Robust adaptive neural network-based compensation control of a class of quadrotor aircrafts

• Published in: Journal of the Franklin Institute Vol. 357; no. 17; pp. 12241 - 12263
• Main Authors: Jin, Xiao-Zheng, He, Tao, Wu, Xiao-Ming, Wang, Hai, Chi, Jing
• Format: Journal Article
• Language: English
• Published: Elmsford Elsevier Ltd 01.11.2020; Elsevier Science Ltd
• Subjects: Adaptive control; Approximation; Attitudes; Compensation; Control methods; Disturbances; Mathematical functions; Neural networks; Robustness (mathematics); Simulation; Subsystems; Tracking control systems; Tracking problem; Uncertainty
• ISSN: 0016-0032; 1879-2693; 0016-0032
• DOI: 10.1016/j.jfranklin.2020.09.009

In this paper, the position and attitude trajectory tracking problem of a class of quadrotor aircrafts with bounded external disturbances and state-dependent internal uncertainties is addressed. Neural network (NN)-based methods are adopted to approximate the unknown uncertainties, while adaptive technique is used to estimate the unknown bounds of disturbances. Then, an adaptive compensation control scheme based on neural networks is proposed to compensate for the effects of disturbances and uncertainties. On the basis of Lyapunov stability theorem, bounded trajectory tracking of a position subsystem and asymptotic trajectory tracking of an attitude subsystem can be achieved by using the NN-based adaptive compensation control scheme in the presence of internal uncertainties and external disturbances. A numerical simulation is carried out to verify the effectiveness of the designed control method of quadrotor aircrafts.