Trajectory tracking controller design using neural networks for a tiltrotor unmanned aerial vehicle

Abstract

This article presents a design of trajectory tracking controller for a tiltrotor unmanned aerial vehicle (UAV). The objective of this design is to control the tiltrotor aircraft with one fixed controller architecture for all flight modes, viz. helicopter mode, conversion mode, and aeroplane mode. The controller is implemented using two time-scale separations, and thus comprises an inner loop for attitude control and an outer loop for trajectory control. The dynamic model inversion (DMI) technique is applied to both the control loops such that the inner-loop and the outer-loop DMIs are driven using the angular equations of motion and the translational equations of motion, respectively. In addition, online adaptive neural networks are employed to compensate for the model inversion errors of the inner loop and the outer loop due to the lack of complete knowledge of tiltrotor aircraft dynamics. The pseudo-control hedging algorithm is adopted to reduce the instability problem caused by the time-delay of control loops, saturation, and rate limit of actuators. The trajectory tracking controller is evaluated using a sophisticated six-degree-of-freedom non-linear simulation programme with an approach and landing scenario including all flight modes of a smart UAV, a tiltrotor UAV.