Metraipolis › archive › dc_0efcd2a63bfb

Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly — arXiv:2609.07534

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.07534
License (as archived): CC0-1.0
Archived: 2026-10-16T15:31:11.006Z
SHA-256 of the archived text: 16094450d77591a43f0da9deb4355e145b8f70d89d4933aef3edace5b9cb3759
Stable URL of this page: https://metraipolis.com/documento/dc_0efcd2a63bfb

How to cite

Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly — arXiv:2609.07534 — arXiv (en), https://arxiv.org/abs/2609.07534 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0efcd2a63bfb (Metraipolis archive dc_0efcd2a63bfb, sha256 16094450d77591a43f0da9deb4355e145b8f70d89d4933aef3edace5b9cb3759)

BibTeX

@misc{dc0efcd2a63bfb,
  title = {Proprioception-Anchored Cross-Modal Pretraining for Zero-Shot Sim-to-Real Contact-Rich Assembly — arXiv:2609.07534},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.07534},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0efcd2a63bfb; sha256 16094450d77591a43f0da9deb4355e145b8f70d89d4933aef3edace5b9cb3759},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.07534. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Contact-rich assembly remains challenging because it requires submillimeter spatial accuracy and reliable interpretation of forces during sustained contact. Although simulation-based reinforcement learning offers a scalable training paradigm, discrepancies in visual observations, contact dynamics, and force/torque (F/T) measurements often limit policy transfer. We observe that proprioception is comparatively consistent across domains because joint positions are expressed in a shared calibrated coordinate system and joint velocities are computed consistently in simulation and on hardware. Based on this observation, we present PACE (Proprioception-Anchored Cross-Modal Encoder), which supervises temporal visual and F/T representations by predicting proprioceptive state transitions. Static domain-specific factors, including lighting, texture, and sensor bias, contain little information about joint motion; optimizing the proposed objective therefore suppresses their influence on the learned representation while retaining task-relevant motion cues. Policies trained on frozen PACE features are directly deployed on hardware without real-world fine-tuning or object-pose tracking. Across four contact-rich assembly tasks, PACE attains an average real-world success rate of 93.3\% and only a 2.7-percentage-point sim-to-real drop, while remaining robust to perturbations that substantially degrade pose-based and learned-fusion baselines.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.07534 — 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 2026-10-16T15:11:47.599Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).