REGNet: REgion-based Grasp Network for End-to-end Grasp Detection in Point Clouds
This work addresses the problem of reliable robotic grasping in unstructured environments for robotics applications, showing strong performance improvements over existing methods.
The paper tackles robotic grasp detection from single-view point clouds by proposing REGNet, an end-to-end network with stages for scoring, region-based proposal, and refinement, achieving a 79.34% success rate and 96% completion rate in real-world clutter.
Reliable robotic grasping in unstructured environments is a crucial but challenging task. The main problem is to generate the optimal grasp of novel objects from partial noisy observations. This paper presents an end-to-end grasp detection network taking one single-view point cloud as input to tackle the problem. Our network includes three stages: Score Network (SN), Grasp Region Network (GRN), and Refine Network (RN). Specifically, SN regresses point grasp confidence and selects positive points with high confidence. Then GRN conducts grasp proposal prediction on the selected positive points. RN generates more accurate grasps by refining proposals predicted by GRN. To further improve the performance, we propose a grasp anchor mechanism, in which grasp anchors with assigned gripper orientations are introduced to generate grasp proposals. Experiments demonstrate that REGNet achieves a success rate of 79.34% and a completion rate of 96% in real-world clutter, which significantly outperforms several state-of-the-art point-cloud based methods, including GPD, PointNetGPD, and S4G. The code is available at https://github.com/zhaobinglei/REGNet_for_3D_Grasping.