| The general aim of visual servoing
is to control the motion of a robot in order that visual features acquired
by a camera become superimposed with a desired visual pattern. Visual servoing
based upon geometrical features such as image points coordinates is now
well set on. Nevertheless, this approach has the drawback that it usually
needs visual marks on the observed object to retrieve geometric features.
The idea developed in this paper is to use motion in the image as input
of the control scheme, since it can be estimated without any a priori knowledge
of the observed scene. Thus, more realistic scenes or objects can be considered.
Two different methods are presented. In the first one, geometric features
are retrieved by integration of motion,which allows to use classical control
laws. This method is applied to a 6 d.o.f. positioning task. We show that,
in such a case, an affine model of 2D motion is insufficient to ensure convergence
and that a quadratic one is needed. In the second method, the principle
is to try to obtain a desired 2D motion field in the image sequence. In
usual image-based visual servoing, variations of visual features are linearly
linked to the camera velocity. In our case, the corresponding relation is
more complex and we describe how it is possible to use this relation. This
approach is illustrated with two tasks: positioning a camera parallel to
a plane, and trajectory following. |
