SuperGrasp: Single-View Object Grasping via Superquadric Similarity Matching, Evaluation, and Refinement
This addresses the problem of incomplete geometric information in robotic manipulation for researchers and practitioners, representing an incremental improvement with a novel method for a known bottleneck.
The paper tackles the challenge of robotic grasping from single-view observations by proposing SuperGrasp, a two-stage framework that generates initial grasp poses via superquadric similarity matching and refines them with an end-to-end network, achieving stable grasping performance and strong generalization across novel objects in simulation and real-world tests.
Robotic grasping from single-view observations remains a critical challenge in manipulation. Existing methods still struggle to generate stable and valid grasp poses when confronted with incomplete geometric information. To address these limitations, we propose SuperGrasp, a novel two-stage framework for single-view grasping with parallel-jaw grippers that decomposes the grasping process into initial grasp pose generation and subsequent grasp evaluation and refinement. In the first stage, we introduce a Similarity Matching Module that efficiently retrieves grasp candidates by matching the input single-view point cloud with a pre-computed primitive dataset based on superquadric coefficients. In the second stage, we propose E-RNet, an end-to-end network that expands the graspaware region and takes the initial grasp closure region as a local anchor region, enabling more accurate and reliable evaluation and refinement of grasp candidates. To enhance generalization, we construct a primitive dataset containing 1.5k primitives for similarity matching and collect a large-scale point cloud dataset with 100k stable grasp labels from 124 objects for network training. Extensive experiments in both simulation and realworld environments demonstrate that our method achieves stable grasping performance and strong generalization across varying scenes and novel objects.