Metraipolis › archive › dc_3aaaaf647533

Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim — arXiv:2609.33982

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.33982
License (as archived)
CC0-1.0
Archived
2026-10-07T23:55:09.725Z
SHA-256 of the archived text
1407df0aeae3e49e2233048fe5a1f850bf4a846555cb01e5a311e958dd56f29b
Stable URL of this page
https://metraipolis.com/documento/dc_3aaaaf647533

How to cite

Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim — arXiv:2609.33982 — arXiv (en), https://arxiv.org/abs/2609.33982 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3aaaaf647533 (Metraipolis archive dc_3aaaaf647533, sha256 1407df0aeae3e49e2233048fe5a1f850bf4a846555cb01e5a311e958dd56f29b)
BibTeX
@misc{dc3aaaaf647533,
  title = {Test-Time Spatial Reasoning for Robot Manipulation Using Generative Real-to-Sim — arXiv:2609.33982},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.33982},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3aaaaf647533; sha256 1407df0aeae3e49e2233048fe5a1f850bf4a846555cb01e5a311e958dd56f29b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33982. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spatial reasoning is fundamental to general robot intelligence, as it enables robots to complete long-horizon tasks involving multi-object interaction. We introduce Simify, a training-free, test-time framework that performs explicit spatial reasoning via massively parallel physics simulation. From a single RGB-D image of a scene, Simify reconstructs simulation-ready assets leveraging 3D generative models and vision-language models. Then given a task specified by a reward function (e.g., build the tallest tower), Simify launches thousands of parallel rollouts in simulation and performs an evolutionary search to optimize object arrangements, typically converging within seconds. We conduct quantitative experiments on real-robot hardware to demonstrate the ability of our framework to execute complex object rearrangement tasks end-to-end with previously unseen objects. Results show that our framework outperforms prior work on foundation models for spatial reasoning by effectively exploiting large-scale parallel simulation during inference, and also highlight the importance of complete and accurate geometry for successful sim-to-real transfer.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.CV).
Categorie arXiv: Robotics (cs.RO) ; Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2609.33982 — 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 2026-10-07T23:29:27.701Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).