AUTHOR=Park Daewon , Le Tien-Loc , Quynh Nguyen Vu , Long Ngo Kim , Hong Sung Kyung 

TITLE=Online Tuning of PID Controller Using a Multilayer Fuzzy Neural Network Design for Quadcopter Attitude Tracking Control

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 14 - 2020

YEAR=2021

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2020.619350

DOI=10.3389/fnbot.2020.619350

ISSN=1662-5218

ABSTRACT=This study presents an online-tuning proportional-integral-derivative (PID) controller using multilayer fuzzy neural network design for the quadcopter attitude control. The PID controller is a simple but effective control method. However, finding the suitable gain of a model-based controller is relatively complicated and time-consuming because it depends on the dynamic modeling of the plant and external disturbances. Therefore, the development of a method for online tuning the quadcopter PID parameter will be a way to save time and effort, as well as obtaining better control performance. In our controller design, the multilayer structure is provided to improve the learning ability and flexibility of the fuzzy neural network. The adaptation laws for online updating network parameters are derived by using the gradient descent method. The Lyapunov analysis is given to guarantee system stability. Finally, the simulation results on control of the quadcopter attitude are performed through the Gazebo robotics simulator and robot operating system (ROS).