aiqbench analysis
Seg2Grasp addresses a critical bottleneck in industrial automation by replacing brittle end-to-end learning with a modular pipeline that combines Transformer-based segmentation with open-vocabulary classification. This approach significantly improves robustness for suction grasping robots operating in cluttered, unstructured environments where object recognition is essential before manipulation. The integration of Mask-CLIP allows the system to handle diverse items without retraining, marking a practical advancement for real-world robotic deployment.
Seg2Grasp: A Robust Modular Suction Grasping in Bin Picking
arXiv:2607.17757v1 Announce Type: cross Abstract: Current bin picking methods that rely heavily on end-to-end learning often falter when confronted with unfamiliar or complex objects in unstructured environments. To overcome these limitations, we introduce Seg2Grasp, a modular pipeline designed for robust suction grasping in dynamic and cluttered bin scenarios. Seg2Grasp is built on a three-step process: Segmentation, Grasping, and Classification. The Segmentation module employs a Transformer-based model to generate class-agnostic object masks from RGB-D images, ensuring accurate detection across various conditions. The Grasping module uses surface normals and mask proposals to determine the optimal suction points, enhancing grasp success. Finally, the Classification module leverages fine-tuned open-vocabulary Mask-CLIP for precise object identification, enabling versatile handling of diverse objects. Real-world robotic experiments demonstrate that Seg2Grasp outperforms existing methods in success rates and adaptability, establishing it as a powerful tool for automated bin picking in industrial settings.
Abstract:Current bin picking methods that rely heavily on end-to-end learning often falter when confronted with unfamiliar or complex objects in unstructured environments. To overcome these limitations, we introduce Seg2Grasp, a modular pipeline designed for robust suction grasping in dynamic and cluttered bin scenarios. Seg2Grasp is built on a three-step process: Segmentation, Grasping, and Classification. The Segmentation module employs a Transformer-based model to generate class-agnostic object masks from RGB-D images, ensuring accurate detection across various conditions. The Grasping module uses surface normals and mask proposals to determine the optimal suction points, enhancing grasp success. Finally, the Classification module leverages fine-tuned open-vocabulary Mask-CLIP for precise object identification, enabling versatile handling of diverse objects. Real-world robotic experiments demonstrate that Seg2Grasp outperforms existing methods in success rates and adaptability, establishing it as a powerful tool for automated bin picking in industrial settings.
7 pages, 6 figures, 2 tables. Published in the 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)
Robotics (cs.RO); Artificial Intelligence (cs.AI)
arXiv:2607.17757 [cs.RO]
(or arXiv:2607.17757v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2607.17757 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2024, pp. 2921-2927
https://doi.org/10.1109/IROS58592.2024.10801644 Focus to learn more DOI(s) linking to related resources
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 277 words
Related coverage
Pickalo: Leveraging 6D Pose Estimation for Low-Cost Industrial Bin Picking
arXiv · Oct 15, 2026
How to Evaluate General-Purpose Robot Policies for Real-World Deployment
NVIDIA · Jul 12, 2026
The best electric screwdrivers of 2026: Expert tested and reviewed
ZDNet · Aug 7, 2026
GraspTwin: Zero-Shot Task-Oriented Grasp Optimization via a Digital Twin
arXiv · Sep 28, 2026