Optimal neural network output feedback control for robot manipulators

Abstract

A robust neural network output feedback scheme is developed for the joint motion control of robot manipulators without directly measuring joint velocities. A neural network observer is used to estimate the joint velocities. The neural network weights in both the observer and the controller are tuned online, with no off-line learning phase required. No exact knowledge of the robot dynamics is required so that the neural network controller is model-free and so applicable to a class of nonlinear systems which have a similar structure to robot manipulators. Implementation results on a single-link robot are reported to show the performance of the proposed technique.