Metraipolis › archive › dc_776fbc60b797

Asynchronous Robot Policies — arXiv:2611.05155

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.05155
License (as archived)
CC0-1.0
Archived
2026-11-04T21:40:22.222Z
SHA-256 of the archived text
dc4d93bb87fcb5619ff4e1b2b93d858174feddf61a6f4500399c855b8b3d751d
Stable URL of this page
https://metraipolis.com/documento/dc_776fbc60b797

How to cite

Asynchronous Robot Policies — arXiv:2611.05155 — arXiv (en), https://arxiv.org/abs/2611.05155 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_776fbc60b797 (Metraipolis archive dc_776fbc60b797, sha256 dc4d93bb87fcb5619ff4e1b2b93d858174feddf61a6f4500399c855b8b3d751d)
BibTeX
@misc{dc776fbc60b797,
  title = {Asynchronous Robot Policies — arXiv:2611.05155},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.05155},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_776fbc60b797; sha256 dc4d93bb87fcb5619ff4e1b2b93d858174feddf61a6f4500399c855b8b3d751d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.05155. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Scaling vision-language foundation models has significantly advanced generalist robot manipulation, but the increased model scale introduces computational latency that degrades real-time physical reactivity. Existing Vision-Language-Action (VLA) architectures execute high-level semantic reasoning and action ex- ecution sequentially within the primary control loop, creating a fundamental tension between semantic-reasoning capability and robot agility. To address this, we propose Asynchronous Robot Policy (ARP), an architectural framework that decouples semantic reasoning from low-level action generation using asynchronous processes operating at independent frequencies. In ARP, a high-capacity Vision-Language Model (VLM) asynchronously updates a semantic memory at low fre- quency, while a lightweight Vision-Action Expert, conditioned on this semantic memory, generates robot actions at a much higher control frequency. Such a formulation, enables having a fast perception-action loop without compromising on the semantic capability. To overcome asynchronous memory staleness, ARP trains the vision-action expert on the semantic staleness and execution delay, with temporally mismatched observation across processes. On Franka manipulation tasks, ARP achieves an 18% higher success rate and 20% less time need for execution in quasi-static setups, while 3-5 times baseline performance in dynamic simulation environments. Furthermore, ARP enables operating the VLM at 10 times lower than its nominal frequency with no significant performance loss making it much more efficient than the baseline. These results highlight the architectural advantages of modeling robot policies as asynchronous processes, enabling real-world reactive deployment without sacrificing the scale of foundation models.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.05155 — 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 2026-11-04T21:35:49.710Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).