| title | Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI |
|---|---|
| authors | Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai, Dongxiao Mao, Baicheng Li, Yue Zhang, Wei Sui |
| date | 2026-09-23 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2609.24815 |
| affiliation | D-Robotics |
| upvotes | 9 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | 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. |
cite
@misc{qin2026uranus,
title={Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI},
author={Wenkang Qin and Yukun Zhou and Noah Shen and Jisong Cai and Dongxiao Mao and Baicheng Li and Yue Zhang and Wei Sui},
year={2026},
eprint={2609.24815},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2609.24815}
}