Metraipolis › archive › dc_4d4aaadef861
Visuo-tactile Diffusion Policy for Robotic Manipulation with Auxiliary Tactile Dynamics Prediction — arXiv:2611.02677
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.02677
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T18:57:19.117Z
- SHA-256 of the archived text
b97055159517735c966d0ec9630cd295546506a0f00cb6b68044a969a9018483- Stable URL of this page
https://metraipolis.com/documento/dc_4d4aaadef861
How to cite
Visuo-tactile Diffusion Policy for Robotic Manipulation with Auxiliary Tactile Dynamics Prediction — arXiv:2611.02677 — arXiv (en), https://arxiv.org/abs/2611.02677 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4d4aaadef861 (Metraipolis archive dc_4d4aaadef861, sha256 b97055159517735c966d0ec9630cd295546506a0f00cb6b68044a969a9018483)
BibTeX
@misc{dc4d4aaadef861,
title = {Visuo-tactile Diffusion Policy for Robotic Manipulation with Auxiliary Tactile Dynamics Prediction — arXiv:2611.02677},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.02677},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4d4aaadef861; sha256 b97055159517735c966d0ec9630cd295546506a0f00cb6b68044a969a9018483},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.02677. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Long-horizon robotic assembly requires reliable perception and action across grasping, alignment, and insertion. Vision captures global object pose and scene context, where as fingertip touch provides local contact cues that are especially useful as contact states change. We present a visuotactile diffusion policy that combines four-step histories from two camera views and two fingertip tactile images to condition action-sequence generation. A recurrent temporal representation integrates recent observations from both modalities. To encourage it to capture how contact evolves under action, an auxiliary objective predicts fingertip-image changes two steps ahead from the temporal representation and demonstrated actions. This objective is used only during training and adds no inference-time computation. Across three independent training seeds in MuJoCo assembly experiments, the full model achieves an average success rate of $59.0\% \pm 2.6\%$, improving on the visual-only baseline ($42.7\% \pm 1.5\%$) by 16.3 percentage points. 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/2611.02677 — 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 2026-11-03T18:17:07.755Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).