Cooperative fuzzy hint acquisition for industrial redundant robots to avoid the joint limits

Abstract

A novel neural network (NN) based inverse kinematics solution of redundant manipulators is proposed to solve the joint limits problem. An adaptive learning algorithm for that NN is derived based on Lyapunov approach. Since the inverse kinematics has infinite number of joint angle vectors, a fuzzy neural network (FNN) is designed to provide an approximate value for that vector. This vector is fed into the NN as a hint input vector to guide the output of the NN within the self-motion. This FNN is designed based on cooperatively controlling each joint angle of the manipulator. Experiments are implemented for the PA-IO redundant manipulator and a comparative study is made with the gradient projection method.