Visually guided robotic tracking and grasping of a moving object

Visually guided tracking and grasping of a moving object by a robot manipulator is discussed in this paper. Position-based and image-based tracking schemes are proposed. It is shown that when the motion of the object is accurately estimated, both schemes are equivalent since they are the same control problem considered in two spaces. If the image of the gripper is also available, the image-based controller can be improved to cope with the system calibration error. The tracking and grasping performance is demonstrated from simulations.<>