A Flexible Miniature Robot Based on Fuzzy Wavelet Neural Network Control

摘要

A 3-DOF robot based on inchworm-type motion mechanism is presented for miniature endoscope inspection. The robot is actuated with pneumatic artificial muscle and clamped by two air chambers. The dynamic model of the robot is built. In order to solve the problems of low stiffness and the nonlinear movement characteristic of the robot system, a fuzzy wavelet neural network (FWNN) controller is proposed to control the robot position servo system using the principle of the pulse width-modulation (PWM). Using gradient method the learning of FWNN is performed to find optimal values of the parameters of controller. Result of simulation of the robot control system based on FWNN is compared with the simulation result of the control system based on wavelet neural network (WNN) and fuzzy neural network (FNN). Simulation and experiment results both demonstrate the training of FWNN controller is faster and it can effectively improve the control quality.