Metraipolis › archive › dc_c2e525fe6fa4

ViBe: Visual Behavior Adaptation for Perceptive Humanoid Whole-Body Control — arXiv:2609.09918

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.09918
License (as archived)
CC0-1.0
Archived
2026-10-16T11:11:40.867Z
SHA-256 of the archived text
fadfe89a4e27ddcb539f3c0821001f96eb55ec3f67c21a0aba6a1d738507998d
Stable URL of this page
https://metraipolis.com/documento/dc_c2e525fe6fa4

How to cite

ViBe: Visual Behavior Adaptation for Perceptive Humanoid Whole-Body Control — arXiv:2609.09918 — arXiv (en), https://arxiv.org/abs/2609.09918 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2e525fe6fa4 (Metraipolis archive dc_c2e525fe6fa4, sha256 fadfe89a4e27ddcb539f3c0821001f96eb55ec3f67c21a0aba6a1d738507998d)
BibTeX
@misc{dcc2e525fe6fa4,
  title = {ViBe: Visual Behavior Adaptation for Perceptive Humanoid Whole-Body Control — arXiv:2609.09918},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09918},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2e525fe6fa4; sha256 fadfe89a4e27ddcb539f3c0821001f96eb55ec3f67c21a0aba6a1d738507998d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09918. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Motion tracking provides a scalable recipe for humanoid whole-body control. By design, the resulting trackers lack exteroceptive feedback hence reacting to the environment remains the responsibility of a higher-level planner. Existing perceptive controllers train geometry-only encoders from scratch, trading semantics for sim-to-real ease, and typically rely on teacher-student distillation for a task of interest. We present ViBe, a post-training framework for adapting motion trackers to perceptive control tasks. We leverage pre-trained visual encoders with a multi-query extractor module to learn task-relevant perceptive feedback. This feedback is grafted onto the tracker's input via low-rank adapters, enabling parameter-efficient fine-tuning. Given a task reward and a reference dataset, this modular controller can be adapted directly via policy optimization. Across four tasks, ViBe shows zero-shot sim-to-real transfer spanning perceptive walking on curbs and parkour, Repose Cube, omni-object loco-manipulation, and dodgeball, with visually robust performance across outdoor, low-light, and RGB distractor conditions. Finally, we solve a goal-oriented Repose Cube task with a deliberately simple planner, demonstrating the efficacy of perceptive controllers, adapted by our approach.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-10 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.09918 — 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 2026-10-16T10:19:11.896Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).