Data-driven grasping with partial sensor data
Authors:
- 1 October 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1278-1283
Abstract
To grasp a novel object, we can index it into a database of known 3D models and use precomputed grasp data for those models to suggest a new grasp. We refer to this idea as data-driven grasping, and we have previously introduced the Columbia Grasp Database for this purpose. In this paper we demonstrate a data-driven grasp planner that requires only partial 3D data of an object in order to grasp it. To achieve this, we 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. Our method uses SIFT features of depth images, and encapsulates ¿nearby¿ views of an object in a compact shape descriptor.Keywords
This publication has 22 references indexed in Scilit:
- The Columbia grasp database2009
- Data-Driven Grasp Synthesis Using Shape Matching and Task-Based PruningIEEE Transactions on Visualization and Computer Graphics, 2007
- Grasp Planning via Decomposition TreesProceedings 2001 ICRA. IEEE International Conference on Robotics and Automation (cat. No.01ch37164), 2007
- Fully Automatic Registration of 3D Point Clouds2006
- From robotic hands to human hands: a visualization and simulation engine for grasping researchIndustrial Robot: the international journal of robotics research and application, 2005
- The princeton shape benchmark2004
- Synthesizing animations of human manipulation tasksACM Transactions on Graphics, 2004
- Fully automatic registration of multiple 3D data setsImage and Vision Computing, 2003
- Object recognition from local scale-invariant features1999
- On Information and SufficiencyThe Annals of Mathematical Statistics, 1951