SuctionNet-1Billion: A Large-Scale Benchmark for Suction Grasping

TL;DR

This paper introduces SuctionNet-1Billion, a large-scale dataset and benchmark for suction grasping, along with a new physical model and a method for predicting suction poses from RGB-D images, improving evaluation and performance in robotic grasping.

Contribution

It provides a large-scale annotated dataset, a physical evaluation model, and a standardized online evaluation system for suction grasping, advancing research in this area.

Findings

Annotations align well with real-world results

Proposed method outperforms previous approaches

Benchmark facilitates fair comparison of algorithms

Abstract

Suction is an important solution for the longstanding robotic grasping problem. Compared with other kinds of grasping, suction grasping is easier to represent and often more reliable in practice. Though preferred in many scenarios, it is not fully investigated and lacks sufficient training data and evaluation benchmarks. To address that, firstly, we propose a new physical model to analytically evaluate seal formation and wrench resistance of a suction grasping, which are two key aspects of grasp success. Secondly, a two-step methodology is adopted to generate annotations on a large-scale dataset collected in real-world cluttered scenarios. Thirdly, a standard online evaluation system is proposed to evaluate suction poses in continuous operation space, which can benchmark different algorithms fairly without the need of exhaustive labeling. Real-robot experiments are conducted to show that our annotations align well with real world. Meanwhile, we propose a method to predict numerous suction poses from an RGB-D image of a cluttered scene and demonstrate our superiority against several previous methods. Result analyses are further provided to help readers better understand the challenges in this area. Data and source code are publicly available at www.graspnet.net.