Leveraging big data for grasp planning
- 1 May 2015
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4304-4311
- https://doi.org/10.1109/icra.2015.7139793
Abstract
We propose a new large-scale database containing grasps that are applied to a large set of objects from numerous categories. These grasps are generated in simulation and are annotated with different grasp stability metrics. We use a descriptive and efficient representation of the local object shape at which each grasp is applied. Given this data, we present a two-fold analysis: (i) We use crowdsourcing to analyze the correlation of the metrics with grasp success as predicted by humans. The results show that the metric based on physics simulation is a more consistent predictor for grasp success than the standard υ-metric. The results also support the hypothesis that human labels are not required for good ground truth grasp data. Instead the physics-metric can be used to generate datasets in simulation that may then be used to bootstrap learning in the real world. (ii) We apply a deep learning method and show that it can better leverage the large-scale database for prediction of grasp success compared to logistic regression. Furthermore, the results suggest that labels based on the physics-metric are less noisy than those from the υ-metric and therefore lead to a better classification performance.Keywords
This publication has 23 references indexed in Scilit:
- ST-HMP: Unsupervised Spatio-Temporal feature learning for tactile dataPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Robot arm pose estimation through pixel-wise part classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Classical grasp quality evaluation: New algorithms and theoryPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- An autonomous manipulation system based on force control and optimizationAutonomous Robots, 2013
- 3DNet: Large-scale object class recognition from CAD modelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2012
- Multivariate discretization for Bayesian Network structure learning in robot graspingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Learning Deep Architectures for AIFoundations and Trends® in Machine Learning, 2008
- Robotic Grasping of Novel Objects using VisionThe International Journal of Robotics Research, 2008
- USING EXPERIENCE FOR ASSESSING GRASP RELIABILITYInternational Journal of Humanoid Robotics, 2004
- Planning optimal graspsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1992