Abstract In this article, a new triple-loop recurrent neural network and observer-based two-stage fast terminal sliding mode controller (TRNNO-TFTSMC) is proposed for a quadrotor unmanned aerial vehicle (UAV) with nonlinear dynamics and external disturbances. The two-stage fast terminal sliding mode control scheme is designed to guarantee fast convergence of trajectory tracking within a finite time. In the architecture of the flight control system, the triple-loop recurrent neural network (TRNN) is designed to approximate the nonlinear dynamics, which include system uncertainties and known nominal terms. Furthermore, to mitigate the impact of external disturbances and the approximation error of TRNN on the performance of the control system, an observer is employed. Finally, the closed-loop stability of the quadrotor system is ensured based on Lyapunov theory, and the outperformance of the proposed flight control scheme is clearly demonstrated through a comparative study with other techniques.
Wang et al. (Mon,) studied this question.