SOURCE-LINKED INTELLIGENCE

One Demonstration, Many Objects: Generalizing Manipulation via Local Contact Geometry

arXiv · AI, language, vision and robotics · article · Sep 1, 2026 · UTC

Dexterous manipulation with multi-fingered robot hands promises human-level dexterity, but collecting large-scale dexterous robot hand data remains difficult. Learning from human demonstrations has emerged as a scalable alternative to robot teleoperation, providing strong priors on object interaction and contact strategies. Recent sim-to-real RL methods incorporate such priors, but often (i) omit rewards that explicitly incentivize precise contact, yielding weak real-world performance, and/or (ii) generalize poorly to unseen object instances. We propose DemoMimic (Dexterous Motion Mimic), a po

Read original source ↗ Open in workspace

recordType

paper

region

Global