SOURCE-LINKED INTELLIGENCE

EgoWild2Dex: Learning Dexterous Robotic Manipulation from In-the-Wild Human Experience

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Egocentric human data provide a principled source of supervision for learning dexterous robot manipulation. Unlike prior approaches that often collect such data in constrained or specially constructed environments, we collect in-the-wild egocentric demonstrations in real-world settings, including homes, factories, and pharmacies, etc., where people perform their ordinary tasks while wearing head-mounted cameras. This collection protocol captures diverse workflows and hand-object interactions across long-tailed object and skill distributions, but also yields visually challenging observations du

Read original source ↗ Open in workspace

recordType

paper

region

Global