The Computation of the Inverse Kinematics of a 3 DOF Redundant Manipulator via an ANN Approach and a Virtual Function

Shahnaz Habibkhah, Rene Mayorga


In this paper a method based on Artificial Neural Networks (ANNs) is presented to solve the Inverse Kinematics (IK) of 3 degrees of freedom (DOF) redundant manipulators. In order to obtain the manipulator’s joint angles coordinates and solve the IK problem with acceptable accuracy; the forward kinematics equations of the manipulator are used to obtain position of the end effector, and also a virtual auxiliary function is included in the ANN approach. Then, the trained ANN’ ability to track a designed target trajectory is tested inside the workspace of the manipulator in two scenarios with different inputs data to the ANN.


Paper Citation