Metraipolis › archive › dc_7d2a28e5707f

Which Physical Tactile Cues Matter for Contact-Rich Imitation Learning? A Controlled Real-Robot Study — arXiv:2611.06673

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.06673
License (as archived)
CC0-1.0
Archived
2026-11-05T18:30:46.579Z
SHA-256 of the archived text
f1015aee3591aa2b22ff4a7eba8f2a7054e953109bf92039c9b52ed26cf61a69
Stable URL of this page
https://metraipolis.com/documento/dc_7d2a28e5707f

How to cite

Which Physical Tactile Cues Matter for Contact-Rich Imitation Learning? A Controlled Real-Robot Study — arXiv:2611.06673 — arXiv (en), https://arxiv.org/abs/2611.06673 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7d2a28e5707f (Metraipolis archive dc_7d2a28e5707f, sha256 f1015aee3591aa2b22ff4a7eba8f2a7054e953109bf92039c9b52ed26cf61a69)
BibTeX
@misc{dc7d2a28e5707f,
  title = {Which Physical Tactile Cues Matter for Contact-Rich Imitation Learning? A Controlled Real-Robot Study — arXiv:2611.06673},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.06673},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7d2a28e5707f; sha256 f1015aee3591aa2b22ff4a7eba8f2a7054e953109bf92039c9b52ed26cf61a69},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.06673. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Vision-based tactile sensors capture multiple aspects of physical interaction within a single image stream, including contact appearance, geometry, indentation depth, and tangential deformation. However, existing visuo-tactile policies often directly process tactile observations as images, making it difficult to determine which physical cues contribute to policy learning. This paper presents a controlled real-robot study that compares physically interpretable tactile signals using the LeRobot platform, enhanced with our visuo-tactile perception system. From the same tactile stream, we derive tactile RGB images, normal/depth maps, and marker-flow fields, representing contact appearance, geometry, and tangential deformation, respectively. Using identical task demonstrations and the same policy backbone, we evaluate the individual and combined contributions of these tactile cues. We further compare tactile encoders and visuo-tactile fusion strategies. Evaluation across 720 real-robot trials yields four key findings: (1) tactile perception substantially improves the overall success rate from 57.8% to 78.9%, although its contribution varies across task stages; (2) marker flow is the most effective individual cue, achieving a success rate of 74.4% and playing a particularly important role in regulating established contact; (3) cue-factorized encoding consistently improves performance, highlighting that different physical cues require tailored processing techniques; and (4) although the effectiveness of tactile fusion is task-dependent, cross-attention offers a lightweight solution with performance comparable to that of pretrained tactile encoders.

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/2611.06673 — 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 2026-11-05T18:20:03.992Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).