Title : 
Homography-based grasp tracking for planar objects
         
        
            Author : 
Carloni, Raffaella ; Recatala, G. ; Melchiorri, Claudio ; Sanz, Pedro J. ; Cervera, E.
         
        
            Author_Institution : 
Dept. of Electron., Comput. Sci. & Syst., Bologna Univ., Italy
         
        
        
        
            fDate : 
26 April-1 May 2004
         
        
        
            Abstract : 
The visual tracking of grasp points is an essential operation for the execution of an approaching movement of a robot arm to an object: the grasp points are used as features for the definition of the control law. This work describes a strategy for tracking grasps on planar objects based on the use of a homography. In particular, the homography is used for transferring (translating) a grasp from a view of an object to a second one, providing in this way a correspondence in the second view. The grasp tracking procedure combines the search of a new grasp with the translation and the evaluation of that grasp between object views. Results of the proposed grasp tracking strategy are shown in case of grasps computed for a two-finger and a three-finger gripper.
         
        
            Keywords : 
dexterous manipulators; grippers; robot vision; tracking; grasp tracking; homography; planar object; robot arm; three-finger gripper; two-finger gripper; visual tracking; Cameras; Computer science; Fingers; Grippers; Intelligent robots; Laboratories; Parallel robots; Robot vision systems; Robotics and automation; Tracking;
         
        
        
        
            Conference_Titel : 
Robotics and Automation, 2004. Proceedings. ICRA '04. 2004 IEEE International Conference on
         
        
        
            Print_ISBN : 
0-7803-8232-3
         
        
        
            DOI : 
10.1109/ROBOT.2004.1307246