Visual Control of robots with changes of visibility in image features

Abstract

Visual servoing concerns several fields of research including vision systems, robotics and automatic control. Visual servoing can be useful for a wide range of applications and it can be used to control many different dynamic systems (manipulator arms, mobile robots, autonomous underwater vehicles, aircraft, etc.). However, visual servoing systems are not complete efficiency due to the numerous problems that are still unresolved. In this paper a new general solution to visibility restriction associated to all visual servoing techniques based directly or un-directly on image features is presented. This solution allows the temporary disappearance of image features during the control task versus the solutions proposed until now which are based on keeping always the object in the field of view. Taking into account this concept, the theoretical bases of a continuous and stable visual servoing approach that allows the temporary presence of features in the image have been defined and developed. Using them, the camera invariant visual servoing approach has been reformulated to adapt it to the temporary disappearance of image features during the control task.