EXPLOITING IMAGE MOTION FOR ACTIVE VISION IN A VISUAL SERVOING FRAMEWORK

The visual, servoing formalism provides a framework for achieving task s in an active closed-loop fashion based on visual information. We con sider a typical visual servoing approach that uses geometric informati on about image features for controlling the position and attitude of a camera and extend the applicability of this approach by using image m otion information. We present two different approaches to visual tasks that use motion information. The first uses the focus of expansion, w hich is related to the translational velocity, of the camera. The seco nd incorporates the parameters of the 2D affine motion model in contro l equations. Both of these approaches are illustrated by means of a ta sk of aligning the optical axis of the camera with the unknown directi on of translational motion of the system on which it is mounted. Resul ts of simulation experiments and real experiments on a six degrees of freedom (DOF) robot with a camera on its end effector are presented.