Metraipolis › archive › dc_f54d4fd3fa9b
Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays — arXiv:2608.04043
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04043
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:34:38.788Z
- SHA-256 of the archived text
084d42537aaec0b259f70e7f330cc8ac1dd8da0992912d59b15dc7d22bdc920a- Stable URL of this page
https://metraipolis.com/documento/dc_f54d4fd3fa9b
How to cite
Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays — arXiv:2608.04043 — arXiv (en), https://arxiv.org/abs/2608.04043 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f54d4fd3fa9b (Metraipolis archive dc_f54d4fd3fa9b, sha256 084d42537aaec0b259f70e7f330cc8ac1dd8da0992912d59b15dc7d22bdc920a)
BibTeX
@misc{dcf54d4fd3fa9b,
title = {Tactus: Open-Vocabulary Object Recognition from Low-Cost Pressure Arrays — arXiv:2608.04043},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04043},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f54d4fd3fa9b; sha256 084d42537aaec0b259f70e7f330cc8ac1dd8da0992912d59b15dc7d22bdc920a},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04043. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Resistive pressure arrays are the cheapest and most widely shipped tactile sensors, yet tactile representation learning has concentrated on optical sensors that image a deforming gel. We present Tactus, an open model that answers text queries from pressure data alone: on the STAG benchmark (27 objects, held-out recordings), it reaches 0.771 +/- 0.062 top-1 over four runs (top-3 0.935), matching, and at best exceeding, the dataset's supervised closed-set CNN at 0.76, with no trained classifier head. The recipe is small-data: 187 training recordings, masked-autoencoder pretraining on 144k unlabeled same-sensor frames, and the sensor's own calibration affine, which recovered more accuracy than every architecture change combined. The released model's errors concentrate in a few contact-ambiguous classes, are uncorrelated with text-target geometry (Spearman rho <= 0.05 over 702 class pairs), and survive paraphrased and even bare-name queries within one point; two diverse frames recover 89% of eight-frame accuracy. Failures are reported with equal precision: cross-sensor pretraining pooling gave no gain, vision co-training degraded touch, and a mis-normalized input pipeline silently discarded 97% of the sensor's dynamic range while producing plausible intermediate results. Weights, code, and the memory layer the model plugs into are released openly. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.LG). Categorie arXiv: Machine Learning (cs.LG) ; Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2608.04043 — 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 2026-10-31T11:24:48.757Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).