Visual Behaviors for Docking

This paper describes visual-based behaviors for docking operations in mobile robotics. Two diierent situations are presented : in the ego-docking, each robot is equipped with a camera, and the motion is controlled when docking to a surface , whereas in the eco-docking, the camera and all the necessary computational resources are placed in a single external docking station, which may serve several robots. In both situations, the goal consists in controlling both the orientation, aligning the camera optical axis with the surface normal, and the approaching speed (slowing down during the maneuver). These goals are accomplished without any eeort to perform 3D reconstruction of the environment or any need to calibrate the setup, in contrast with traditional approaches. Instead, we use image measurements directly to close the control loop of the mobile robot. In the approach we propose, the robot motion is directly driven by the rst order time-space image derivatives, which can be estimated robustly and fast. The docking system is operating in real time and the performance is robust both in the ego-docking and eco-docking paradigms. Experiments are described. The authors wish to thank the anonymous reviewers for their helpful comments and suggestions, that helped to improve the quality and the presentation of the paper. A fellowship from a bilateral collaboration between Consiglio Nazionale delle Ricerche (CNR) and Junta Nacional de Investigaa c~ ao Cient ca e Tecnoll ogica (JNICT) is gratefully acknowledged by Jos e Santos-Victor.