Attitude Control of Fixed-Wing UAVs under Input Constraints

Fixed-wing unmanned aerial vehicles (UAVs) have gained widespread use in both civilian and military applications due to their low cost, long endurance, and high operational efficiency. However, ensuring precise attitude control under physical constraints such as input saturation remains a significant challenge. This study addresses the attitude control problem of fixed-wing UAVs under input constraints. The system model is divided into two subsystems, and a high-gain backstepping controller is designed. A neural network term is incorporated into the control method to overcome the effects of the residual control signal. The performance of the proposed control scheme is demonstrated through numerical simulations, showing that the method operates efficiently even in the presence of noise in the state variables.