ACRONYM: A Large-Scale Grasp Dataset Based on Simulation

TL;DR

ACRONYM is a comprehensive large-scale dataset of simulated robot grasps, designed to enhance grasp planning algorithms by providing extensive diverse data for training and evaluation.

Contribution

The paper introduces ACRONYM, a large-scale, physics-based grasp dataset with nearly 18 million grasps across thousands of objects, enabling improved learning-based grasp planning.

Findings

Training on ACRONYM improves grasp success rates.

Large dataset enhances the performance of state-of-the-art algorithms.

Dataset covers diverse objects and grasp scenarios.

Abstract

We introduce ACRONYM, a dataset for robot grasp planning based on physics simulation. The dataset contains 17.7M parallel-jaw grasps, spanning 8872 objects from 262 different categories, each labeled with the grasp result obtained from a physics simulator. We show the value of this large and diverse dataset by using it to train two state-of-the-art learning-based grasp planning algorithms. Grasp performance improves significantly when compared to the original smaller dataset. Data and tools can be accessed at https://sites.google.com/nvidia.com/graspdataset.