Output Feedback Fault-Tolerant Attitude Control for Quadrotor Based on Neural Network Approximation

This paper explores the control of a quadrotor in the presence of attitude tracking and actuator failure, and introduces the Nussbaum function in the design of the backstepping controller in order to eliminate the influence of the unknown parameters, thus ensuring the stability and performance of the quadrotor. In order to estimate the unmeasurable states in the attitude tracking of the quadrotor, a novel design of a state observer for the quadrotor is also proposed and the use of neural networks to approximate the unknowns in the process. The proposed control scheme ensures that all signals of the quadrotor are bounded and the tracking errors converge to a small range around zero. Finally, numerical example results are also given to further demonstrate the effectiveness of the proposed control scheme.