GraspFactory: A Large Object-Centric Grasping Dataset

Srinidhi Kalgundi Srinivas, Yash Shukla, Adam Arnold, Sachin Chitta

Keywords: CAD, Grasp dataset, Learning, Geometric Diversity

TL;DR: We present GraspFactory, a large-scale dataset of 6-DoF parallel-jaw grasps with gripper widths, totaling over 109M grasps. It covers 33,710 objects for the Robotiq 2F85 gripper and 14,690 for the Franka Panda, ensuring broad geometric diversity.

Abstract: Robotic grasping is a crucial task in industrial automation, where robots are increasingly expected to handle a wide range of objects. However, a significant challenge arises when robot grasping models trained on limited datasets encounter novel objects. In real-world environments such as warehouses or manufacturing plants, the diversity of objects can be vast, and grasping models need to generalize to this diversity. Training large, generalizable robot-grasping models requires geometrically diverse datasets. In this paper, we introduce GraspFactory, a dataset containing over 109 million 6-DoF grasps collectively for the Franka Panda (with 14,690 objects) and Robotiq 2F85 grippers (with 33,710 objects). GraspFactory is designed for training data-intensive models, and we demonstrate the generalization capabilities of one such model trained on a subset of GraspFactory in both simulated and real-world settings. The dataset and tools are made available for download at https://graspfactory.github.io/.

Submission Number: 19