DocumentCode :
1533567
Title :
A hybrid neural control scheme for visual-motor coordination
Author :
Behera, Laxmidhar ; Kirubanandan, Nandagopal
Author_Institution :
Birla Inst. of Technol., Pilani, India
Volume :
19
Issue :
4
fYear :
1999
fDate :
8/1/1999 12:00:00 AM
Firstpage :
34
Lastpage :
41
Abstract :
Visual-motor coordination, also referred to as hand-eye coordination, in the context of robotics is the process of using visual information to control a robot manipulator to reach a target point in its workspace. The task requires learning the mapping that exists between camera output and desired end effector location. Biological organisms have demonstrated their superior adaptive capabilities in motion control over present-day robotic systems. Inspired by this fact, various neural network models based on biological systems have been developed for robot control tasks. The drawback of many neural schemes to tackle visual-motor control problems is that of a long training period. We suggest an approach using Kohonen´s self-organizing scheme to learn this hand-eye coordination problem in reduced time with high accuracy. Our approach has also been compared with a conventional calibration-based algorithm. These schemes have been implemented in real time on a CRS PLUS robot arm. Experimental results show that the proposed neural scheme is on an average 10 times faster in training compared to similar neural approaches existing in the literature. This speed is also comparable to the conventional algorithm and is more accurate
Keywords :
calibration; learning (artificial intelligence); manipulator kinematics; motion control; neurocontrollers; robot vision; self-organising feature maps; CRS PLUS robot arm; Kohonen´s self-organizing scheme; calibration-based algorithm; camera output; desired end effector location; hand-eye coordination; hybrid neural control scheme; mapping; training; visual-motor coordination; Adaptive control; Biological systems; Cameras; End effectors; Manipulators; Motion control; Programmable control; Robot control; Robot kinematics; Robot vision systems;
fLanguage :
English
Journal_Title :
Control Systems, IEEE
Publisher :
ieee
ISSN :
1066-033X
Type :
jour
DOI :
10.1109/37.777787
Filename :
777787
Link To Document :
بازگشت