GRASPING OF STATIC AND MOVING-OBJECTS USING A VISION-BASED CONTROL APPROACH

Robotic systems require the use of sensing to enable flexible operatio n in uncalibrated or partially calibrated environments. Recent work co mbining robotics with vision has emphasized an active vision paradigm where the system changes the pose of the camera to improve environment al knowledge or to establish and preserve a desired relationship betwe en the robot and objects in the environment. Much of this work has con centrated upon the active observation of objects by the robotic agent. We address the problem of robotic visual grasping (eye-in-hand config uration) of static and moving rigid targets. The objective is to move the image projections of certain feature points of the target to effec t a vision-guided reach and grasp. An adaptive control algorithm for r epositioning a camera compensates for the servoing errors and the comp utational delays that are introduced by the vision algorithms. Stabili ty issues along with issues concerning the minimum number of required feature points are discussed. Experimental results are presented to ve rify the validity and the efficacy of the proposed control algorithms. We then address an adaptation to the control paradigm that focuses up on the autonomous grasping of a static or moving object in the manipul ator's workspace. Our work extends the capabilities of an eye-in-hand system beyond those as a 'pointer' or a 'camera orienter' to provide t he flexibility required to robustly interact with the environment in t he presence of uncertainty. The proposed work is experimentally verifi ed using the Minnesota Robotic Visual Tracker (MRVT) [7] to automatica lly select object features, to derive estimates of unknown environment al parameters, and to supply a control vector based upon these estimat es to guide the manipulator in the grasping of a static or moving obje ct.