Abstract: Due to the underdriven nature of the UAV and the coupling resulting from the rigid connection with the robotic arm, robustness and high precision controllers are crucial for the UAV. In this paper, we simplify the rotor UAV system dynamics model. A global fast terminal sliding mode （GFTSM） controller is designed to ensure precise tracking of a predefined trajectory in the presence of perturbations. To enhance active disturbance rejection and achieve high tracking accuracy, we integrate an RBF neural network into the controller. This neural network estimates the total perturbations, including both internal coupling and external disturbances. By applying Lyapunov theory, we derive the controller and the neural network to ensure the stability of the system. In addition, we present a set of illustrative metrics to evaluate the performance of the designed controller. We compare the performance of our controller with that of other controllers through simulation. The results show that the proposed controller significantly improves the robustness and accuracy of the rotary wing UAV system and converges well.