R3D: 3Dポリシー学習の再考
R3D: Revisiting 3D Policy Learning
3Dポリシー学習の不安定性と過学習の原因を診断し、3Dデータ拡張の欠如とバッチ正規化の悪影響を特定。スケーラブルなトランスフォーマー型3Dエンコーダと拡散デコーダを組み合わせた新しいアーキテクチャを提案し、操作ベンチマークで最先端を達成した。
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: Zhengdong Hong, Shenrui Wu, Haozhe Cui, Boyi Zhao, Ran Ji, Yiyang He, Hangxing Zhang, Zundong Ke, Jun Wang, Guofeng Zhang, Jiayuan Gu
分類: cs.CV, cs.RO
原文アブストラクト
3D policy learning promises superior generalization and cross-embodiment transfer, but progress has been hindered by training instabilities and severe overfitting, precluding the adoption of powerful 3D perception models. In this work, we systematically diagnose these failures, identifying the omission of 3D data augmentation and the adverse effects of Batch Normalization as primary causes. We propose a new architecture coupling a scalable transformer-based 3D encoder with a diffusion decoder, engineered specifically for stability at scale and designed to leverage large-scale pre-training. Our approach significantly outperforms state-of-the-art 3D baselines on challenging manipulation benchmarks, establishing a new and robust foundation for scalable 3D imitation learning. Project Page: https://r3d-policy.github.io/
