Adaptive learning with large variability of teaching signals for neural networks and its application to motion control of an industrial robot

Authors:
Fusaomi Nagata;Keigo Watanabe
Affiliations:
Department of Mechanical Engineering, Faculty of Engineering, Tokyo University of Science, Sanyo-Onoda, Japan 756-0884;Department of Intelligent Mechanical Systems, Graduate School of Natural Science and Technology, Okayama University, Okayama, Japan 700-8530
Venue:
International Journal of Automation and Computing
Year:
2011

Citing 8
Cited 1

Introduction to Robotics: Mechanics and Control

Introduction to Robotics: Mechanics and Control
The Influence of the Sigmoid Function Parameters on the Speed of Backpropagation Learning

IWANN '96 Proceedings of the International Workshop on Artificial Neural Networks: From Natural to Artificial Neural Computation
Feedback error learning and nonlinear adaptive control

Neural Networks
An adaptive-learning algorithm to solve the inverse kinematics problem of a 6 D.O.F serial robot manipulator

Advances in Engineering Software
A comparison between direct and indirect dynamic parameter identification methods in industrial robots

Robotica
Hybrid MATLAB and LabVIEW with neural network to implement a SCADA system of AC servo motor

Advances in Engineering Software
Neural network learning algorithm for a class of interconnected nonlinear systems

Neurocomputing
Improved exponential stability criteria for recurrent neural networks with time-varying discrete and distributed delays

International Journal of Automation and Computing

A precise robust fuzzy control of robots using voltage control strategy

International Journal of Automation and Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Recently, various control methods represented by proportional-integral-derivative (PID) control are used for robotic control. To cope with the requirements for high response and precision, advanced feedforward controllers such as gravity compensator, Coriolis/centrifugal force compensator and friction compensators have been built in the controller. Generally, it causes heavy computational load when calculating the compensating value within a short sampling period. In this paper, integrated recurrent neural networks are applied as a feedforward controller for PUMA560 manipulator. The feedforward controller works instead of gravity and Coriolis/centrifugal force compensators. In the learning process of the neural network by using back propagation algorithm, the learning coefficient and gain of sigmoid function are tuned intuitively and empirically according to teaching signals. The tuning is complicated because it is being conducted by trial and error. Especially, when the scale of teaching signal is large, the problem becomes crucial. To cope with the problem which concerns the learning performance, a simple and adaptive learning technique for large scale teaching signals is proposed. The learning techniques and control effectiveness are evaluated through simulations using the dynamic model of PUMA560 manipulator.