Quaternion-Based Adaptive Backstepping RFWNN Control of Quadrotors Subject to Model Uncertainties and Disturbances

Abstract

This paper presents a quaternion-based adaptive backstepping control method using recurrent fuzzy wavelet neural network (RFWNN) for regulation and trajectory tracking of quadrotors subject to model uncertainties and disturbances. For the controller synthesis, a more complete model of an uncertain quadrotor is first obtained by incorporating with mass variations and wind disturbances, which are online learned by using the RFWNN. Afterward, a quaternion-based adaptive backstepping RFWNN controller is synthesized by integrating backstepping, quaternion control, and the RFWNN online learner. The closed-loop stability of the overall quadrotor control system is shown semi-globally uniformly ultimately bounded via Lyapunov stability theory. The effectiveness and performance of the proposed control method are well exemplified by conducting four simulations on hovering and three-dimensional sinusoidal trajectory tracking control of a quadrotor. Through the simulation results, the proposed control method is shown superior by comparing to two existing methods.