Adaptive Neural-Network-Based Nonsingular Fast Terminal Sliding Mode Control for a Quadrotor with Dynamic Uncertainty

This paper proposes an adaptive neural-network-based nonsingular fast terminal sliding mode (NN-NFTSMC) approach to address the trajectory tracking control problem of a quadrotor in presence model uncertainties and external disturbances. First, dynamic with uncertainty is derived. Then, scheme using (NFTSMC) proposed guarantee finite-time convergence its desired trajectory. NFTSMC firstly formulated for case that upper bound lumped known advance. Under this framework, disturbance observer by hyperbolic tangent nonlinear differentiator (TANH-NTD) designed estimate interference, neural network (NN) approximator used develop online uncertainty. Subsequently, algorithms are compensate approximation error update NN weight matrix. An NN-NFTSMC algorithm provide system robustness disturbance. Moreover, Lyapunov-based employed prove global stability closed-loop errors. The results comparative simulation study other recent methods illustrate method reduces chattering effectively has remarkable performance.