Metraipolis › archive › dc_3cdb26985998

UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision — arXiv:2609.39388

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.39388
License (as archived)
CC0-1.0
Archived
2026-10-07T14:46:51.433Z
SHA-256 of the archived text
0c1d3f06688aede0bce079f5483049cff96c8d7894f74b7048379c6bff44005f
Stable URL of this page
https://metraipolis.com/documento/dc_3cdb26985998

How to cite

UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision — arXiv:2609.39388 — arXiv (en), https://arxiv.org/abs/2609.39388 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3cdb26985998 (Metraipolis archive dc_3cdb26985998, sha256 0c1d3f06688aede0bce079f5483049cff96c8d7894f74b7048379c6bff44005f)
BibTeX
@misc{dc3cdb26985998,
  title = {UniWAM Technical Report: Unified Mobile Manipulation via Mixed-Stream World-Action Modeling and Manipulation Anchor Pose Supervision — arXiv:2609.39388},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.39388},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3cdb26985998; sha256 0c1d3f06688aede0bce079f5483049cff96c8d7894f74b7048379c6bff44005f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39388. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Mobile manipulation requires precise navigation to a manipulation-ready pose followed by reliable object interaction. These two stages differ in action spaces and visual requirements, which complicates unified policy learning. In addition, collecting diverse real-world navigation data with explicit manipulation-ready pose supervision remains costly and difficult to scale. We introduce UniWAM, a unified mixed-stream world-action model with separate action encoders and output heads for navigation and manipulation, sharing a common backbone. This design supports joint representation learning on independently sampled navigation and manipulation data. UniWAM supports independent inference for either stream and batch-parallel inference for both. We further introduce Manipulation Anchor Pose (MAP) supervision for where to stop and how to orient for manipulation. An automated pipeline constructs MAP-Data from large-scale 3D scenes, yielding over 1.5 million episodes and 7,500 hours. MAP-Data provides per-frame target-object bounding boxes and image-plane MAP coordinates as auxiliary navigation supervision. Together with projected end-effector trajectories for manipulation, these prediction targets provide stream-specific image-plane supervision for action learning from egocentric observations. With large-scale MAP-Data, UniWAM outperforms the strongest external baselines on our MAP-Bench by 30.1\% in position error and 44.0\% in heading error. Across 24 real-robot tasks, UniWAM achieves leading results in MAP navigation and mobile manipulation, with competitive manipulation performance. We have released code, data, and benchmark.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-01 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.39388 — 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 2026-10-07T14:19:00.906Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).