Plug-and-Play Shape Matching Module for Zero-Shot Mesh-Free Grasp Refinement on Unknown Objects
- 17 October 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 10 (12) , 12852-12859
Abstract
Reliably grasping unknown objects in logistics automation remains a major challenge. While most approaches rely on 3D CAD models or large-scale training, their applicability to novel items is limited. This letter proposes a plug-and-play geometric refinement module that can be appended to any existing grasp planner. The module operates in a training-free and mesh-free manner, estimating an object’s approximate centroid from a single RGB-D image to enhance grasp stability. Its core mechanism involves using an initial grasp candidate as an automatic prompt for segmentation, followed by geometric primitive fitting to the isolated object’s point cloud. By rescoring grasp candidates based on proximity to the estimated centroid, our module improves physical stability. Experimental results demonstrate that our module improves the success rate of baseline grasp planners by up to 25%p enhancing real-world pick-and-place performance without requiring any offline training or prior object models.Keywords
Funding Information
- National Research Foundation of Korea
- Korea government (RS-2023-00207772)
This publication has 32 references indexed in Scilit:
- Segment and Recognize Anything at Any Granularity2024
- FreeZe: Training-Free Zero-Shot 6D Pose Estimation with Geometric and Vision Foundation Models2024
- GigaPose: Fast and Robust Novel Object Pose Estimation via One Correspondence2024
- SAM-6D: Segment Anything Model Meets Zero-Shot 6D Object Pose Estimation2024
- Improving reinforcement learning based moving object grasping with trajectory predictionIntelligent Service Robotics, 2023
- GDR-Net: Geometry-Guided Direct Regression Network for Monocular 6D Object Pose Estimation2021
- Automated order picking systems and the links between design and performance: a systematic literature reviewInternational Journal of Production Research, 2020
- DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion2019
- Implicit 3D Orientation Learning for 6D Object Detection from RGB Images2018
- You Only Look Once: Unified, Real-Time Object Detection2016