Metraipolis › archive › dc_8fe61db6392d
STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation — arXiv:2609.12549
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12549
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:58:13.006Z
- SHA-256 of the archived text
3af202c29b409ec80e464fe737470bde0f3dc9577eaf5d6139a74178115d31bf- Stable URL of this page
https://metraipolis.com/documento/dc_8fe61db6392d
How to cite
STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation — arXiv:2609.12549 — arXiv (en), https://arxiv.org/abs/2609.12549 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8fe61db6392d (Metraipolis archive dc_8fe61db6392d, sha256 3af202c29b409ec80e464fe737470bde0f3dc9577eaf5d6139a74178115d31bf)
BibTeX
@misc{dc8fe61db6392d,
title = {STAR: Sparse Tactile Representation Learning in Vision-Tactile-Language-Action Models for Dexterous Manipulation — arXiv:2609.12549},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12549},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8fe61db6392d; sha256 3af202c29b409ec80e464fe737470bde0f3dc9577eaf5d6139a74178115d31bf},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12549. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Dexterous manipulation requires coordinated multi-finger control and effective tactile feedback, yet learning these capabilities remains challenging due to the lack of large-scale real-world data and the difficulty of extracting effective representations from sparse tactile signals. We build a robot platform and teleoperation system to collect a 200-hour bimanual dexterous manipulation dataset with synchronized visual, tactile, and language annotations, comprising 10,576 trajectories across 65 tasks, 69.5% of which involve dexterous multi-finger manipulation. We further propose STAR, an integrated training recipe for vision-tactile-language-action (VTLA) models that addresses the spatial, temporal, and informational sparsity of tactile signals through visual-tactile joint pre-training, sparse-global tactile token representation, and sparse future tactile prediction. Trained on this dataset, STAR achieves a 61% average success rate across four real-world tasks with 100 post-training trajectories per task, demonstrating dexterous performance under task-specific post-training. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-14 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.12549 — 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 2026-10-16T03:44:44.727Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).