Robotic hand-eye coordination: from observation to manipulation

In this paper, we present a new hybrid method of performing eye-to-hand coordination and manipulation to produce a working robot named COERSU. The method is an optimized combination of two neuro-fuzzy approaches developed by the authors: direct fuzzy servoing and fuzzy correction. The fuzzy methods are tuned by an adaptive neuro-fuzzy inference system (ANFIS). On the whole, a genetic tuner and two neuro-fuzzy networks contribute to find the final optimum position of the robotic tooltip in order to grasp the target. Experimental results from COERSU in a table-top scenario to manipulate some soft objects (e.g. fruit/egg) also validate the method.

[1]  Shahram Jafari,et al.  A genetic off-line tuner for robotic humanoid visual perception , 2003, The 2003 Congress on Evolutionary Computation, 2003. CEC '03..

[2]  Patricia A. Nava,et al.  Neural network algorithms for tuning of fuzzy certainty factor expert systems , 2002, Proceedings of the 5th Biannual World Automation Congress.

[3]  Danica Kragic,et al.  Cue integration for visual servoing , 2001, IEEE Trans. Robotics Autom..

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

[5]  Bärbel Mertsching,et al.  The SENROB vision-system and its philosophy , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[6]  Minoru Asada,et al.  Trajectory generation for obstacle avoidance of uncalibrated stereo visual servoing without 3D reconstruction , 1995, Proceedings 1995 IEEE/RSJ International Conference on Intelligent Robots and Systems. Human Robot Interaction and Cooperative Robots.

[7]  Glen Castore,et al.  From solid model to robot vision , 1984, ICRA.

[8]  Huan Liu,et al.  Robot hand-eye coordination: shape description and grasping , 1988, Proceedings. 1988 IEEE International Conference on Robotics and Automation.

[9]  W. von Seelen,et al.  A flexible architecture for intelligent cruise control , 1999, Proceedings 199 IEEE/IEEJ/JSAI International Conference on Intelligent Transportation Systems (Cat. No.99TH8383).

[10]  Philippe Martinet,et al.  Is 3D useful in stereo visual control? , 2002, Proceedings 2002 IEEE International Conference on Robotics and Automation (Cat. No.02CH37292).

[11]  Minoru Asada,et al.  Versatile visual servoing without knowledge of true Jacobian , 1994, Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94).

[12]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[13]  Michael Negnevitsky,et al.  Artificial Intelligence: A Guide to Intelligent Systems , 2001 .

[14]  Michael Sorg,et al.  What can be learned from human reach-to-grasp movements for the design of robotic hand-eye systems? , 1999, Proceedings 1999 IEEE International Conference on Robotics and Automation (Cat. No.99CH36288C).

[15]  Robert J. Schilling,et al.  Fundamentals of robotics - analysis and control , 1990 .

[16]  Shiaw-Chian Wu,et al.  Adaptive fuzzy visual servoing in robot control , 1997, Proceedings of International Conference on Robotics and Automation.

[17]  Ezio Malis.  Visual servoing invariant to changes in camera-intrinsic parameters , 2004, IEEE Trans. Robotics Autom..

[18]  Mansur R. Kabuka,et al.  Robot vision tracking system , 1988 .

[19]  Li-Chen Fu,et al.  5D target trajectory detection via intelligent monocular visual tracking system in real-time with air-target orientation recognition , 1999, Proceedings of the 1999 American Control Conference (Cat. No. 99CH36251).

[20]  Tsutomu Kimoto,et al.  Manipulator control with image-based visual servo , 1991, Proceedings. 1991 IEEE International Conference on Robotics and Automation.