暗黙的ドリフト方策：条件付き専門家幾何による一段階行動生成
Implicit Drifting Policy: One-Step Action Generation via Conditional Expert Geometry
拡散やフローマッチングに基づく生成行動ポリシーは反復サンプリングが遅いため、一段階生成を提案。訓練時のドリフト補正を明示的なベクトル場推定なしで取り込む暗黙的ドリフト方策(IDP)を導入し、2D・3D・実世界操作タスクで有効性を実証した。
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: Zemin Yang, Yaoyu He, Yiming Zhong, Yuhao Zhang, Xinge Zhu, Yao Mu, Qingqiu Huang, Yuexin Ma
分類: cs.RO, cs.AI
原文アブストラクト
Generative action policies based on diffusion or flow matching excel in behavior cloning, yet their iterative sampling is prohibitive for high-frequency robot control. While recent one-step formulations alleviate this latency, they inevitably discard the intermediate trajectory evolution that provides crucial action correction. Directly recovering this mechanism by explicitly estimating a training-time drifting field is mathematically ill-posed due to extreme conditional demonstration sparsity. We introduce Implicit Drifting Policy (IDP), a one-step imitation learning framework that brings the training-time correction of Drifting into policy learning without explicit vector field estimation. IDP extracts a conditional expert geometry from the local variation of observation-similar expert actions, and compares it against a global reference geometry to isolate condition-specific constraints. This local geometric structure adaptively weights a scalar potential objective. Combined with an expert-proximal terminal evaluation, IDP directly enforces manifold constraints on the one-step generator during training. Extensive evaluations across 2D, 3D, and real-world manipulation tasks show IDP effectively maintains adherence to valid action manifolds, improving upon explicit drifting methods and achieving competitive performance with strong one-step baselines.
