Using vision-based control techniques for grasping objects

We present additions to the Controlled Active Vision framework that focus upon the autonomous grasping of a moving object in the manipulator's workspace. Our work extends the capabilities of an eye-in-hand robotic system beyond those as a 'pointer' or a 'camera orienter' to provide the flexibility required to robustly interact with the environment in the presence of uncertainty. The proposed work is experimentally verified using the Minnesota Robotic Visual Tracker (MRVT) to automatically select object features, to derive estimates of unknown environmental parameters, and to supply a control vector based upon these estimates to guide the manipulator in the grasping of a moving object. The system grasps objects in the manipulator's workspace without requiring the object to follow a specific trajectory and without requiring the object to maintain a specific orientation.