Uranus：构建具身智能的下一代仿真基础设施
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
- D-Robotics（大疆创新）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
Uranus是一个基于关节轨迹条件自回归扩散模型的数据驱动机器人仿真器，支持流式展开、低延迟生成和统一多视角控制，为具身智能提供可扩展的仿真基础设施。
AI中文摘要：
可扩展的仿真对于机器人数据生成、策略训练、评估和安全迭代至关重要，然而真实世界交互成本高昂，且传统仿真器需要耗费大量人力进行构建。我们提出了Uranus，一个基于关节轨迹条件自回归扩散模型的数据驱动机器人仿真器。Uranus提供三项关键能力：（1）流式、开放式展开，它在线接收未来的关节位置轨迹，并自回归地每步生成一个潜帧，对应四个RGB帧，无需固定视界；（2）低延迟生成，经推理优化后达到24 FPS；（3）可扩展、可扩展的机器人控制，为不同机器人形态和相机配置下的同步多视角生成提供统一接口。我们在分布内和分布外数据上进行了全面的定量和定性评估，对Uranus进行了客观评估，并明确指出了其当前局限性。我们发布了代码和模型权重，以赋予社区实用工具和见解。
英文摘要：
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.
