Metraipolis › archive › dc_368f291f9175

Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight — arXiv:2611.04839

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04839
License (as archived)
CC0-1.0
Archived
2026-11-04T19:05:15.547Z
SHA-256 of the archived text
7b61e00f048d26d9291da09cbbdb60842dc2f55590b0c67cbcf665000b35aad0
Stable URL of this page
https://metraipolis.com/documento/dc_368f291f9175

How to cite

Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight — arXiv:2611.04839 — arXiv (en), https://arxiv.org/abs/2611.04839 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_368f291f9175 (Metraipolis archive dc_368f291f9175, sha256 7b61e00f048d26d9291da09cbbdb60842dc2f55590b0c67cbcf665000b35aad0)
BibTeX
@misc{dc368f291f9175,
  title = {Coordinating Humanoid Loco-Manipulation through Action-Conditioned Latent Foresight — arXiv:2611.04839},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04839},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_368f291f9175; sha256 7b61e00f048d26d9291da09cbbdb60842dc2f55590b0c67cbcf665000b35aad0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04839. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Humanoid loco-manipulation requires coordinated body motion and hand interaction over time, and a plausible-looking command sequence can still drop a held object or leave an interaction incomplete. We present action-conditioned latent foresight, a latent world-action model (WAM) that evaluates proposed command sequences before execution. An action generator proposes joint motion-hand command sequences from vision, language, and the robot state. An action-conditioned endpoint predictor estimates the visual features each sequence prefix reaches and measures progress toward a demonstration-derived subgoal, while a joint temporal prior scores temporal consistency given the robot state and preceding commands. The robot executes the first commands of the best-scoring sequence and replans from the next observation. During training, action consistency regularization reconstructs the first demonstrated command from observed and predicted feature changes, encouraging the predictor to retain action-relevant information. On ten tasks in the humanoid loco-manipulation simulation benchmark SIMPLE, our method achieves 89.7% average success, compared with 73.7% for Psi-Zero and 82.0% for DiT4DiT. On seven real-robot tasks, it achieves 85.7% under standard conditions and 65.7% under unseen object configurations, while GR00T N1.7 achieves 70.0% and 48.6%, respectively. Project page: this https URL

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/2611.04839 — 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 2026-11-04T18:39:52.412Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).