Robotic Catching of Thrown Objects through a Monocular Vision System

Catching a thrown object through a robotic system requires several capabilities, like smart sensing, object tracking, motion prediction, online trajectory planning, and motion coordination. In the robotic literature, several papers deal with such a problem and the problem of motion trajectory estimation. Most approaches use a stereo vision system to solve the 3D catching problem or a single camera for the 2D case. Using only one camera can reduce the cost of the equipment. Moreover, the calibration procedure for one camera is more comfortable than in the stereo case. Fabio Ruggiero proposed several solutions to this problem, also considering rolling and bouncing balls.

Proposed solutions:

• V. Lippiello, F. RUGGIERO, B. Siciliano, 3D monocular robotic ball catching, in Robotics and Autonomous Systems, vol. 61, n. 7, pp. 1615-1625, 2013, DOI: 10.1016/j.robot.2013.06.008.
• P. Cigliano, V. Lippiello, F. RUGGIERO, B. Siciliano, Robotic ball catching with an eye- in-hand single-camera system, in IEEE Transactions on Control Systems Technology, vol. 23, n. 5, pp. 1657-1671, 2015, DOI: 10.1109/TCST.2014.2380175.
• V. Lippiello, F. RUGGIERO, 3D monocular robotic ball catching with an iterative trajectory estimation refinement, 2012 IEEE International Conference on Robotics and Automation, St. Paul, MN, pp. 3950-3955, 2012, DOI: 10.1109/ICRA.2012.6224994.
• V. Lippiello, F. RUGGIERO, Monocular eye-in-hand robotic ball catching with parabolic motion estimation, 10th International IFAC Symposium on Robot Control, Dubrovnik, HR, pp. 229-234, 2012, DOI: 10.3182/20120905-3-HR-2030.00015.