Thumbnail
Access Restriction
Open

Author Mishra, Teichmann ♦ Mishra, B.
Source CiteSeerX
Content type Text
File Format PDF
Language English
Subject Domain (in DDC) Computer science, information & general works ♦ Data processing & computer science
Subject Keyword Reactive Algorithm ♦ Grip Point ♦ Fingered Hand ♦ Constant Horizontal Cross Section ♦ Limited Information ♦ Off-line Geometric Algorithm ♦ Good Grasp ♦ Usual Approach ♦ Angle Sensor ♦ Grasping Point ♦ Object Boundary ♦ Teichmann Mt92 ♦ Robot Hand ♦ Unknown Convex Object ♦ Standard Parallel Jaw Gripper ♦ Accurate Model
Description We study the problem of grasping an unknown 2- 1 2 D object with constant horizontal cross section using three types of robot hands. We consider a three fingered hand, a two fingered hand and a standard parallel jaw gripper and equip these with distance and angle sensors that are located at the fingers or jaws. The sensors used are simple, provide only limited information, but allow us to reactively find a good grasp on an unknown convex object. When grasped the forces applied will be normal to the object boundary. Furthermore the object is not disturbed as the grasping points are being sought. 1 Introduction In the past, the usual approach to grasping has been to assume an accurate model of the object to be grasped and from such a model, an off-line geometric algorithm determines a set of grip points, where the fingers are then placed. (See Mishra et. al. [MSS87] and Mishra and Teichmann [MT92], Stam et. al. [SPF92]). Once the grip points have been determined, the geometry of the ob...
Educational Role Student ♦ Teacher
Age Range above 22 year
Educational Use Research
Education Level UG and PG ♦ Career/Technical Study
Learning Resource Type Article
Publisher Date 1994-01-01
Publisher Institution In IEEE/RSJ International Workshop on Intelligent Robots and Systems