Metraipolis › archive › dc_5e35439b84ff

$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation — arXiv:2608.06375

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.06375
License (as archived)
CC0-1.0
Archived
2026-10-31T10:38:24.454Z
SHA-256 of the archived text
75c05a76e933f6cbd16b713c5e5825d6974598483da2175360559d99071a6ffe
Stable URL of this page
https://metraipolis.com/documento/dc_5e35439b84ff

How to cite

$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation — arXiv:2608.06375 — arXiv (en), https://arxiv.org/abs/2608.06375 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_5e35439b84ff (Metraipolis archive dc_5e35439b84ff, sha256 75c05a76e933f6cbd16b713c5e5825d6974598483da2175360559d99071a6ffe)
BibTeX
@misc{dc5e35439b84ff,
  title = {$ω$-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulation — arXiv:2608.06375},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.06375},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_5e35439b84ff; sha256 75c05a76e933f6cbd16b713c5e5825d6974598483da2175360559d99071a6ffe},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.06375. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid household tasks often require concurrent loco-manipulation, where the robot must move, adjust posture, maintain balance, and manipulate objects as a single coordinated behavior. Yet existing humanoid policies typically decompose locomotion and manipulation, while recent world-action models remain either arm-centric or video-centered. We present $\omega$-0, a latent predictive whole-body world-action model for real-world humanoid concurrent loco-manipulation. Given a language instruction, current visual observation, and robot proprioceptive state, $\omega$-0 directly predicts controller-compatible whole-body action latents for real-robot execution. Rather than reconstructing future videos, $\omega$-0 learns compact future observation embeddings as a lightweight predictive objective, coupling latent visual foresight with diffusion-based whole-body action generation. The model supports egocentric RGB, exocentric RGB, and exocentric depth inputs, and leverages controller-based simulation replay to ground human/public visual-motion priors into robot-executable action latents. We further collect $\omega$-HOME, a 40+ hour real-world household humanoid dataset with synchronized multi-view observations, whole-body SMPL motions, robot states, and action latents. Real-world experiments on 11 household tasks demonstrate that a single $\omega$-0 model can produce smooth manipulate-while-moving behaviors and consistently outperform representative imitation learning, VLA, humanoid, and WAM baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.06375 — 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 2026-10-31T10:24:02.139Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).