Control of Robot Manipulator using VSS-Recurrent Neural Networks

VSS-귀한 신경망을 이용한 로보트 매니퓰레이터 제어

  • Published : 1996.12.01

Abstract

비선형 동적 시스템을 제어하기에 적합한 귀환 신경망에 대한 연구는 안정성(stability) 유도와 학습 알고리듬(learning algorithm) 개발의 두가지 방향으로 지금까지 많은 연구가 이루어져 왔다. 본 논문에서는 비선형 동적 시스템 제어시 온라인(on-line) 학습이 가능하고 안정성을 보장하도록 귀환 신경망의 학습 알고리듬에 VSS이론을 도입하여 개발한다. 또한 개발한 학습 알고리듬을 사용한 귀환 신경망을 전형적인 비선형 동적 시스템인 로보트 매니퓰레이터의 제어 시스템에 적용하고 기존의 학습 방법의 적용 결과와 비교하여 개발한 제어 알고리듬의 효용성을 입증한다.

Keywords

References

  1. IEEE Trans. on Neural Networks v.1 no.1 Identification and Control of Dynamical system Using Neural networks K.S.Narendra;K.Patharathy
  2. IEEE Trans. on Neural Networks v.4 no.6 Identification and Decentralized Adaptive Control Using Dynamical Neural Networks with Application to Robotic Manipulators A.Karakasoglu;S.I.suharsanan;M.K.Sundareshan
  3. IEEE Trans. on SMC v.24 no.3 Adaptive Control of Unknown Plants Using Dynamical Neural Networks George A.Rovithakis;A.Christodoulou
  4. Proc. of the 1998 Connectionist Models Summer School Learning to Solve Random-Dot Stereograms of Dense Transparent Surfaces with Recurrent Backpropragation Guan N.;T.J.Sejnowski
  5. IEEE Trans. on SMC v.18 no.1 On the Stability, Storage Capacity, and Design of Nonlinear Continuous Neural Networks A.Guez;V.Protopopsecu;J.Barhen
  6. Proc.1993 IEEE Int.Conf.Neural Net. v.Ⅱ Dynamics and Stability of Mutilayered Recurrent Neural Networks Liang Jin;Peter N.Nikiforuk;madan M.Gupta
  7. Neural Computation v.1 Recurrent Backpropagation and the dynamical Approach to Adaptive Neural Computation F.J.Pineda
  8. Neural Computation v.1 Learning State Space Trajectories in Recurrent Neural Networks B.A.Pearlmutter
  9. 1987 Proc. of IEEE First Int.Conf.neural Networks v.Ⅱ A Learning Rule for Asynchronous Perception with Feedback in a combinatorial Environmnt L.B.Almeida
  10. Neural Computation v.1 A Learning Algorithm for Continully Running Fully Recurrent Neural Networks R.J.Williams;D.Zipser
  11. Biological Cybernetics v.62 A Real Time Learning Algorithm for Recurrent Analog neural Networks M.Sato
  12. Fifth IFSA World Congress v.2 Recurrent Neural Networks Y.Uchikawa;H.Takase;T.Watanabe;K.Gouhara
  13. Sliding Modes and Their Application in Variable Structure System V.I.Utkin