On Developing The Intellingent contro System of a Robot Manupulator by Fussion of Fuzzy Logic and Neural Network

퍼지논리와 신경망 융합에 의한 로보트매니퓰레이터의 지능형제어 시스템 개발

  • Published : 1995.03.01

Abstract

Robot manipulator is a highly nonlinear-time varying system. Therefore, a lot of control theory has been applied to the system. Robot manipulator has two types of control; one is path planning, another is path tracking. In this paper, we select the path tracking, and for this purpose, propose the intelligent control¬ler which is combined with fuzzy logic and neural network. The fuzzy logic provides an inference morphorlogy that enables approximate human reasoning to apply to knowledge-based systems, and also provides a mathematical strength to capture the uncertainties associated with human cognitive processes like thinking and reasoning. Based on this fuzzy logic, the fuzzy logic controller(FLC) provides a means of converhng a linguistic control strategy based on expert knowledge into automahc control strategy. But the construction of rule-base for a nonlinear hme-varying system such as robot, becomes much more com¬plicated because of model uncertainty and parameter variations. To cope with these problems, a auto-tuning method of the fuzzy rule-base is required. In this paper, the GA-based Fuzzy-Neural control system combining Fuzzy-Neural control theory with the genetic algorithm(GA), that is known to be very effective in the optimization problem, will be proposed. The effectiveness of the proposed control system will be demonstrated by computer simulations using a two degree of freedom robot manipulator.

로보트 매니퓰레이터는 고도의 비선형 시변 시스템으로써 정밀한 제어가 매우 어려운 제어 대상으로 인식되어 왔으며 따라서 수많은 제어이론의 적용대상이 되어왔다. 로보트 매니퓰레이터의 제어에는 두가지 형태가 있는데 한가지는 궤적계획이고, 또한가지는 궤적 추종이다. 본 논문에서는 궤적 추종을 목적으로 하고, 이를 위해 퍼지논리와 신경회로망을 결합한 지능형 제어를 제안한다. 제안된 제어시스템은 사고 및 추론과 같은 인간의 인식처리에 해당하는 불확실한 것들의 구체화를 가능케하는 퍼지논리와 학습 및 병렬처리능력이 있는 신경회로망을 융합하여 구성된 퍼지-신경망 제어시스템이다. 그러나 이러한 장점을 갖는 퍼지-신경망 제어기도 정확한 제어 규칙의 발생은 어려은데 이는 신경회로망의 지역적 최소치에 빠지는 특성에 기인한다고 볼 수 있다. 그리고 일반적으로 시스템의 비선형 정도는 탐색에 의해서만 알수 있는 성질의 것이므로 본 논문에서는 최적의 탐색알고리듬으로 널리 인정되고 있는 유전알고리듬을 사용하여 전역적이 규칙공간을 탐색한 후 이를 바탕으로 퍼지-신경망 제어기를 완성한다. 제안된 제어시스템의 효율성은 2자유도의 로보트 매니퓰레이터를 사용하여 컴퓨터의 모의실험을 통해 입증된다.

Keywords

References

  1. Fuzzy Sets and Syst. v.16 Fuzzy control of model car M.Sugeno;M.Nishida
  2. IEEE Control Sys. Mag. Use a rule-based system for Process control J,A,Benard
  3. IEEE Control Sys. Mag. Development of fuzzy algorithms for servo systems Y.F.Li;C.C.Lau
  4. Fuzzy Sets and Syst. v.26 Fuzzy Self-Organizing Contoller and its Application for Dynimic Processes S.Shao
  5. Int. Conf. on Fuzzy Thory & Neural Network(IIZUKA '90) v.1 no.13-26 Fusion Technology of Fuzzy Theory and Neural Network-Survey and Future Directions H.Takigi
  6. Proc. of IECON'90 v.2 Composition Method of Fuzzy Neural Networks S.Horikawa;T.Horuhasi;S.Okuma;Y.Uchikawa
  7. Proc. of IECON'90 v.2 Fuzzy and Neural Network Controller Y.Dote
  8. Proc. 2nd UEEE Int. Conf. Fuzzy Systems Intergrating Design Stages of Fuzzy Systems Using Genetic Algorithms M.Lee;H.Takagi
  9. Proc. of the fourth Int. Conf. on Genetic Algorithms Fuzzy logic synthesis with genetic algorithms P.Thrift
  10. Genetic Algorithms in Search, Optimization & Machine Learning David E. Goldberg
  11. Handbook of Genetic Algorithm L.Davis
  12. IEEE Trans. on Neural Networks v.5 no.1 Genetic Evolution of the Topology and Weight Distribution of Neural Networks V.Maniezzo
  13. IEEE Trans. on Neural Networks v.5 no.1 An Evolutinary Algorithm that constructs Recurrent Neural Networks P.J.Angeline;G.M.Saunders;J.B.Pollack
  14. IEEE Trans. Syst. Man Cybernet. v.15 Fuzzy identification of systems and its applocations to modeling and control T.Takagi;M.Sugeno
  15. IEEE Control Syst. Mag. Hierarchical neural network model of for voluntary movement with application to robotic M.Kawato;Y.Uno;M.Isobe;R.Suzuki
  16. Introduction to Robotics : Mechanics and Control(2nd ed.) J.J.Craig
  17. Fifth IFSA World Congress Self-Organixation of Fuzzy Rule Base Using Genetic Algorithm Y.H.Kim;H.T.Jeon(et al.)