Metraipolis › archive › dc_e148b847dc52

Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction — arXiv:2608.15897

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.15897
License (as archived)
CC0-1.0
Archived
2026-10-18T23:05:55.044Z
SHA-256 of the archived text
3a0f961005f2d7c8037539d2bc0391465309682cfc24c50366f8778199413004
Stable URL of this page
https://metraipolis.com/documento/dc_e148b847dc52

How to cite

Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction — arXiv:2608.15897 — arXiv (en), https://arxiv.org/abs/2608.15897 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e148b847dc52 (Metraipolis archive dc_e148b847dc52, sha256 3a0f961005f2d7c8037539d2bc0391465309682cfc24c50366f8778199413004)
BibTeX
@misc{dce148b847dc52,
  title = {Tactile Sim2Real without Tactile Simulation via Bottlenecked Latent Reconstruction — arXiv:2608.15897},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.15897},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e148b847dc52; sha256 3a0f961005f2d7c8037539d2bc0391465309682cfc24c50366f8778199413004},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15897. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Robot sensor designs, particularly tactile sensors, are highly diverse and evolve rapidly. Modeling each sensor in simulation demands substantial domain expertise and computational approximations can degrade the fidelity of the simulated signals. We propose Sim2Real via Bottlenecked Latent Reconstruction (SBLR), a framework that avoids sensor-specific simulation entirely by (1) training policies on a simulator-native oracle sensor that is easy to construct without modeling any particular sensor (e.g. we use a point-cloud and finger-tip forces as a tactile oracle), and (2) aligning real sensor latent embeddings to those of the oracle sensor at inference time. Policy training proceeds in two-stage: the policy first learns from the oracle sensor latents, then a bottlenecked latent reconstruction adapts it to the information loss expected when using the real sensor instead of the oracle. The alignment between oracle and real sensor is learned from unpaired random-play data collected in both simulation and the real world, using rectified-flow-based transformation networks trained on nearest-neighbor pseudo-pairs. Simulation experiments on three contact-rich tasks show that SBLR matches or approaches the performance of an oracle with direct access to tactile simulation. Hardware experiments on Peg Insertion and Gear Meshing with GelSight Mini and DIGIT sensors demonstrate 85-97.5% zero-shot success without requiring any sensor-specific modeling or calibration, outperforming a physics-based tactile simulation baseline by 7.5-15%.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-18 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2608.15897 — 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 2026-10-18T23:01:50.367Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).