saturated neural adaptive robust output feedback control of robot manipulators:an experimental comparative study

In this study, an observer-based tracking controller is proposed and evaluated experimentally to solve the trajectory tracking problem of robotic manipulators with the torque saturation in the presence of model uncertainties and external disturbances. in comparison with the state-of-the-art observer-based controllers in the literature, this paper introduces a saturated observer-based controller based on a radial basis function neural network. this technique helps the controller produce feasible control signals for the robot actuators. as a result, it efficiently diminishes the actuators saturation risk and consequently, a better transient performance is obtained. the stability analyses of the dynamics of the tracking errors and state estimation errors are given with the help of a lyapunov-based stability analysis method. the theoretical analyses will systematically prove that the errors are semi-globally uniformly ultimately bounded and they converge to a small set around the origin whose size is adjustable by a suitable tuning of parameters. at last, some real experiments are performed on a laboratory robotic arm to illustrate the efficiency of the proposed control system for real industrial applications.