Uranus: a next-generation simulation environment for robots
Uranus is a data-driven robot simulator built on a joint-trajectory-conditioned autoregressive diffusion model. Three capabilities stand out: open-ended streaming that takes future joint positions online and generates one latent frame, meaning four RGB frames, per step; 24 frames per second after inference optimization; and a single interface offering synchronized multi-view generation across different robot embodiments and camera configurations. Evaluation covers long-horizon interaction, consistency between simulated and real execution, and generalization to unseen scenes. The code and model weights have been released.
Sources
- arXiv, “Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI”, (arxiv.org)
- D-Robotics (GitHub), “Uranus-OSS”, code and model weights repository for Uranus (github.com)
About this story
This story was posted on Instagram by @jarrus.tech on Sept. 28, 2026.
Spotted an error in this story? [email protected] · Instagram
Short link: thejarrus.com/en/uranus-simulator
This story in Turkish: Uranus: robotlar için yeni nesil bir simülasyon ortamı önerildi
On the same topic
Robot tests: even the best model completed only 19% of 84 robot tasks, and 63 tasks were solved by no model
In RobotWorld, a benchmark released October 7, the top model, GPT-6 Astra, completed only 16 of 84 simulated robot tasks; no model solved 63 of the tasks.
OpenAI’s image model posts a near-perfect score on text-dense images
On UltraText Bench, a dense-text test led by Westlake University, OpenAI’s GPT Image 2 ranked first of 24 configurations with 99.35 out of 100.
AWS adds Chinese lab Z.ai’s GLM 5.3 model to Amazon Bedrock
AWS added GLM 5.3, a 753-billion-parameter model from Beijing-based Z.ai (formerly Zhipu AI), to Amazon Bedrock for eligible enterprise customers on October 5.