Metraipolis › archive › dc_9997e45d288a

EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation — arXiv:2609.37181

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.37181
License (as archived)
CC0-1.0
Archived
2026-10-07T16:26:59.558Z
SHA-256 of the archived text
b76045039c7a460b2fa6c85c0c5c5954bd745c0c517fbc2a4af07d2dd3c04b4a
Stable URL of this page
https://metraipolis.com/documento/dc_9997e45d288a

How to cite

EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation — arXiv:2609.37181 — arXiv (en), https://arxiv.org/abs/2609.37181 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_9997e45d288a (Metraipolis archive dc_9997e45d288a, sha256 b76045039c7a460b2fa6c85c0c5c5954bd745c0c517fbc2a4af07d2dd3c04b4a)
BibTeX
@misc{dc9997e45d288a,
  title = {EgoHumanoid-V2: Human-to-Humanoid Transfer of Coordinated Whole-Body Skills for Loco-Manipulation — arXiv:2609.37181},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.37181},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_9997e45d288a; sha256 b76045039c7a460b2fa6c85c0c5c5954bd745c0c517fbc2a4af07d2dd3c04b4a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.37181. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human demonstrations capture diverse scenes and rich whole-body skills without requiring robot teleoperation. Prior work on egocentric transfer has emphasized scene generalization in loco-manipulation under decoupled control, leaving direct transfer of coordinated whole-body skills less explored. We present EgoHumanoid-V2, the first egocentric human-to-humanoid skill transfer framework for coordinated whole-body loco-manipulation. At its core, coarse-to-fine action alignment combines kinematic reference correction with dynamics-aware refinement. It improves end-effector pose accuracy while preserving whole-body coordination. We also use robot-arm rendering and training-time image augmentation to reduce the visual embodiment gap and improve viewpoint robustness. On four real-world tasks, vision-language-action (VLA) policies trained on aligned human data show zero-shot skill transfer without target-task robot demonstrations. Task scores are comparable to those of policies trained on teleoperation data at a lower collection cost. These results support human data as direct skill supervision.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.37181 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.953Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).