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

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.

[1]  E. Malis,et al.  2 1/2 D Visual Servoing , 1999 .

[2]  Bruno Siciliano,et al.  Robot Force Control , 2000 .

[3]  Peter I. Corke,et al.  A tutorial on visual servo control , 1996, IEEE Trans. Robotics Autom..

[4]  David E. Goldberg,et al.  Genetic Algorithms in Search Optimization and Machine Learning , 1988 .

[5]  William J. Wilson,et al.  Relative end-effector control using Cartesian position based visual servoing , 1996, IEEE Trans. Robotics Autom..

[6]  Claire Dune,et al.  One Click Focus with Eye-in-hand/Eye-to-hand Cooperation , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[7]  David W. Capson,et al.  Multiple camera model-based 3-D visual servo , 2000, IEEE Trans. Robotics Autom..

[8]  Wei Song,et al.  On-line Evolutionary Head Pose Measurement by Feedforward Stereo Model Matching , 2007, Proceedings 2007 IEEE International Conference on Robotics and Automation.

[9]  Gerd Hirzinger,et al.  Hierarchical Featureless Tracking for Position-Based 6-DoF Visual Servoing , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[10]  H. Suzuki,et al.  Visual servoing to catch fish using global/local GA search , 2005, IEEE/ASME Transactions on Mechatronics.

[11]  Mamoru Minami,et al.  On-line Stable Evolutionary Recognition Based on Unit Quaternion Representation by Motion-Feedforward Compensation , 2008 .

[12]  François Chaumette,et al.  Point-based and region-based image moments for visual servoing of planar objects , 2005, IEEE Transactions on Robotics.

[13]  Robert E. Mahony,et al.  Visual servoing of an under-actuated dynamic rigid-body system: an image-based approach , 2002, IEEE Trans. Robotics Autom..