• DocumentCode
    2342181
  • Title

    Robotic Tracking and Marking of Surface Shape Defects on Moving Automotive Panels

  • Author

    Borsu, Valentin ; Payeur, Pierre

  • Author_Institution
    Sch. of Inf. Technol. & Eng., Univ. of Ottawa, Ottawa, ON, Canada
  • fYear
    2011
  • fDate
    25-27 May 2011
  • Firstpage
    56
  • Lastpage
    63
  • Abstract
    This paper examines the complex problem of robotic interaction with moving panels exhibiting few distinctive visual features, in the context of marking surface deformation defects for quality control in the automotive industry. In order to integrate a defects detection station and a robotic tracking and marking system within a unified framework, an original inter-calibration technique is developed, which allows for the distribution of these systems in two different stations along the assembly line. A robotic prototype for performing the marking operation on a moving panel, using a spraying gun, is built and its operation validated under realistic industrial scenarios. The marking accuracy that is achieved demonstrates the suitability of the proposed robotic solution to perform fully automated region marking of deformations over large surfaces and for substantial volumes of production, while relying only on passive stereoscopy.
  • Keywords
    automobile industry; calibration; quality control; robots; stereo image processing; visual servoing; automotive industry; distinctive visual features; intercalibration technique; moving automotive panels; passive stereoscopy; quality control; robotic tracking; spraying gun; surface shape defects; Accuracy; Automotive engineering; Robot kinematics; Robot sensing systems; Three dimensional displays; calibration; motion prediction; stereoscopic vision; visual servoing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer and Robot Vision (CRV), 2011 Canadian Conference on
  • Conference_Location
    St. Johns, NL
  • Print_ISBN
    978-1-61284-430-5
  • Electronic_ISBN
    978-0-7695-4362-8
  • Type

    conf

  • DOI
    10.1109/CRV.2011.15
  • Filename
    5957542