Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
- 类型：arxiv
- 标识：2609.24815
- 链接：https://arxiv.org/abs/2609.24815
- 主分类：multimodal
- 形态：position
- TLDR：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
- 待LLM分类：否
- 来源文件：
- /inbox/tom/_candidates/2026-09-24-agent-rag-longcontext-candidates.json