In this paper, we present a visual servoing approach to the problem of
object grasping and more generally, to the problem of aligning an end
-effector with an object. First we extend the method proposed in [1] t
o the case of a camera which is not mounted onto the robot being contr
olled and we stress the importance of the real-time estimation of the
image Jacobia., Second, me show how to represent a grasp or more gener
ally, an alignment between two solids in three-dimensional (3-D) proje
ctive space using an uncalibrated stereo rig. Such a 3-D projective re
presentation is view-invariant in the sense that it can be easily mapp
ed into an image set-point without any knowledge about the camera para
meters. Third, we perform an analysis of the performances of the visua
l servoing algorithm and of the grasping precision that can be expecte
d from this type of approach.