This paper presents an improved model reference adaptive controller (I-MRAC) with RBF neural network approximation to deal with the model uncertainties, unknown actuator dynamics and input saturation of the unmanned aerial vehicle (UAV). On the one hand, the output of the RBF neural network (NN) is used as the compensator to eliminate the uncertainties of the system. On the other hand, the reference model is modified to deal with the unknown actuator dynamics and input saturation, improve stability and robustness, and prevent the high frequency oscillations. Meanwhile, the stability of the whole closed-loop system is proved by the Lyapunov analysis. The numerical simulation results of UAV attitude control demonstrate the effectiveness of the proposed method.
Improved Model Reference Adaptive Controller with RBF Neural Network Approximation for UAV
Lect. Notes Electrical Eng.
International Conference on Autonomous Unmanned Systems ; 2021 ; Changsha, China September 24, 2021 - September 26, 2021
Proceedings of 2021 International Conference on Autonomous Unmanned Systems (ICAUS 2021) ; Chapter : 176 ; 1788-1796
2022-03-18
9 pages
Article/Chapter (Book)
Electronic Resource
English
Improved Model Reference Adaptive Controller with RBF Neural Network Approximation for UAV
British Library Conference Proceedings | 2022
|Model reference adaptive controller uniform design for nonlinear neural network systems
British Library Online Contents | 2002
|Model Reference Adaptive Decoupling Controller Based on Neural Network Generalized Inverse for PMSM
British Library Online Contents | 2013
|