Metraipolis › archive › dc_8cb2c8ad1f08

Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation — arXiv:2609.18763

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18763
License (as archived)
CC0-1.0
Archived
2026-10-15T16:58:45.046Z
SHA-256 of the archived text
b86632e7454b674ae35d804a4971b76cb87428f189cba58eb3828167892e6f7a
Stable URL of this page
https://metraipolis.com/documento/dc_8cb2c8ad1f08

How to cite

Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation — arXiv:2609.18763 — arXiv (en), https://arxiv.org/abs/2609.18763 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8cb2c8ad1f08 (Metraipolis archive dc_8cb2c8ad1f08, sha256 b86632e7454b674ae35d804a4971b76cb87428f189cba58eb3828167892e6f7a)
BibTeX
@misc{dc8cb2c8ad1f08,
  title = {Gated Residual Body-Hand Coordination for Whole-Body Humanoid Teleoperation — arXiv:2609.18763},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18763},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8cb2c8ad1f08; sha256 b86632e7454b674ae35d804a4971b76cb87428f189cba58eb3828167892e6f7a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18763. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Whole-body humanoid teleoperation commonly combines a motion-tracking policy with a separate dexterous-hand retargeter. However, independently generated commands do not explicitly preserve body-hand geometric relations, leading to mismatches in relative wrist poses and fingertip positions during bimanual interaction. We present a gated residual coordination framework that keeps both modules frozen and applies bounded corrections to their outputs. A motion-conditioned action gate allocates correction authority across joint groups, while reference-geometry-dependent reward gates emphasize relevant interaction objectives during training. To establish the nominal body controller on Agile One, we introduce multi-pose morphology calibration that jointly estimates triaxial scales and effector-local offsets, together with staged motion dataset curation for training a SONIC-based tracker. The residual policy uses human motion references, initial commands, and robot proprioception without explicit object or contact observations. In simulation, it reduces wrist and fingertip geometry errors by 39.2-56.3% over direct composition on held-out GRAB motions, while preserving whole-body tracking on AMASS, with success rates of 89.03% without residual coordination and 89.29% with it. Ablations characterize the contributions of reward gating, adaptive correction authority, and separate body and hand correction heads.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-17 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.18763 — 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 2026-10-15T16:13:27.323Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).