aiqbench analysis
This paper applies learning-based methods to robotic grasping, presenting an end-to-end network that predicts dense dexterous grasps from single-view point clouds in cluttered multi-object scenes, along with a 307-object, 240-scene dataset. The reported gains (88.63% simulation and 78.98% real-robot success, lower penetration) are measured against unspecified baselines, and real-world results are a single platform, so generalization claims need broader validation. For AI readers, the useful takeaways are the scene-level data generation pipeline and the explicit modeling of pre-grasp configurations as supervision.
DGS-Net: Learning Dexterous Grasps from Single-View Point Clouds via a Multi-Object Scene Dataset
arXiv:2603.15410v2 Announce Type: replace Abstract: Dexterous grasping in multi-object scene constitutes a fundamental challenge in robotic manipulation. Current mainstream grasping datasets predominantly focus on single-object scenarios and predefined grasp configurations, often neglecting environmental interference and the modeling of dexterous pre-grasp gesture, thereby limiting their generalizability in real-world applications. To address this, we propose DGS-Net, an end-to-end grasp prediction network capable of learning dense grasp configurations from single-view point clouds in multi-object scene. Furthermore, we propose a two-stage grasp data generation strategy that progresses from dense single-object grasp synthesis to dense scene-level grasp generation. Our dataset comprises 307 objects, 240 multi-object scenes, and over 350k validated grasps. By explicitly modeling grasp offsets and pre-grasp configurations, the dataset provides more robust and accurate supervision for dexterous grasp learning. Experimental results show that DGS-Net achieves grasp success rates of 88.63\% in simulation and 78.98\% on a real robotic platform, while exhibiting lower penetration with a mean penetration depth of 0.375 mm and penetration volume of 559.45 mm^3, outperforming existing methods and demonstrating strong effectiveness and generalization capability. Our dataset is available at https://github.com/4taotao8/DGS-Net.
Abstract:Dexterous grasping in multi-object scene constitutes a fundamental challenge in robotic manipulation. Current mainstream grasping datasets predominantly focus on single-object scenarios and predefined grasp configurations, often neglecting environmental interference and the modeling of dexterous pre-grasp gesture, thereby limiting their generalizability in real-world applications. To address this, we propose DGS-Net, an end-to-end grasp prediction network capable of learning dense grasp configurations from single-view point clouds in multi-object scene. Furthermore, we propose a two-stage grasp data generation strategy that progresses from dense single-object grasp synthesis to dense scene-level grasp generation. Our dataset comprises 307 objects, 240 multi-object scenes, and over 350k validated grasps. By explicitly modeling grasp offsets and pre-grasp configurations, the dataset provides more robust and accurate supervision for dexterous grasp learning. Experimental results show that DGS-Net achieves grasp success rates of 88.63\% in simulation and 78.98\% on a real robotic platform, while exhibiting lower penetration with a mean penetration depth of 0.375 mm and penetration volume of 559.45 mm^3, outperforming existing methods and demonstrating strong effectiveness and generalization capability. Our dataset is available at this https URL.
10 pages, 6 figures. Submitted to IEEE Transactions on Automation Science and Engineering (T-ASE)
Robotics (cs.RO)
arXiv:2603.15410 [cs.RO]
(or arXiv:2603.15410v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2603.15410 Focus to learn more arXiv-issued DOI via DataCite
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 · 282 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Industrial Dexterity Benchmark: A Hardware-Software Benchmarking Platform for Industrial Dexterous Manipulation
arXiv · Jul 27, 2026
The Machines that Make the Machines
NVIDIA · Oct 7, 2026
Physical AI’s moment has arrived – but moving from demo to deployment is the hard part. AWS wants to fix that
ZK Research · Aug 24, 2026