Probabilistic Models of Object Geometry with Application to Grasping

• Main Authors: Rus, Daniela L. (Contributor), Glover, Jared (Contributor), Roy, Nicholas (Contributor)
• Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory (Contributor), Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science (Contributor)
• Format: Article
• Language: English
• Published: Sage Publications, 2010-09-29T14:42:08Z.
• Subjects: Article
• Online Access: Get fulltext

Robot manipulators typically rely on complete knowledge of object geometry in order to plan motions and compute grasps. But when an object is not fully in view it can be difficult to form an accurate estimate of the object's shape and pose, particularly when the object deforms. In this paper we describe a generative model of object geometry based on Mardia and Dryden's "Probabilistic Procrustean Shape" which captures both non-rigid deformations and object variability in a class. We extend their shape model to the setting where point correspondences are unknown using Scott and Nowak's COPAP framework. We use this model to recognize objects in a cluttered image and to infer their complete 2-D boundaries with a novel algorithm called OSIRIS. We show examples of learned models from image data and demonstrate how the models can be used by a manipulation planner to grasp objects in cluttered visual scenes.
National Science Foundation (U.S.). Division of Information and Intelligent Systems (Grant No. 0546467)
United States. Air Force Office of Scientific Research (STTR Contract FA9550- 06-C-0088)
National Science Foundation (U.S.). Division of Computer and Network Systems (grant 0707601)
National Science Foundation (U.S.) ( grant 0426838)
National Science Foundation (U.S.) ( grant 0735953)