Design of an Intelligent Controller for Station Keeping, Attitude Control, and Path Tracking of a Quadrotor Using Recursive Neural Networks

During recent years there has been growing interest in unmanned aerial vehicles (UAVs). Moreover, the necessity to control and navigate these vehicles has attracted much attention from researchers in this field. This is mostly due to the fact that the interactions between turbulent airflows apply complex aerodynamic forces to the system. Since the dynamics of a quadrotor are non-linear and the system is a multivariable one, moreover, it has six degrees of freedom for only four control inputs, then it is an under actuated system. This is why conventional control algorithms employed to track desired trajectories of fully actuated aerial vehicles are no longer applicable for quadrotors. The main step in the manufacturing of a fully autonomous unmanned aerial vehicle is to design a controller which stabilizes the aerial vehicle in the presence of uncertainties and disturbances, then navigate it along a desired trajectory. The aim of this study is to design and implement an intelligent controller for station keeping, attitude control, and path tracking of a quadrotor. For this purpose, an artificial neural network method was employed. The artificial neural network is one of the most powerful and useful tools in the modification of a control system. In this study, the control methods conventionally applied to quadrotors are reviewed at first. Then, in order to analyze the behavior of the system and also to design the controller, the state equations of a quadrotor are discussed. Following that, the design of a recurrent neural network based non-linear PID control algorithm is presented. Finally, the results of the simulation performed are presented, and the performance of the proposed algorithm are investigated. It was shown that by using the proposed algorithm, the quadrotor tracks the desired trajectory, and simultaneously, its attitude is stabilized.

کلیدواژه ها:

Artificial Neural Network ، Intelligent Controlling ، Non-Linear PID Control ، Quadrotor ، Station Keeping ، Trajectory Tracking