Monocular Eye-in-Hand Robotic Ball Catching with Parabolic Motion Estimation

A monocular robotic ball catching system is presented in this paper. A visual servoing control is used in order to keep a thrown ball in the field of view of an eye-in-hand camera and generate a robot motion toward the ball interception point. Simultaneously, the 3D ball trajectory is estimated with a least-squares method, which employs only information provided by the available camera. Experiments demonstrate the feasibility of the proposed approach.