Metraipolis › archive › dc_02100c3fe15a
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI — arXiv:2609.24815
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24815
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:59:08.606Z
- SHA-256 of the archived text
0c93d0d403c039fca73e937a2d9183d590cc8f1a2d0d117564444fd9d10f2ffb- Stable URL of this page
https://metraipolis.com/documento/dc_02100c3fe15a
How to cite
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI — arXiv:2609.24815 — arXiv (en), https://arxiv.org/abs/2609.24815 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_02100c3fe15a (Metraipolis archive dc_02100c3fe15a, sha256 0c93d0d403c039fca73e937a2d9183d590cc8f1a2d0d117564444fd9d10f2ffb)
BibTeX
@misc{dc02100c3fe15a,
title = {Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI — arXiv:2609.24815},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24815},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_02100c3fe15a; sha256 0c93d0d403c039fca73e937a2d9183d590cc8f1a2d0d117564444fd9d10f2ffb},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24815. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and conventional simulators require labor-intensive construction. We present Uranus, a data-driven robot simulator built around a joint-trajectory-conditioned autoregressive diffusion model. Uranus offers three key capabilities: (1) streaming, open-ended rollout, which receives future joint-position trajectories online and autoregressively generates one latent frame per step, corresponding to four RGB frames, without a fixed horizon; (2) low-latency generation, achieving 24 FPS after inference optimization; and (3) scalable, extensible robot control, providing a unified interface for synchronized multi-view generation across diverse robot embodiments and camera configurations. We conduct comprehensive quantitative and qualitative evaluations on both in-distribution and out-of-distribution data, providing an objective assessment of Uranus and clearly identifying its current limitations. We release the code and model weights to empower the community with practical tools and insights. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24815 — 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 2026-10-07T20:29:01.949Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).