Adaptive Neural Composite Learning Finite-Time Control for a QUAV with Guaranteed Tracking Performance

This paper discusses the neural adaptive composite learning finite-time control for a quadrotor unmanned aerial vehicle (QUAV). Based on the command filter backstepping control (CFBC) scheme, the computational complexity caused by repetitive derivation and the inverse effect of the filter error are effectively removed. Moreover, the neural networks (NNs) are employed to identify the nonlinear coupling terms in the controlled vehicle, and the prediction error is introduced to adjust the composite learning law of neural weights, which improves the learning ability of NNs. Then, an adaptive neural composite learning finite-time prescribed performance controller is designed to achieve the convergence constraint on the tracking error, which makes the tracking error always in the planned steady-state region, and all variables of the closed-loop system are practical finite-time bounded. Finally, simulation results are shown to demonstrate the validity of the proposed method.