![](bg1.png)
AVOIDING VISUAL SERVOING SINGULARITIES USING A
COOPERATIVE CONTROL ARCHITECTURE
N. Garc
´
ıa, C. P
´
erez, L. Pay
´
a, R.
˜
Neco, J.M. Sabater, J. M. Azor
´
ın
Dept. Ingenier
´
ıa de Sistemas Industriales. Universidad Miguel Hern
´
andez.
Avd. de la Universidad s/n. Edif. Torreblanca. 03202 Elche (Spain)
Keywords:
Visual servoing, control, sensors, computer vision, robotics.
Abstract:
To avoid the singularities of an image-based visual control of an industrial robot (Mitsubishi PA-10), a simple
and efficient control law which combines the information of two cameras in a cooperative way has been devel-
oped and tested. One of this cameras is rigidly mounted on the robot end-effector (eye-in-hand configuration)
and the other one observes the robot within its workspace (eye-to-hand configuration). The system architecture
proposed allows us to control the 6 dof of an industrial robot when typical problems of image-based visual
control techniques are produced.
1 INTRODUCTION
Nowadays, the great majority of robot population op-
erates in factories where the work environment is
structured and previously well-known. The applica-
tion of a robot to carry out a certain task depends, in a
high percentage, on the previously knowledge about
the work environment and object placement. This
limitation is due to inherent lack of sensory capability
in contemporary commercial industrial robots. It has
been long recognized that sensor integration is funda-
mental to increase the versatility and application do-
main of robots. One of these sensor systems is Com-
puter Vision.
Computer Vision is a useful robotic sensor since it
mimics the human sense of vision and allows for non
contact measurement of the work environment. In-
dustrial robot controllers with fully integrated vision
systems are now available from a large number of sup-
pliers. In these systems, visual sensing and manipu-
lation are typically integrated in an open-loop mode,
looking then moving. The precision of the resulting
operation depends directly on the accuracy of the vi-
sual sensor and the robot end-effector.
An alternative solution for the position and motion
control of an industrial manipulator evolved in un-
structured environments is to use the visual informa-
tion in a feedback loop. This robot control strategy
is called visual servo control or visual servoing. Vi-
sual servoing systems have recently received a grow-
ing interest, as the computational power of commer-
cially available computers became compatible with
real time visual feedback(B. Espiau, 1992)(Hutchin-
son et al., 1996).
During the last years, position or image based vi-
sual servoing systems, systems with different archi-
tectures (a camera or multiples cameras), stability
problems, calibration limitation, etc, have been stud-
ied. In particular, many image based visual ser-
voing systems have been developed basically with
two types of architecture: eye-in-hand configura-
tion(Garcia et al., 2002), when the camera is rigidly
mounted on the robot end-effector or eye-to-hand
configuration(R. Horaud and Espiau, 1998) when the
camera observes the robot within its work space.
The first approximation of using two cameras
in eye-in-hand/eye-to-hand configurations were pre-
sented in the work of (Marchand and Hager, 1998).
The system proposed used two task controlled by a
camera mounted on the robot and a global camera to
avoid obstacles during a 3D task. Then, in the paper
reported by (Flandin et al., 2000) a system for inte-
gration a fixed camera and a camera mounted on the
robot end-effector is presented. One task is used to
control the translation dof of the robot with the fixed
camera while other task is used to control the in eye-
in-hand camera orientation. In this paper, an image
based visual servo control of a 6 dof industrial robot
manipulator with a cooperative eye-in-hand/eye-to-
hand configuration is presented. In Section 2, the the-
162
García N., Pérez C., Payá L., Ñeco R., Sabater J. and Azorín J. (2004).
AVOIDING VISUAL SERVOING SINGULARITIES USING A COOPERATIVE CONTROL ARCHITECTURE.
In Proceedings of the First International Conference on Informatics in Control, Automation and Robotics, pages 162-168
DOI: 10.5220/0001134201620168
Copyright
c
SciTePress