A novel data-driven control for fixed-wing UAV path following

In this paper, a novel data-driven control (DDC) algorithm is proposed to adaptive control for fixed-wing (Unmanned Aerial Vehicle) UAV path following using input and output (I/O) data. Differently from model based control, data-driven control reduces the dependence of accurate mathematics model in process of controller designation. The key difficulty in fixed-wing UAV path following is that the model of UAV is generally underactuated and nonlinear, and easy to be affected by disturbances. The unique feature of this paper is that we explicitly employ data-driven control to design controller directly in two dimensions at constant height to overcome the drawback of dynamical uncertainties and wind disturbances. The tracking error is guaranteed converging to zero and simulation results and flight test show the effectiveness and applicability of the control law.