An unsupervised learning based neural network approach for a robotic manipulator

This paper presents a neural network approach for solving the inverse kinematics of a robotic manipulator. Inverse kinematics equations are more challenging than the forward kinematics equations and therefore are more computationally complex to solve. Here, we are using a neural network approach due to its ability to give more accurate results in complex situations as compared to the other approaches. Moreover, we are using this model for trajectory tracking of a two DOF robotic arm to test its validity in real life situations.