Metraipolis › archive › dc_2cc7dcdbbc0c

AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison — arXiv:2609.21377

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.21377
License (as archived): CC0-1.0
Archived: 2026-10-10T02:30:08.235Z
SHA-256 of the archived text: 63a578d7a621945f4534baa2e0217e2ee52af6e14332e7b2182358e63127701f
Stable URL of this page: https://metraipolis.com/documento/dc_2cc7dcdbbc0c

How to cite

AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison — arXiv:2609.21377 — arXiv (en), https://arxiv.org/abs/2609.21377 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cc7dcdbbc0c (Metraipolis archive dc_2cc7dcdbbc0c, sha256 63a578d7a621945f4534baa2e0217e2ee52af6e14332e7b2182358e63127701f)

BibTeX

@misc{dc2cc7dcdbbc0c,
  title = {AVT-Fabric: Active Visuo-Tactile Perception via Adaptive Evidence Selection for Efficient Robotic Fabric Comparison — arXiv:2609.21377},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.21377},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cc7dcdbbc0c; sha256 63a578d7a621945f4534baa2e0217e2ee52af6e14332e7b2182358e63127701f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.21377. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robotic fabric comparison needs to actively combine visual appearance and tactile cues. Here, we present AVT-Fabric, an RGB-first framework that allocates tactile evidence according to the difficulty of each comparison. A dual-scale gate evaluates answer-token confidence and raw logit separation to determine whether another force-tagged GelSight observation is needed. Compact textual memory preserves the executed history, and majority voting consolidates the selected predictions. On 400 held-out comparisons, AVT-Fabric achieves 98.0% accuracy with a compact 7B Multimodal Large Language Model (MLLM), surpassing the 94.0% reported by the 90B MLLM-Fabric baseline by 4.0 percentage points while processing only 1.60 of five available stages on average. It improves on matched passive inference by 9.25 percentage points and reduces model-side latency by 61.8%, while also improving on RGB-only accuracy. Four additional MLLM backbones support the generalizability, accuracy, and efficiency of the framework. This framework is also deployed on a real robotic system, achieving 78.1% pairwise ranking accuracy and correct fabric selection in seven of eight application scenarios. AVT-Fabric demonstrates that adaptive evidence selection can improve both the accuracy and efficiency of robotic visuo-tactile reasoning.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-21 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.21377 — 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 2026-10-10T02:09:55.340Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-21?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).