Improvement of learning performance and control of a robot manipulator using neural network with adaptive learning rate

적응 학습률을 이용한 신경회로망의 학습성능개선 및 로봇 제어

  • Published : 1997.08.01

Abstract

In this paper, the design and the implementation of the adaptive learning rate neural network controller for an articulate robot, which is being developed (or) has been developed in our Automatic Control Laboratory, are mainly discussed. The controller reduces software computational load via distributed processing method using multiple CPU's, and simplifies hardware structures by the time-division control with TMS32OC31 DSP chip. Proposed neural network controller with adaptive learning rate structure using expert's heuristics can improve learning speed. The proposed controller verifies its superiority by comparing response characteristics of conventional controller with those of the proposed controller that are obtained from the experiments for the 5 axis vertical articulated robot. We, also, present the generalization property of proposed controller for unlearned trajectory and the change of load through experimental data.

Keywords

References

  1. The International Journal of Robotics Research v.6 no.2;Summer Application of a general maniqulators W. Thomas Miller Ⅲ;Filson H. Glanz;L. Gordon Kraft Ⅲ
  2. IEEE International Conference on Robotics and Automation On reference trajectory modification approach for cartesian space neural network control of robot manipulators Seul Jung;T. C. Hsia
  3. IEEE International Conference on Robotics and Automation On neural network application to robust impedance control of robot manipulators Seul Jung;T. C. Hsia
  4. ICARCV '92 Second International Conference on Automation, Robotics and Computer Vision v.3 Disturbance rejection in the control of the robotic manipulators using a neural network structure Qing Li;A. N. Poo;C. L. Teo
  5. Intellignet Robots and Systems v.1 Trajectory tracking neural network controller for a robot Mechanism and Lyapunov Theory of Stability Riko Safaric;Karel jezernik
  6. IEEE International Conference on Systems, Man and Cybernetics v.3 Stability analysis of robot manipulators subject to feedforward neural network controllers Ahmad abdalla;Lilong Cai
  7. Int. J. Control. v.60 no.6 Adaptive model-based control using neural networks P. M. Mills;A. Y. Zomaya;M. O. Tade
  8. IEEE Control System Real-Time neural network control of a biped walking robot W. Thomas Miller, Ⅲ
  9. Intelligent Robots and Systems v.3 Generation of optimal configuration for a reducdant manipulator with a trained neural network D. C. Kar;K. Jayarajan;P. K. Pal
  10. Proc. of the IEEE Int. Conf. o Neural Networks v.4 Neural computation and learning strategy for manipulator position control K. Tsutumi;H. Matsumoto
  11. Neural Networks v.1 Feedback error learning neural network for trajectory control of a robotic manipulator M. Kawato;H. Miyamoto;T. Setoyama;R. Suzuki
  12. 전기학회 논문지 v.40 no.8 신경회로를 이용한 6축 로보트의 역동력학적 토크제어 오세영;조문중;문영주
  13. Neural Networks Algorithms, Applications, and Programming Techniques James A. Freeman
  14. 학습하는 기계 신경망 이상원
  15. Funcdamentals of Artificial Neural Networks Mohamad H. Hassoun
  16. 로봇 동역학과 제어 강철구;권인소;윤중선;정완균