Neural Network-Based Adaptive Fractional-Order Backstepping Control of Uncertain Quadrotors with Unknown Input Delays

Adaptive control is essential and effective for reliable quadrotor operations in the presence of uncertain modeling parameters unknown time-delayed inputs. This paper presents an original radial basis function neural network-based adaptive fractional-order backstepping controller (RBF-ADFOBC). The nonlinearity inputs eliminated by introducing augmented state variable via Pade’s approximation method. For each subsystem dynamics, a companioned second-order compensation system developed. candidate Lyapunov functions are then properly designed incorporating errors, parameter uncertainties estimation errors networks’ weight vectors. It shown that semi-globally uniformly ultimately boundedness all variables error can be guaranteed. In addition, trajectory-tracking driven to adjustable small neighborhood origin setting selectable parameters. Numerical simulations reveal tracking performance proposed improved continuously as fractional order increases specific positive value, with negative may demonstrate higher robustness uncertainties. Favorably, comparison other two previous controllers further reveals superior accuracy RBF-ADFOBC controller.