Metraipolis › archive › dc_24de89af8ca4
Transferring the Intelligence of VLMs to Robotic Control — arXiv:2609.22966
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.22966
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:23:41.983Z
- SHA-256 of the archived text
ab0766b22c54eb4145067ef0372dcf80343da2d5e723bd325613f12f3a56de0d- Stable URL of this page
https://metraipolis.com/documento/dc_24de89af8ca4
How to cite
Transferring the Intelligence of VLMs to Robotic Control — arXiv:2609.22966 — arXiv (en), https://arxiv.org/abs/2609.22966 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_24de89af8ca4 (Metraipolis archive dc_24de89af8ca4, sha256 ab0766b22c54eb4145067ef0372dcf80343da2d5e723bd325613f12f3a56de0d)
BibTeX
@misc{dc24de89af8ca4,
title = {Transferring the Intelligence of VLMs to Robotic Control — arXiv:2609.22966},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.22966},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_24de89af8ca4; sha256 ab0766b22c54eb4145067ef0372dcf80343da2d5e723bd325613f12f3a56de0d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.22966. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Humans can seamlessly adapt to both physical and digital worlds, suggesting that while a digital-to-real gap exists in embodiment, environment and task, human intelligence itself may transfer across this gap. This naturally raises a fundamental question: can the intelligence of vision-language models (VLMs) similarly generalize from the digital world to the physical world for robotic control? We investigate this question through RoboDawn, a human-intuitive interface that exposes robotic control to an agentic VLM through a compact set of discrete translation, rotation, and gripper commands. Using this interface, the VLM controls a robot in a closed loop: it observes the current visual state, reasons about the next action, executes it, and adapts subsequent decisions to the resulting state. Furthermore, we introduce an in-context learning (ICL) scheme that uses a few demonstrations to ground the VLM in both interface usage and task-solving strategies. Experiments on RoboTwin 2.0 C2R and RoboDojo demonstrate that RoboDawn achieves strong performance without task-specific robot training. In the zero-shot setting, RoboDawn outperforms several strong policies trained on benchmarkspecific robot data, while a single in-context demonstration further yields substantial performance gains and establishes state-of-the-art (SOTA) results. On RoboTwin 2.0 C2R, the success rate increases from 53.2% zero-shot to 73.6% one-shot, exceeding the solid baseline {\pi}0.5 (46.0%). Similar gains are observed on RoboDojo, where success rate improves from 35.67% zero-shot to 47.17% one-shot. The same framework also transfers to real-world robots, performing block-in-basket and block stacking on Franka.
Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2609.22966 — 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 2026-10-09T21:59:59.514Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).