Egocentric human videos offer a scalable alternative to robot teleoperation for collecting dexterous manipulation data. However, two challenges limit their use as reliable training data: accurate hand-object interaction (HOI) reconstruction from monocular RGB and high-quality robot demonstrations, especially visual obs...
Zi-Heng Wang, Yan-Ming Shao, Ting Mao et al.· 0 citations
Monocular videos of human manipulation provide abundant dexterous demonstrations, yet reconstructing hand-object interaction from a single view and transferring it to robot hands remain difficult, limiting their direct use for robot execution. Prior methods either require task-specific RL training, limiting scalability...
Ting Mao, Yan-Ming Shao, Zi-Heng Wang et al.· 0 citations
As dexterous hands proliferate, collecting data and training policies separately for every morphology becomes increasingly impractical. Scalable cross-embodiment learning therefore requires a unified representation that captures shared manipulation structure while preserving morphology-specific control. Differences in...
Xiang-Wei Jiang, Yao Mu, Li-Xin Duan et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.