Web-Books
in the Austria-Forum
Austria-Forum
Web-Books
International
Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
Page - 169 -
  • User
  • Version
    • full version
    • text only version
  • Language
    • Deutsch - German
    • English

Page - 169 - in Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“

Image of the Page - 169 -

Image of the Page - 169 - in Proceedings - OAGM & ARW Joint Workshop 2016 on

Text of the Page - 169 -

Localization  of  an  Automated  Guided  Vehicle  (AGV)  by Stereo  Based  Visual  Odometry  and  Artificial  Landmark Detection Daniel  Klingersberger  and  Gerald  Zauner FH  OÖ  Forschungs  &  Entwicklungs  GmbH,  Stelzhamerstr.  23,  4600  Wels  gerald.zauner@fh­ wels.at Abstract Localization  in  a  known  environment  is  an  essential  topic  in  the  field  of  robotics  –  consequently  a variety  of  methods  (e.g.  Visual  Odometry  or  SLAM)  are  scientifically  well  established.  Compared to  experimental  robotics,  the  determination  of  position  based  on  Machine  Vision  approaches  is  not yet  fully  implemented  in  the  domain  of  Automated  Guided  Vehicles  (AGV).  Thus,  the  aim  of  this master’s  thesis  is  to  design,  realize  and  test  a  localization  system  exclusively  based  on  Machine Vision  for  the  use  in  AGVs.  The  x­   and  y­ axis  positioning  as  well  as  the  determination  of orientation  of  the  vehicle  in  all  three  axes  is  carried  out  by  a  stereo  camera  based  Visual  Odometry approach  and  a  supporting  detection  of  artificial  landmarks  placed  on  the  ceiling.  Both  methods complement  each  other  perfectly:  while  Visual  Odometry  bridges  distances  without  landmarks, drift  caused  by  Visual  Odometry  is  corrected  by  artificial  landmarks.    Test  series  have  shown  that the  localization  error  falls  below  ±20mm  if  the  distance  between  camera  and  landmark  does  not exceed  4500mm.  Also  the  inclination  of  the  vehicle  is  equalized.  This  localization  system  has various  advantages  compared  to  well  established  methods:  designing  and  installation  efforts  can be  reduced,  while  the  flexibility  for  route  changes  can  be  increased  compared  to  traditional magnetic  guidance  systems.  The  interference  immunity  is  higher  compared  to  contour  matching methods  due  to  the  use  of  absolute  reference  points  placed  on  the  ceiling.  The  proposed  system  is not  suitable  for  use  in  halls  because  the  distance  between  camera  and  ceiling­ landmarks  should  not exceed  4500mm.  Nevertheless,   this  localization  system  is  an  interesting  alternative  to  well established  methods  primarily  for  the  use  in  the  public  sector,  e.g.  hospitals  or  libraries. 169
back to the  book Proceedings - OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“"
Proceedings OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
Title
Proceedings
Subtitle
OAGM & ARW Joint Workshop 2016 on "Computer Vision and Robotics“
Authors
Peter M. Roth
Kurt Niel
Publisher
Verlag der Technischen Universität Graz
Location
Wels
Date
2017
Language
English
License
CC BY 4.0
ISBN
978-3-85125-527-0
Size
21.0 x 29.7 cm
Pages
248
Keywords
Tagungsband
Categories
International
Tagungsbände

Table of contents

  1. Learning / Recognition 24
  2. Signal & Image Processing / Filters 43
  3. Geometry / Sensor Fusion 45
  4. Tracking / Detection 85
  5. Vision for Robotics I 95
  6. Vision for Robotics II 127
  7. Poster OAGM & ARW 167
  8. Task Planning 191
  9. Robotic Arm 207
Web-Books
Library
Privacy
Imprint
Austria-Forum
Austria-Forum
Web-Books
Proceedings