HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.
RUKA: Rethinking the design of humanoid hands with learning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.RO 3years
2026 3representative citing papers
DexLink Hand is a linkage-driven 16-DOF anthropomorphic robotic hand prototype with embedded actuation that achieves maximum Kapandji score and all 33 Feix grasp types in a human-scale, low-cost package.
MM-Hand presents a modular 21-DOF dexterous hand with remote tendon actuation, integrated multimodal sensing, and open-source hardware that achieves 25 N fingertip force over 1 m transmission distance.
citing papers explorer
-
Human Universal Grasping
HUG trains a flow-matching model on a new 1M-frame egocentric human grasp dataset to generate retargetable grasps from single RGB-D images, beating baselines by 23-34% on a new 90-object benchmark.
-
DexLink Hand: A Compact, Affordable, 16-DOF Linkage-Driven Hand with Human-Like Dexterity
DexLink Hand is a linkage-driven 16-DOF anthropomorphic robotic hand prototype with embedded actuation that achieves maximum Kapandji score and all 33 Feix grasp types in a human-scale, low-cost package.
-
MM-Hand: A 21-DOF Multi-modal Modular Dexterous Robotic Hand with Remote Actuation
MM-Hand presents a modular 21-DOF dexterous hand with remote tendon actuation, integrated multimodal sensing, and open-source hardware that achieves 25 N fingertip force over 1 m transmission distance.