Adaptive Neural Network Control of an Airborne Robotic Manipulator System

Abstract

In this paper, adaptive neural network control is studied for an Airborne Robotic Manipulator (ARM) system. To handle the uncertainties and disturbances of the ARM system and improve its robustness, radial basis function neural network (RBFNN) is used for approximating unknown dynamics model of the system to realize better adaptive neural network control. With using the adaptive law verified via the Lyapunov's method, the stability of the system and the convergence of the weight adaptation are guaranteed. The simulation studies are performed to illustrate the effectiveness of the controller. The proposed RBFNN-based control scheme is used for approximating errors, which can be effective in making learning objective smaller and learning time shorter compared with conventional approaches.