A dynamic neural network for adaptive optimal learning of robot motion with guaranteed convergence rate

This paper presents an optimal learning controller for uncertain robot systems which makes use of simple dynamic neural network units to estimate uncertain parameters and learn the unknown desired optimal input. With the aid of a Lyapunov function, it is shown that all the error signals in the system are bounded and the robot trajectory converges to the desired one globally and exponentially. The effectiveness of the proposed controller is shown by applying the controller to a planar robot manipulator