Coordination of an Uncalibrated 3-D Visuo-Motor System Based on Multiple Self-Organizing Maps

This paper presents a method to coordinate an uncalibrated visuo-motor system in a 3D space. In order to handle spaces occluded by obstacles, a 3-camera system and two related self-organizing maps (SOMs) are employed. The self-organizing maps are directly connected to the camera system and are trained to perform position control. Based on the visibility of targets given in the workspace, an appropriate map is adopted. The maps determine the joint angles of the manipulator which make the end effector reach the targets precisely, and make the manipulator take obstacle-free poses. The proposed learning method ensures that the manipulator moves smoothly and consistently in whole workspace even though we use two maps to control it. In our visuo-motor system, neither any priori knowledge about the manipulator nor the camera parameters is required. In addition, the system is robust to change in its geometry. Simulation results are presented to demonstrate the effectiveness of the proposed method and the robustness of the system.

[1]  Donald Fraser,et al.  M2dSOMAP: clustering and classification of remotely sensed imagery by combining multiple Kohonen self-organizing maps and associative memory , 1993, Proceedings of 1993 International Conference on Neural Networks (IJCNN-93-Nagoya, Japan).

[2]  Werner von Seelen,et al.  Self-organizing maps for visual feature representation based on natural binocular stimuli , 2000, Biological Cybernetics.

[3]  Gabriele M. T. D'Eleuterio,et al.  The "feature CMAC": a neural-network-based vision system for robotic control , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[4]  L. Behera,et al.  A hybrid neural control scheme for visual-motor coordination , 1999 .

[5]  Helge J. Ritter,et al.  Three-dimensional neural net for learning visuomotor coordination of a robot arm , 1990, IEEE Trans. Neural Networks.

[6]  Klaus Schulten,et al.  Motion planning of a pneumatic robot using a neural network , 1997 .

[7]  W. Thomas Miller,et al.  Real-time application of neural networks for sensor-based control of robots with vision , 1989, IEEE Trans. Syst. Man Cybern..

[8]  Patrice Wira,et al.  Multiple self-organizing maps to facilitate the learning of visuo-motor correlations , 1999, IEEE SMC'99 Conference Proceedings. 1999 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.99CH37028).

[9]  Klaus Schulten,et al.  Implementation of self-organizing neural networks for visuo-motor control of an industrial robot , 1993, IEEE Trans. Neural Networks.

[10]  Jean-Luc Buessler,et al.  Visually guided movements: learning with modular neural maps in robotics , 1998, Neural Networks.