CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
CoToGrasp: Contact-Topology-Conditioned Dexterous Grasp Synthesis via Canonical Workspace Learning
This research proposes CoToGrasp, a generative framework that synthesizes diverse and stable grasps conditioned on specific contact topologies, without requiring object-annotated datasets. The method uses a canonical workspace to decouple semantic intent from object geometry, enabling zero-shot generalization. It achieves state-of-the-art performance on DexGraspNet and demonstrates physical feasibility on a robot platform.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- code: Available Artifact link Open source S5
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
ity and kinematic feasibility of our synthesized contact topologies on a physical robot platform. Code is available on our project website at https://cea-list.github.io/cotograspweb/ .
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org