Skip to main navigation Skip to search Skip to main content

Supervisory control of a multirotor drone using on-line sequential extreme learning machine

  • Oualid Doukhi*
  • , Abdur Razzaq Fayjie
  • , Deok Jin Lee
  • *Corresponding author for this work
  • Kunsan National University

Research output: Contribution to conferenceConference paperpeer-review

Abstract

Quadrotors are underactuated nonlinear systems, which mean it needs online monitoring and controller tuning during flight period. Classical proportional integral derivative (PID) control and artificial neural network control (NNC) shows good results in many applications. Therefore in this paper, we propose a neural network supervisory control technique for the classical PID controller using fast online sequential learning method called on-line sequential extreme learning machine (OS-ELM). This technique seeks to online tune the control input to improve the flight capabilities automatically. The effectiveness of the proposed control algorithm comparing it with the conventional neural network based PID controller is demonstrated through realistic simulation using ROS-Gazebo framework.

Original languageEnglish
Title of host publicationIntelligent Systems and Applications - Proceedings of the 2018 Intelligent Systems Conference IntelliSys Volume 1
EditorsKohei Arai, Supriya Kapoor, Rahul Bhatia
PublisherSpringer Verlag
Pages914-924
Number of pages11
ISBN (Print)9783030010539
DOIs
StatePublished - 2018
EventIntelligent Systems Conference, IntelliSys 2018 - London, United Kingdom
Duration: 2018.09.62018.09.7

Publication series

NameAdvances in Intelligent Systems and Computing
Volume868
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

ConferenceIntelligent Systems Conference, IntelliSys 2018
Country/TerritoryUnited Kingdom
CityLondon
Period18.09.618.09.7

Keywords

  • Disturbances
  • Neural network
  • On-line learning
  • Quadrotor

Fingerprint

Dive into the research topics of 'Supervisory control of a multirotor drone using on-line sequential extreme learning machine'. Together they form a unique fingerprint.

Cite this