Uranus: 身体性AIのための次世代シミュレーション基盤の構築
Uranus: Building the Next-Generation Simulation Infrastructure for Embodied AI
関節軌道条件付き自己回帰拡散モデルを用いたデータ駆動型ロボットシミュレータUranusを提案し、ストリーミング生成、低遅延、多様なロボット制御に対応した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Wenkang Qin, Yukun Zhou, Noah Shen, Jisong Cai, Dongxiao Mao, Baicheng Li, Yue Zhang, Wei Sui
分類: cs.RO, cs.AI
原文アブストラクト
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.
