Metraipolis › archive › dc_fa260043e075
SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion — arXiv:2610.41844
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41844
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T05:05:48.620Z
- SHA-256 of the archived text
dba6ba798f04808f4b4010935b2206508611974a6228f064ea26e4b409b86402- Stable URL of this page
https://metraipolis.com/documento/dc_fa260043e075
How to cite
SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion — arXiv:2610.41844 — arXiv (en), https://arxiv.org/abs/2610.41844 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fa260043e075 (Metraipolis archive dc_fa260043e075, sha256 dba6ba798f04808f4b4010935b2206508611974a6228f064ea26e4b409b86402)
BibTeX
@misc{dcfa260043e075,
title = {SketchMate: Agentic Geometric Reasoning for Zero-Shot Precision Insertion — arXiv:2610.41844},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41844},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fa260043e075; sha256 dba6ba798f04808f4b4010935b2206508611974a6228f064ea26e4b409b86402},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41844. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Inserting an unseen part requires sub-millimetre precision and the correct orientation of keyed features. Current zero-shot agentic manipulation methods built on vision-language models (VLMs) produce spatial outputs that are far too coarse for this. We propose to let a VLM build a sketch model of the task, i.e., a few geometric primitives and two mate frames, which a VLM agent measures with geometric tools in multi-view depth and which a standard planner and compliant controller execute. Because a sketch describes the parts independently of their placement, the robot needs to build it only once per task. A sketch memory stores each agent run and transfers the stored sketch to later placements by point-cloud registration, so that the VLM is called only for unfamiliar parts. After grasping the part, the robot inspects both mating faces at close range and corrects the sketch by shape matching. On 69 simulated insertion episodes, our method inserts 88% of the parts at the assembled pose in a strict kinematic test, while ReKep and MOKA with the same VLM insert none. On new placements of eight tasks, reusing one stored run inserts as many parts as calling the agent in each episode, and it produces the sketch in 3.4 s instead of about 90 s. 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/2610.41844 — 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 2026-11-02T04:49:28.228Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).