Metraipolis › archive › dc_4e8e3c2a4bd2

ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware — arXiv:2609.18514

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.18514
License (as archived)
CC0-1.0
Archived
2026-10-15T15:08:03.417Z
SHA-256 of the archived text
9d0b0a056602cb4c783392000159ec88436aa2bd04fff3a90c94f5006e01f600
Stable URL of this page
https://metraipolis.com/documento/dc_4e8e3c2a4bd2

How to cite

ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware — arXiv:2609.18514 — arXiv (en), https://arxiv.org/abs/2609.18514 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4e8e3c2a4bd2 (Metraipolis archive dc_4e8e3c2a4bd2, sha256 9d0b0a056602cb4c783392000159ec88436aa2bd04fff3a90c94f5006e01f600)
BibTeX
@misc{dc4e8e3c2a4bd2,
  title = {ActiveScale: Scaling Active Perception for Robots across Model, Data, and Hardware — arXiv:2609.18514},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.18514},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4e8e3c2a4bd2; sha256 9d0b0a056602cb4c783392000159ec88436aa2bd04fff3a90c94f5006e01f600},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.18514. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Active perception is essential for robotic manipulation when fixed viewpoints leave task-relevant information occluded or unobserved. However, enabling vision-language-action (VLA) models to reason across changing viewpoints and actively acquire informative observations remains challenging. We present ActiveScale, a framework that advances active perception through coordinated model, data, and hardware designs. Our model augments a VLA with historical video observations and explicit camera-pose supervision, using per-frame pose tokens and a lightweight prediction head to associate observations across viewpoints and support a coherent understanding of the scene. To learn from the camera motion naturally present in human activity, we introduce a scalable human--robot mid-training recipe using 1000 hours of egocentric and robotic data, adapting the model to temporal inputs and pose supervision. We further introduce Active-perception Mobile-manipulation Platform (AMP), a robotic platform that supports active perception and mobile manipulation through single-operator teleoperation, enabling scalable collection of demonstrations that coordinate viewpoint changes and manipulation. Experiments demonstrate improved success rates on active-perception tasks, while ablation studies validate the contributions of camera-pose-aware modeling and egocentric mid-training. Together, these components provide an integrated foundation for studying and developing active perception in robotic manipulation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-17 in cs.LG).
Categorie arXiv: Robotics (cs.RO) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.18514 — 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 2026-10-15T14:08:19.256Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-17?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).