Asymptotic attitude tracking of the rotorcraft-based UAV via RISE feedback and NN feedforward

This paper presents an asymptotic attitude tracking controller for a rotorcraft-based unmanned aerial vehicle (RUAV) using the robust integral of the signum of the error(RISE) feedback and neural network (NN) feedforward terms. Usually, the typical NN-based attitude controller guarantees the uniformly ultimately bounded stability. In this study, semi-global asymptotic tracking of the RUAV is guaranteed by the RISE feedback term and NN feedforward term adapted by the projection method. The controller is basically designed by the linear dynamic model inversion method whose model is obtained by the linearization of the nonlinear RUAV model at the hover flight. Then, the uncertainty generated in the linearization is removed by the RISE feedback and NN feedforward terms. The asymptotic tracking of the attitude states is proven with the Lyapunov stability analysis, and a numerical simulation using the nonlinear RUAV model is performed to validate the effectiveness of the proposed controller.