Metraipolis › archive › dc_85d3df19233a

TACTIC: Understanding Tactile Encoders and Conditioning for Contact-rich Robot Manipulation Policies — arXiv:2609.30969

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.30969
License (as archived)
CC0-1.0
Archived
2026-10-08T03:14:56.453Z
SHA-256 of the archived text
9525aaa1b79f0f1be0497e3cbe12f748f0642c400a42616d5cf13347fc6a5e00
Stable URL of this page
https://metraipolis.com/documento/dc_85d3df19233a

How to cite

TACTIC: Understanding Tactile Encoders and Conditioning for Contact-rich Robot Manipulation Policies — arXiv:2609.30969 — arXiv (en), https://arxiv.org/abs/2609.30969 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_85d3df19233a (Metraipolis archive dc_85d3df19233a, sha256 9525aaa1b79f0f1be0497e3cbe12f748f0642c400a42616d5cf13347fc6a5e00)
BibTeX
@misc{dc85d3df19233a,
  title = {TACTIC: Understanding Tactile Encoders and Conditioning for Contact-rich Robot Manipulation Policies — arXiv:2609.30969},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.30969},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_85d3df19233a; sha256 9525aaa1b79f0f1be0497e3cbe12f748f0642c400a42616d5cf13347fc6a5e00},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30969. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tactile information is essential for contact-rich manipulation tasks in robotics. Vision-based tactile sensors make it particularly easy to design end-to-end manipulation policies with tactile sensing, as they enable the use of existing encoders from computer vision. However, this has led to a huge variety of architectures, training datasets, and evaluation protocols, making it difficult to determine which design choices best encode touch. In this work, we address this gap and present a comprehensive study of tactile encoders and fusion strategies across various contact-rich manipulation tasks in real-world experiments. To enable a controlled comparison, we train and evaluate all models under the same pipeline and experimental setup, comprising more than 2000 real-world rollouts. Our results go beyond other studies that only compare simulation performance, which does not necessarily translate to real-world settings, where large-scale evaluations are needed to obtain reliable statistics. Our key finding is that there is no universally optimal representation or fusion strategy for encoding visual-tactile. Instead, the best encoder backbone and fusion scheme depend strongly on the task.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-28 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.30969 — 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 2026-10-08T02:58:08.912Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).