Metraipolis › archive › dc_497fb274659c
RoboMP-DINOv2: Prompts, Not Filters for Robust Robot Manipulation — arXiv:2609.25506
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25506
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T16:43:23.643Z
- SHA-256 of the archived text
56e3e53269ce6f92dbcfe11d3c0f1339655f369dae2fff6a74d3987b6fc914a5- Stable URL of this page
https://metraipolis.com/documento/dc_497fb274659c
How to cite
RoboMP-DINOv2: Prompts, Not Filters for Robust Robot Manipulation — arXiv:2609.25506 — arXiv (en), https://arxiv.org/abs/2609.25506 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_497fb274659c (Metraipolis archive dc_497fb274659c, sha256 56e3e53269ce6f92dbcfe11d3c0f1339655f369dae2fff6a74d3987b6fc914a5)
BibTeX
@misc{dc497fb274659c,
title = {RoboMP-DINOv2: Prompts, Not Filters for Robust Robot Manipulation — arXiv:2609.25506},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25506},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_497fb274659c; sha256 56e3e53269ce6f92dbcfe11d3c0f1339655f369dae2fff6a74d3987b6fc914a5},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25506. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Robot manipulation policies must generalize across visual shifts while preserving scene context relevant to action. General-purpose vision encoders are not tailored to visuomotor control, while object-centric approaches often use segmentation masks as hard filters that discard potentially useful context. We propose RoboMP-DINOv2 (Robotics Mask-Prompted DINOv2), a full-scene vision encoder that treats masks as spatial prompts rather than visibility filters. It extracts dense DINOv2 features from the full observation, injects learned region-specific embeddings at masked locations, and jointly contextualizes prompted and unprompted tokens for action prediction. We further introduce masked-region color randomization (MCR) to improve appearance robustness, yielding RoboMP-DINOv2-MCR. Across seven simulated manipulation settings, RoboMP-DINOv2 achieves 60.7% success under spatial shifts and 59.7% under scene clutter, compared with 50.7% and 41.0% for a DINOv2-based Diffusion Policy. Under unseen object colors, RoboMP-DINOv2-MCR achieves 72.5% success versus 35.1% for the strongest color-randomized baseline. Additional experiments and representation analyses show improved robustness while preserving behaviorally relevant scene information. Code is available at this https URL . Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-23 in cs.RO). Categorie arXiv: Robotics (cs.RO). Pagina del lavoro: https://arxiv.org/abs/2609.25506 — 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 2026-10-08T15:56:53.433Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).