GraspNet-1Billion: A Large-Scale Benchmark for General Object Grasping

By Haoshu Fang, Chenxi Wang, Minghao Gou, Cewu Lu. Computer Vision and Pattern Recognition, 2020

844 citations recorded by the source corpus.

Object grasping is critical for many applications, which is also a challenging computer vision problem. However, for cluttered scene, current researches suffer from the problems of insufficient training data and the lacking of evaluation benchmarks. In this work, we contribute a large-scale grasp pose detection dataset with a unified evaluation system. Our dataset contains 97,280 RGB-D image with over one billion grasp poses. Meanwhile, our evaluation system directly reports whether a grasping is successful by analytic computation, which is able to evaluate any kind of grasp poses without exhaustively labeling ground-truth. In addition, we propose an end-to-end grasp pose prediction network given point cloud inputs, where we learn approaching direction and operation parameters in a decoupled manner. A novel grasp affinity field is also designed to improve the grasping robustness. We conduct extensive experiments to show that our dataset and evaluation system can align well with real-world experiments and our proposed network achieves the state-of-the-art performance. Our dataset, source code and models are publicly available at www.graspnet.net.

Subfields: Computer Vision and Pattern Recognition, Control and Systems Engineering, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/f76c9834a249a97ebcaf225a216c6076032af99c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Control and Systems Engineering

In Human-Computer Interaction

Citations in the corpus

Contact-GraspNet: Efficient 6-DoF Grasp Generation in Cluttered Scenes (2021, methodology): “Convergence is significantly faster than on previous methods [12, 14, 11] which take up to one week on a single GPU for training.”
Aligning Cyber Space With Physical World: A Comprehensive Survey on Embodied AI (2024, neutral): “For example, CLIPORT [165] and Transporter Networks [223] utilized Pybullet simulator data for training and successfully transferred models to real-world applications.”
AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domains (2022, methodology): “Although our algorithm is also temporal continuous and can enable closed-loop grasping, it is fragile to the occlusion induced by the robot.”
Vision-based robotic grasping from object localization, object pose estimation to grasp estimation for parallel grippers: a review (2020, background): “[Fang et al., 2020] proposed a large-scale grasp pose detection dataset called GraspNet-1Billion, which contains 97,280 RGB-D image with over one billion grasp poses.”
Foundation models in robotics: Applications, challenges, and the future (2023, neutral): “Developing techniques that perform runtime monitoring and OOD detection with statistical guarantees on false positive/negative error rates in a data-efﬁcient manner remains an important research direction.”