Metraipolis › archive › dc_bd136d903333

X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control — arXiv:2609.15213

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.15213
License (as archived): CC0-1.0
Archived: 2026-10-16T02:14:45.813Z
SHA-256 of the archived text: 228859e06c98d0d0533c676c5387a9b83e3de48aaf9a94d89912a0ed2fb75085
Stable URL of this page: https://metraipolis.com/documento/dc_bd136d903333

How to cite

X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control — arXiv:2609.15213 — arXiv (en), https://arxiv.org/abs/2609.15213 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bd136d903333 (Metraipolis archive dc_bd136d903333, sha256 228859e06c98d0d0533c676c5387a9b83e3de48aaf9a94d89912a0ed2fb75085)

BibTeX

@misc{dcbd136d903333,
  title = {X-WBC: A Cross-Embodiment Foundation Model for Humanoid Whole-Body Control — arXiv:2609.15213},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.15213},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bd136d903333; sha256 228859e06c98d0d0533c676c5387a9b83e3de48aaf9a94d89912a0ed2fb75085},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.15213. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scaling humanoid whole-body control toward general-purpose deployment requires large human motion corpora and training experience shared across robot bodies. Existing methods usually train one policy per robot, leaving motion experience isolated across embodiments. We introduce X-WBC, a cross-embodiment foundation framework that separates relatively shared human motion semantics from embodiment-specific physical execution. Human-centered command tokens align full human motion, robot reference motion, and sparse VR observations. A causal Transformer learns reusable temporal structure from mixed multi-robot rollouts, while lightweight robot-specific modules map the shared representation to each robot's proprioception and action space. Across nine simulated embodiments, external motions, and four real robots, experiments show that joint training improves tracking, the aligned representation supports consistent control across command sources, and the learned policy remains competitive beyond the training corpus. These results support heterogeneous humanoids as joint data sources and establish cross-embodiment joint training as a practical route toward whole-body control foundation models.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.15213 — 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 2026-10-16T01:52:32.360Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).