Comparison of inverse kinematics solutions using neural network for 6R robot manipulator with offset

Abstract

An artificial neural network (ANN) using backpropagation algorithm is applied to solve inverse kinematics problems of industrial robot manipulator. 6R robot manipulator with offset wrist was chosen as industrial robot manipulator because geometric feature of this robot does not allow solving inverse kinematics problems analytically. In other words, there is no closed form solution for this problem. In order to define orientation of robot end-effector, three different representations are used here: homogeneous transformation matrix, Euler angles and equivalent angle axis. These representations were compared to obtain inverse kinematics solutions for 6R robot manipulator with offset wrist. Simulation results show that prediction performance from the approximation accuracy point of view is satisfactory with low effective errors based on 10 degrees data resolution