One-shot learning and generation of dexterous grasps for novel objects
- 18 September 2015
- journal article
- research article
- Published by SAGE Publications in The International Journal of Robotics Research
- Vol. 35 (8), 959-976
- https://doi.org/10.1177/0278364915594244
Abstract
This paper presents a method for one-shot learning of dexterous grasps and grasp generation for novel objects. A model of each grasp type is learned from a single kinesthetic demonstration and several types are taught. These models are used to select and generate grasps for unfamiliar objects. Both the learning and generation stages use an incomplete point cloud from a depth camera, so no prior model of an object shape is used. The learned model is a product of experts, in which experts are of two types. The first type is a contact model and is a density over the pose of a single hand link relative to the local object surface. The second type is the hand-configuration model and is a density over the whole-hand configuration. Grasp generation for an unfamiliar object optimizes the product of these two model types, generating thousands of grasp candidates in under 30 seconds. The method is robust to incomplete data at both training and testing stages. When several grasp types are considered the method selects the highest-likelihood grasp across all the types. In an experiment, the training set consisted of five different grasps and the test set of 45 previously unseen objects. The success rate of the first-choice grasp is 84.4% or 77.7% if seven views or a single view of the test object are taken, respectively.Keywords
This publication has 41 references indexed in Scilit:
- Synthesizing grasp configurations with specified contact regionsThe International Journal of Robotics Research, 2010
- A strategy for grasping unknown objects based on co-planarity and colour informationRobotics and Autonomous Systems, 2010
- Coping with the Grasping Uncertainties in Force-closure AnalysisThe International Journal of Robotics Research, 2005
- Closure and Quality Equivalence for Efficient Synthesis of Grasps from ExamplesThe International Journal of Robotics Research, 2004
- The Cortical Motor SystemNeuron, 2001
- Computing n-Finger Form-Closure Grasps on Polygonal ObjectsThe International Journal of Robotics Research, 2000
- Robot Grasp Synthesis Algorithms: A SurveyThe International Journal of Robotics Research, 1996
- On computing three-finger force-closure grasps of polygonal objectsIEEE Transactions on Robotics and Automation, 1995
- Optimization by Simulated AnnealingScience, 1983
- Dispersion on a SphereProceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 1953