RoboDreamer: 予測状態空間モデルによる先読み型ヒューマノイド歩行
RoboDreamer: Anticipatory Humanoid Locomotion with Predictive State-Space Models
観測マスキングと蒸留を用いた2段階教師-学生フレームワークで、不完全なセンシング下でも安定したヒューマノイド歩行を実現する。
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: Zhe Li, Yangyang Wei, Xichen Yuan, Zhenzhe Zhang, Weihao Yuan, Shanghang Zhang, Jianfei Yang
分類: cs.RO
原文アブストラクト
Humanoid locomotion requires control policies that remain stable under imperfect sensing while exploiting temporal context for consistent motion. We present RoboDreamer, a two-stage teacher--student framework that combines next-observation consistency with randomized continuous temporal masking. A teacher is first trained on clean observations, and a student is then distilled under masked recent observations, encouraging the policy to infer missing current information from history. At inference, the same masking interface is reused for implicit closed-loop action refinement and optional multi-step action chunking. Mamba is used as the temporal backbone, while matched ablations show that masking/distillation provides a substantial part of the gain and Mamba contributes additional tracking improvements with real-time latency. Experiments in IsaacLab, MuJoCo, and on a Unitree G1 demonstrate robust motion tracking under observation masking and successful real-world deployment.