Adaptive neural network control based on neural observer for quadrotor unmanned aerial vehicle

This paper proposes an adaptive neural network control with neural state's observer for quadrotor. The adaptive approach is used to solve the dynamics uncertainty problem of the controller. To perform the control, a Single Hidden Layer Neural Network (SHLNN) is used. Based on the structure of S...

Full description

Saved in:
Bibliographic Details
Published in:Advanced robotics 2014-09, Vol.28 (17), p.1151-1164
Main Authors: Boudjedir, Hana, Bouhali, Omar, Rizoug, Nassim
Format: Article
Language:English
Subjects:
adaptive control
Engineering Sciences
neuronal control and observer
noise rejection
quadrotor
sliding mode observers
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper proposes an adaptive neural network control with neural state's observer for quadrotor. The adaptive approach is used to solve the dynamics uncertainty problem of the controller. To perform the control, a Single Hidden Layer Neural Network (SHLNN) is used. Based on the structure of Sliding Mode Observer (SMO), a new neural observer is proposed to estimate the states. The aim of this work is to propose an observer insensitive to the measurement noise. The stability proof of global system is made by Lyapunov direct method. The adaptation laws of both artificial neural networks (ANNs) are derived from Lyapunov theory. The proposed controller is validated by simulation on the quadrotor under measurement noise conditions. A comparative study with SMO is made to highlight the performances of the proposed neural observer.
ISSN:0169-1864
1568-5535
DOI:10.1080/01691864.2014.913498