Design and Practical Implementation of a Feed-Forward Neural Observer to Control Quadrotor

In this paper a neural observer is deigned to control a Quadrotor Drone. Quadrotor is a type of flying robot which can fly vertically and has a simple structure. This robot is one of the best models of flying robot that is considered by many researchers recently. Because of nonlinear dynamics of the system, Stability of the control process has an important role in this robot. In this study first, a PD controller is designed to track the desired state and stabilizing the quadrotor based on particle swarm optimization algorithm. Nonlinear observer is then synthesized in order to estimate the unmeasured states. Then a neural network observer is designed and trained based on data that extract of nonlinear observer. After that, simulation results are also provided in order to illustrate the performances of the proposed controller and observer. Finally In addition to simulation we have practically implemented these control and observer methods on a quadrotor test bench. Practical implementation results demonstrate the effectiveness of the presented method.