GDN: A Coarse-To-Fine (C2F) Representation for End-To-End 6-DoF Grasp Detection
This addresses robotic grasping efficiency and accuracy for applications like manipulation, though it appears incremental as it builds on existing grasp detection methods.
The paper tackles 6-DoF grasp detection from point clouds by proposing an end-to-end network (GDN) with a coarse-to-fine representation, achieving at least 20x faster speed than previous two-stage methods and improving success rates by 8% in single-object scenes and 40% in clutter scenes.
We proposed an end-to-end grasp detection network, Grasp Detection Network (GDN), cooperated with a novel coarse-to-fine (C2F) grasp representation design to detect diverse and accurate 6-DoF grasps based on point clouds. Compared to previous two-stage approaches which sample and evaluate multiple grasp candidates, our architecture is at least 20 times faster. It is also 8% and 40% more accurate in terms of the success rate in single object scenes and the complete rate in clutter scenes, respectively. Our method shows superior results among settings with different number of views and input points. Moreover, we propose a new AP-based metric which considers both rotation and transition errors, making it a more comprehensive evaluation tool for grasp detection models.