Date Added: Oct 2009
To grasp a novel object, the authors can index it into a database of known 3D models and use precomputed grasp data for those models to suggest a new grasp. They refer to this idea as data-driven grasping, and they have previously introduced the Columbia Grasp Database for this purpose. In this paper they demonstrate a data-driven grasp planner that requires only partial 3D data of an object in order to grasp it. To achieve this, they introduce a new shape descriptor for partial 3D range data, along with an alignment method that can rigidly register partial 3D models to models that are globally similar but not identical.