Robust control of quadrotor MAV using self‐organizing interval type‐II fuzzy neural networks (SOIT‐IIFNNs) controller

Abstract

PurposeQuadrotor micro aerial vehicle (MAV) is nonlinear and under actuated plant, and it is difficult to obtain an accurate mathematical model for quadrotor MAV due to uncertainties. The purpose of this paper is to propose one robust control strategy for quadrotor MAV to accommodate system uncertainties, variations, and external disturbances.Design/methodology/approachThe robust control strategy is composed of two self‐organizing interval type‐II fuzzy neural networks (SOIT‐IIFNNs) and one PD controller: the PD controller is adopted to control the attitude and position; one of the SOIT‐IIFNNs is designed to learn the inverse model of quadrotor MAV online; the other SOIT‐IIFNNs is the copy of the former one to compensate for model errors, system uncertainties and external disturbances, both structure and parameters of SOIT‐IIFNNs are tuned online at the same time, and then the stability of the resulting quadrotor MAV closed‐loop control system is proved using Lyapunov stability theory.FindingsThe validity of the proposed control method has been verified through real‐time experiments. The experimental results show that the performance of SOIT‐IIFNNs is significantly improved compared with Backstepping‐based controller.Practical implicationsThis approach has been used in quadrotor MAV, the controller works well, and it could guarantee quadrotor MAV control system with good performances under uncertainties, variations, and external disturbances.Originality/valueThe proposed SOIT‐IIFNNs controller is interesting for the design of an intelligent control scheme. The main contributions of this paper are: the overall closed‐loop control system is globally stable, demonstrated by Lyapunov stable theory; the tracking error can be asymptotically attenuated to a desired small level around zero by appropriate chosen parameters and learning rates; and the quadrotor MAV control system based on SOIT‐IIFNNs controller can achieve favorable tracking performance.