A two-layer recurrent neural network for kinematic control of redundant manipulators

Abstract

A recurrent neural network is presented for the kinematic control of kinematically redundant robot manipulators. The proposed recurrent neural network is composed of two bidirectionally connected layers of neuron arrays. While the signals of desired velocity of the end-effector are fed into the input layer, the output layer generates the joint velocity vector of the manipulator. The proposed recurrent neural network is shown to be capable of asymptotic tracking for the motion control of kinematically redundant manipulators.