Metraipolis › archive › dc_4874773ba8a8
Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation — arXiv:2610.22342
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22342
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T10:40:12.527Z
- SHA-256 of the archived text
854b0b7e2acebdd9886703605b5e909b4eae4230bf662a4b017ce1f43c9df667- Stable URL of this page
https://metraipolis.com/documento/dc_4874773ba8a8
How to cite
Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation — arXiv:2610.22342 — arXiv (en), https://arxiv.org/abs/2610.22342 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4874773ba8a8 (Metraipolis archive dc_4874773ba8a8, sha256 854b0b7e2acebdd9886703605b5e909b4eae4230bf662a4b017ce1f43c9df667)
BibTeX
@misc{dc4874773ba8a8,
title = {Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation — arXiv:2610.22342},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22342},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4874773ba8a8; sha256 854b0b7e2acebdd9886703605b5e909b4eae4230bf662a4b017ce1f43c9df667},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22342. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalist robot policies benefit from large-scale visual pretraining but often struggle with contact-rich dexterous manipulation, where force, compliance, and incipient slip are hard to observe from images. We present Spark-0, a spatially aligned vision-tactile-language-action (VTLA) model that uses touch in two complementary ways. During pretraining, image-space contact maps derived from tactile gloves, together with features from a frozen 3D geometry teacher, supervise the visual tokens; these objectives are removed at inference. In parallel, a tactile pathway encodes regional force histories and 3D taxel states to condition the action expert. A single checkpoint therefore supports both vision-only and tactile-conditioned deployment. To scale this supervision, we build HumanTouch, a 1,000-hour dataset of full-hand tactile human manipulation, and pretrain Spark-0 on it together with egocentric video, robot data, and simulation. We also release SparkArena, which pairs vision-only simulated tasks with tactile-conditioned real-robot tasks on one dexterous embodiment. Spark-0 achieves the highest mean success rate on both SparkArena tracks and ranks first on all eight aggregate metrics of the Ego Humanoid Manipulation Benchmark. Compared with vision-only pretraining on the same data and compute with touch discarded, retaining the touch of 1,000 hours of HumanTouch raises vision-only success on Ego Humanoid from 52.5% to 71.7%, and success on SparkArena-Real, where touch is also used at deployment, from 44.0% to 52.0%, indicating that touch serves not only as a policy input but also as scalable supervision for dexterous visuomotor pretraining. The Website is available at: this https URL . Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2610.22342 — 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 2026-10-16T08:52:17.711Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).