An RC helicopter autonomous control system with single web camera

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

A simple vision based autonomous flight control system is developed in this paper to study the feedback control capability of a system using only one web camera as the sensor. The position and attitude estimation is achieved based on the homography. Markers are attached to a RC helicopter to simplify the image processing. The position of markers relative to the helicopter is used as a prior knowledge in the position and attitude estimation. The system uses a PD controller to autonomously control the flight of the helicopter. Hovering experiments have been carried out to test the visual feedback control system. The helicopter hovered at a point 0.6m above the origin of the world coordinate for about 20 seconds during the test with single web camera. The system is capable to autonomous hovering flight, however has problems like drift. Further study and improvement is needed in the future works.

Original languageEnglish
Title of host publication2012 Proceedings of SICE Annual Conference, SICE 2012
PublisherSociety of Instrument and Control Engineers (SICE)
Pages2127-2132
Number of pages6
ISBN (Print)9781467322591
Publication statusPublished - 2012 Jan 1
Event2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012 - Akita, Japan
Duration: 2012 Aug 202012 Aug 23

Publication series

NameProceedings of the SICE Annual Conference

Other

Other2012 51st Annual Conference on of the Society of Instrument and Control Engineers of Japan, SICE 2012
CountryJapan
CityAkita
Period12/8/2012/8/23

Keywords

  • Autonomous Control
  • Micro UAV
  • Visual Servo
  • Web Camera

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Computer Science Applications
  • Electrical and Electronic Engineering

Fingerprint Dive into the research topics of 'An RC helicopter autonomous control system with single web camera'. Together they form a unique fingerprint.

Cite this