Trajectory tracking neural network controller for a robot mechanism and Lyapunov theory of stability

In this paper a neural network controller for trajectory tracking for a two DOF SCARA robot mechanism is presented. Two types of neural network controllers have been built: a joint space neural network controller and a task space neural network controller. The two controllers have been compared with the computed torque method controller, also in the joint and task space. The four controllers were tested on a real robot mechanism. Lyapunov theory, for deriving the adaptation law, or the learning algorithm of neural networks, was used to prove the robot system stability with a neural network controller.