Metraipolis › archive › dc_e02ac38cd7d9

From Legs to Wheels: Embodiment-Aware Human Motion Retargeting for Mobile-Base Humanoids — arXiv:2610.08381

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08381
License (as archived)
CC0-1.0
Archived
2026-10-07T13:12:23.253Z
SHA-256 of the archived text
256f4b5c35141e4d8cb0602ac4e3957e30cf5e820343bdd91ff9653e802d1eb1
Stable URL of this page
https://metraipolis.com/documento/dc_e02ac38cd7d9

How to cite

From Legs to Wheels: Embodiment-Aware Human Motion Retargeting for Mobile-Base Humanoids — arXiv:2610.08381 — arXiv (en), https://arxiv.org/abs/2610.08381 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e02ac38cd7d9 (Metraipolis archive dc_e02ac38cd7d9, sha256 256f4b5c35141e4d8cb0602ac4e3957e30cf5e820343bdd91ff9653e802d1eb1)
BibTeX
@misc{dce02ac38cd7d9,
  title = {From Legs to Wheels: Embodiment-Aware Human Motion Retargeting for Mobile-Base Humanoids — arXiv:2610.08381},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08381},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e02ac38cd7d9; sha256 256f4b5c35141e4d8cb0602ac4e3957e30cf5e820343bdd91ff9653e802d1eb1},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08381. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Human video offers a scalable source of robot demonstrations, yet most human-to-humanoid retargeting methods assume a legged robot with human-like kinematics. This assumption does not hold for mobile-base humanoids equipped with a wheeled base, vertical lift, and two arms. Human walking must be expressed through base motion, while torso bending may require coordinated lift and arm motion. We address this mismatch with a task-conditioned framework that assigns reconstructed human motion to base, lift, and arm responsibilities before robot-specific realization. The allocator preserves the human-derived path, stabilizes heading, separates turn and translation when needed, retimes commands to satisfy base limits, and repairs lift and arm trajectories. A deployment adapter then converts the reference to 50 Hz commands using stationary-base detection, deadband and slew-rate filtering, time-consistent playback scaling, and separate linear and angular gains. We evaluate the resulting references with human-derived task-space comparisons, policy-free simulation replay, and a qualitative execution on a physical robot.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.08381 — 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 2026-10-07T12:42:33.622Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).