HUGS: Guiding Unified Dexterous Grasp Synthesis Across Modes and Scales via Learned Human Priors
2026-07-06 • Robotics
Robotics
AI summaryⓘ
The authors developed HUGS, a system that helps robots learn how to grasp objects of very different sizes, from small screws to large boxes. Instead of directly copying human hand movements, they teach the robot a kind of 'grasping intuition' based on many examples of how humans naturally hold things. This approach helps the robot decide the best way to use its fingers and hands to grab objects more reliably and with more variety. They tested HUGS by creating millions of robot grasps on many objects and showed that robots can choose the right grasping method on their own in real-world tasks.
dexterous graspingforce-closurecontact modesbimanual grasphuman priorgrasp synthesisrobotic manipulationoptimizationgrasp datasetwrist initialization
Authors
Mingrui Yu, Yongpeng Jiang, Yongyi Jia, Kangchen Lv, Li Huang, Yi Ren, Xiang Li
Abstract
Dexterous grasping across diverse object scales requires contact modes ranging from two-finger pinches to bimanual grasps. Existing dexterous grasp synthesis methods reduce the high-dimensional optimization space with manually designed expected contacts and initialization heuristics, which struggle to balance synthesis success rate and diversity. We present HUGS (Human-prior-guided Unified Dexterous Grasp Synthesis), a human-prior-guided framework for unified dexterous grasp synthesis across modes and scales. Instead of directly retargeting human demonstrations, HUGS learns an object-conditioned human prior that captures human grasp preferences and guides downstream force-closure-aware optimization. The prior is trained on a compact self-collected human grasp dataset with 1.8K grasps over 304 objects, providing broad coverage of object scales and contact modes. During synthesis, HUGS adaptively proposes contact modes and wrist initializations, substantially improving the balance between contact-mode coverage and synthesis success rate over heuristic-based methods. With HUGS, we synthesize 3.2M robotic grasps over 157K scenes, spanning object half-diagonal lengths from 2 cm to 30 cm and modes from two-finger to bimanual grasps. Models trained on the synthesized dataset autonomously select appropriate contact modes in the real world, enabling grasping from screws to large boxes.