Adaptive neural network-based sliding mode tracking control for agricultural quadrotor with variable payload

In this paper, the path tracking controller for a class of agricultural quadrotor with variable payload under the influence of the model uncertainties and exogenous disturbances is proposed. Neural network-based adaptive control method is adopted to approximate the unknown and continuous dynamic of the quadrotor as well as to offset model uncertainties. Then a sliding mode control approach is employed to ensure that tracking errors are convergence. In order to compensate for payload changes, the total mass of the aircraft is estimated by using adaptive technique. Finally, a neural network-based adaptive sliding mode control algorithm is proposed to eliminate the effects of model uncertainties and exogenous disturbances so that path tracking of the quadrotor could be achieved. The asymptotic stability of the tracking system is confirmed by Lyapunov stability theory. The effectiveness of the proposed control strategy is verified by simulation results.