Leveraging big data for grasp planning

TLDR

The study introduces a large‑scale grasp database and aims to evaluate grasp stability metrics through crowdsourced human judgments and to demonstrate that deep learning can better predict grasp success than logistic regression. Grasps are generated in simulation, annotated with multiple stability metrics, represented by a compact local shape descriptor, and used to train a deep learning model for success prediction. Physics‑simulation‑based metrics outperform the υ‑metric as predictors of grasp success, human labels are unnecessary, and a deep learning model trained on these metrics achieves higher prediction accuracy than logistic regression.

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.