Introduction

Visual servoing techniques use the information provided by one or several cameras in order to control the motions of a robotic system. By controlling between one and all the degrees of freedom of a system, we can carry out a great number of positioning tasks, or mobile target tracking. Whatever the sensor configuration, which can vary from one on-board camera to several free-standing cameras, the aim is to select the best set of measurements allowing to control the desired degrees of freedom, and to elaborate a control law so that these measurements reach a desired value.

Though the first systems date back to the late 1970s and early 1980s, it is not until the mid 1990s that there is a sharp increase in publications and working systems, due to the availability of fast and affordable vision processing systems. The issue has raised much attention from the main journals in vision and robotics, with the publication of special issues: 1996 IEEE Tr. on R&A 12(5) 1996, IEEE R&A Magazine 5 (4), 1998, IJCV 37 (1), 2000), IJRR 22(10-11) 2003, R&A (CFP 2004). Also Workshops, tutorials, invited sessions, have been organized in the framework of the most important robotics conferences throughout the world: ICRA, IROS, ICAR. The principal objective of this course is to provide a comprehensive overview of the key topics and state of the art in visual servoing techniques to last year engineering, master and PhD students. The course includes fundamental knowledge of image processing, robot control and visual feedback control. Also the last advanced issues in visual servoing systems will be presented.

The materials and practical exercises have been prepared and supervised by top-level researchers in this topic.