robots And Systems, vol. 3, pp. 1584-1589, 1998 https://doi.org/10.1109/IROS.1998.724824