Title :
Relative visual servoing
Author :
Jafari, Shahram ; Jarvis, Ray ; Sivahumaran, Thirukkumaran
Author_Institution :
Intelligent Robotics Res. Centre, Monash Univ., Clayton, Vic., Australia
Abstract :
In this paper, we present two methods of performing eye-to-hand visual servoing: relative visual servoing and interpolation. These methods need only a monocular eye-to-hand camera and primitive tactile sensors. The set-up is part of a humanoid robot under development, named COERSU. Experimental results from COERSU are provided to validate these methods. An evolved visual perception system based on genetic algorithms was used to obtain the best possible combination of segmentation parameters. The experimental results show, relative visual servoing represents a significant improvement over the other methods in terms of reliability.
Keywords :
humanoid robots; image motion analysis; interpolation; robot vision; COERSU; eye-to-hand visual servoing; genetic algorithms; humanoid robot; interpolation; monocular eye-to-hand camera; primitive tactile sensors; relative visual servoing; visual perception system; Cameras; Humanoid robots; Image edge detection; Intelligent robots; Object detection; Robot kinematics; Robot sensing systems; Robot vision systems; Tuners; Visual servoing;
Conference_Titel :
Robotics, Automation and Mechatronics, 2004 IEEE Conference on
Print_ISBN :
0-7803-8645-0
DOI :
10.1109/RAMECH.2004.1438034