Neural Adaptive PID Control of a Quadrotor using EFK

SORIA, CARLOS M.; ROSALES, CLAUDIO D.; TOSETTI, SANTIAGO R.; ROSSOMANDO, FRANCISCO GUIDO

IEEE LATIN AMERICA TRANSACTIONS

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

Año: 2018 vol. 16 p. 2722 - 2730

1548-0992

In this paper, we present a novel trajectorytracking algorithm for a four-rotor air vehicle (quadrotor). ThePID controller is developed following an adaptive neuronaltechnique, and the discrete theory of Lyapunov verifies itsstability. Also, the neuronal identification of the UAV dynamicmodel is presented. Besides, an extended Kalman filter is used inorder to filter the signals from the aerial vehicle that arecontaminated by measurement noises, and that can affect thequality of the identification. Then, the output errors are repropagatedto adjust the PID gains to reduce the control errors.Finally, the experimental results are presented using a four-rotoraerial vehicle (quadrotor), by comparing the presented proposalwith a classical fixed-gain PID.