Metraipolis › archive › dc_2a57f12bb257

WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors — arXiv:2609.18197

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18197
License (as archived)
CC0-1.0
Archived
2026-10-15T16:55:48.594Z
SHA-256 of the archived text
833a0dc692f03344bbc7b4606925741d261fd36c3939f18db2ebf4f226d3350f
Stable URL of this page
https://metraipolis.com/documento/dc_2a57f12bb257

How to cite

WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors — arXiv:2609.18197 — arXiv (en), https://arxiv.org/abs/2609.18197 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a57f12bb257 (Metraipolis archive dc_2a57f12bb257, sha256 833a0dc692f03344bbc7b4606925741d261fd36c3939f18db2ebf4f226d3350f)
BibTeX
@misc{dc2a57f12bb257,
  title = {WholeBodyWAM: Learning Whole-Body World Action Models with Scalable Motion Priors — arXiv:2609.18197},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18197},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a57f12bb257; sha256 833a0dc692f03344bbc7b4606925741d261fd36c3939f18db2ebf4f226d3350f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18197. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid whole-body manipulation requires coordinated whole-body dynamics, yet large-scale trajectories from a target robot are expensive to collect and difficult to scale. In contrast, whole-body motion from human and humanoid sources is abundantly available, although such data cannot be directly used as embodiment-specific robot actions. This work asks whether these scalable motion resources can instead provide a transferable predictive prior for humanoid world-action modeling. We introduce WholeBodyWAM, a humanoid world-action model that learns whole-body dynamics from large-scale heterogeneous motion before target-robot training. We curate UniMotion-4K, a motion corpus spanning more than 4K hours from human videos, native 3D motion datasets, and heterogeneous humanoid platforms, and canonicalize these diverse sources into a unified motion space. A language-conditioned Motion Expert is then pretrained to predict future whole-body motion without target-robot action supervision. During robot post-training, the pretrained Motion Expert is integrated with Video and Action Experts through asymmetric Mixture-of-Transformers (MoT) attention, enabling predictive scene dynamics and whole-body motion to jointly inform embodiment-specific action generation. Experiments show that WholeBodyWAM consistently benefits from increased motion-pretraining scale, improves future-motion prediction and downstream task performance, and transfers effectively to real-world humanoid manipulation. Moreover, the pretrained motion prior substantially improves data efficiency under limited target-robot demonstrations.

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/2609.18197 — 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 2026-10-15T16:13:27.274Z 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).