Stochastic Adaptive Control for a Kind of Fixed-Wing UAV with State Constraints

Fixed-wing unmanned aerial vehicles (UAVs) fly in a complex environment, which leads to multiple uncertainties in the flight control system. Furthermore, nonlinear disturbances are inevitable in the dynamics of fixed-wing UAVs. In this paper, we focus on neural network-based adaptive attitude control for fixed-wing UAVs subjected to stochastic multiple uncertainties and state constraints. In the control scheme, radial basis function neural networks are used to approximate unknown nonlinear uncertainties, which can effectively reduce the adverse impact caused by unknown time-varying disturbances and random uncertainties. All the signals in the closed-loop system are allowed to be semi-globally uniformly ultimately bounded, and the state constraints are guaranteed by establishing a stochastic Lyapunov function. Simulation results show the effectiveness of the proposed control scheme in this paper.