Forward and inverse kinematics solution of a robotic manipulator using a multilayer feedforward neural network

Abstract

In this paper, a multilayer feedforward neural network (MLFFNN) is proposed for solving the problem of forward and inverse kinematics of the manipulator. For forward kinematics solution, two cases are presented. The first case is that one MLFFNN is designed and trained to find only the position of the robot end-effector. In the second case, another MLFFNN is designed and trained to find both the position and the orientation of the robot end-effector. Both MLFFNNs are designed considering the joints’ positions as the inputs. For inverse kinematics solution, a MLFFNN is designed and trained to find the joints’ positions considering the position and the orientation of the robot end-effector as the inputs. For training any of the proposed MLFFNNs, data are generated in MATLAB using two different cases. The first case is considering incremental motion of the robot joints, whereas the second case is considering a sinusoidal motion. This method is designed to be generalized to any DOF manipulator. For simplicity, it is applied using a 2-DOF planar robot. The results show that the approximation error between the desired and estimated output is very low and approximately zero. The MLFFNN is efficient to solve the forward and inverse kinematics problems.