Finite-Time Prescribed Performance Attitude Control for a Class of Fixed-Wing UAV with Structural Uncertainties

In this article, we focus on the finite-time prescribed performance control (FTPPC) of unmanned aerial vehicle (UAV) based on neural network. By introducing a novel concept called finite-time performance function (FTPF), the model is converted so that the tracking error can converge to the specified area within a finite time. In addition, radial basis function neural networks (RBFNNs) are used to approximate unknown nonlinear continuous functions, which can effectively avoid obstacles caused by unknown time-varying disturbances and random uncertainties. Simulation results have demonstrated that compared with the existing control algorithms, the proposed algorithm significantly improves the convergence speed, stability and robustness. Moreover, this algorithm has good adaptability to deal with the time-varying structural uncertainties faced with UAV.