Metraipolis › archive › dc_f247d244222a
VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation — arXiv:2611.03268
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.03268
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-03T11:44:51.921Z
- SHA-256 of the archived text
5fa8268115da22278d93ad3532374054e8286148bb16d9b4939d1273a86510ab- Stable URL of this page
https://metraipolis.com/documento/dc_f247d244222a
How to cite
VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation — arXiv:2611.03268 — arXiv (en), https://arxiv.org/abs/2611.03268 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f247d244222a (Metraipolis archive dc_f247d244222a, sha256 5fa8268115da22278d93ad3532374054e8286148bb16d9b4939d1273a86510ab)
BibTeX
@misc{dcf247d244222a,
title = {VerifLM: Physically Verified Image-Edit-Guided Goal Pose Generation for Robotic Manipulation — arXiv:2611.03268},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.03268},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f247d244222a; sha256 5fa8268115da22278d93ad3532374054e8286148bb16d9b4939d1273a86510ab},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03268. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Many manipulation goals are easier to visualize than to specify numerically through explicit geometric constraints. We present VerifLM, a framework that converts image-edited goal configurations into physically verified 6-DoF object poses for planning. Using an edited image, VerifLM recovers an initial relative pose between an active object and a passive object, then prompts a vision-language model to generate axis-wise sampling constraints and a task-specific validation program. Candidate poses are evaluated in a physics simulator, and the VLM selects the most task-consistent retained candidate. To operate without predefined object meshes or physical parameters, VerifLM reconstructs metric object geometry from RGB-D observations and constructs multiple hypothetical simulations with varying physics and geometry. Parallel-world validation evaluates candidates across geometry--physics variations and ranks them by the number of worlds in which they satisfy the validation program. We evaluate VerifLM on nine manipulation tasks. VerifLM achieves the highest task success on eight of nine tasks, with the largest performance gain on goals requiring precise orientation and contact relationships. 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/2611.03268 — 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 2026-11-03T11:06:52.319Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).