Abstract
This paper proposes the approach of employing artificial neural network (ANN) as a disturbance observer in the sliding mode control of a quadrotor. ANN is adopted for the disturbance estimation task in this study. A quadrotor type unmanned aerial vehicle is considered as the system of interest to apply and assess the performance of ANN as a disturbance observer. Quadrotor continuous time mathematical model is taken into account in a standard integrator based on Euler discritization. Both parametric uncertainties and external disturbances are lumped in a disturbance term and added to the nominal model. That term is approximated by ANN in an output error prediction context by minimizing the state estimation error via gradient descent. The proposed disturbance observer works in collaboration with a standard nonlinear observer. It is only necessary for estimating the system states using the measured system output while ANN performs the estimation of disturbance. Simulation results demonstrate that robustness of the employed control method is empowered due to the significant closed loop disturbance estimation by ANN disturbance observer compared to some of well-known nonlinear observers in the literature.