• DocumentCode
    2386125
  • Title

    Hand & eye-vergence dual visual servoing to enhance observability and stability

  • Author

    Song, Wei ; Minami, Mamoru

  • Author_Institution
    Dept. of Human & Artificial Intell. Syst., Univ. of Fukui, Fukui, Japan
  • fYear
    2009
  • fDate
    12-17 May 2009
  • Firstpage
    714
  • Lastpage
    721
  • Abstract
    In this paper, we propose a new two-way visual servoing method, named as hand & eye-vergence visual servoing. This idea stems from animal´s evolution history, predator have evolved their eye positions to be at the front face and their eyes turn to gaze at the target prey to be suited to triangulation, enhancing the ability to measure precisely the distance to the prey for catching it. This animal´s visual tracking includes motion control by visual servoing and triangular eye vergence. Our proposed method includes two loops: an outer loop for conventional visual servoing that direct a manipulator toward a target object and an inner loop for active motion of binocular camera for accurate and broad observation of the target object. The effectiveness of the hand & eye-vergence visual servoing is evaluated through simulations incorporated with actual dynamics of 7-DoF robot on the view points of how the new idea improved the stability in visual servoing dynamics and the accuracy of hand pose.
  • Keywords
    manipulators; motion control; stability; visual servoing; 7-DoF robot; animal visual tracking; binocular camera; eye-vergence dual visual servoing; hand dual visual servoing; hand pose; motion control; Eyes; History; Manipulator dynamics; Motion control; Observability; Position measurement; Robot vision systems; Stability; Target tracking; Visual servoing;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Robotics and Automation, 2009. ICRA '09. IEEE International Conference on
  • Conference_Location
    Kobe
  • ISSN
    1050-4729
  • Print_ISBN
    978-1-4244-2788-8
  • Electronic_ISBN
    1050-4729
  • Type

    conf

  • DOI
    10.1109/ROBOT.2009.5152695
  • Filename
    5152695