Servoing Based on Image Motion

The general aim of visual servoing is to control the motion of a robot so that visual features acquired by a camera become superimposed with a desired visual pattern. Visual servoing based on geometrical features such as image point coordinates is now well established. 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 the 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 method, geometric features are retrieved by integration of motion, which allows the use of classical control laws. This method is applied to a 6 degree-of-freedom positioning task. The authors show that, in such a case, an affine model of 2-D motion is insufficient to ensure convergence and that a quadratic model is needed. In the second method, the principle is to try to obtain a desired 2-D motion field in the image sequence. In usual image-based visual servoing, variations of visual features are linearly linked to the camera velocity. In this case, the corresponding relation is more complex, and the authors describe how it is possible to use this relation. This approach is illustrated with two tasks: positioning a camera parallel to a plane and following trajectory. KEY WORDS—visual servoing, 2D image motion, positioning