In this paper we address the issue of hybrid 2D/3D visual servoing. Contrary to popular approaches, we consider the position-based visual servo as the core of our scheme. 2D information is only added when necessary, that is when the observed object is about to leave from the field of view, even partially. The injection of 2D information is tuned by only one parameter, that simply defines the area where a point is considered to be near to the image border. Simulations allow the comparison of the proposed scheme with both positionbased and hybrid schemes, showing nice properties. Finally, experiments are performed on a real object that is tracked by a pose estimation algorithm. Results validate the approach by showing the object stays entirely in the image field of view.

Abstract-We present and validate a framework for visual navigation with obstacle avoidance. The approach was originally designed in [1], but major improvements and real outdoor experiments are added here. Visual navigation consists of following a path, represented as an ordered set of key images, that have been acquired in a preliminary teaching phase. While following such path, the robot is able to avoid new obstacles which were not present during teaching, and which are sensed by a range scanner. We guarantee that collision avoidance and navigation are achieved simultaneously by actuating the camera pan angle, in the presence of obstacles, to maintain scene visibility as the robot circumnavigates the obstacle. The circumnavigation verse and the collision risk are estimated using a potential vector field derived from an occupancy grid. The framework can also deal with unavoidable obstacles, which make the robot decelerate and eventually stop.