フローからワンステップへ：暗黙的最大尤度推定に基づく分布蒸留によるリアルタイムマルチモーダル軌道ポリシー
From Flow to One Step: Real-Time Multi-Modal Trajectory Policies via Implicit Maximum Likelihood Estimation-based Distribution Distillation
条件付きフローマッチングの専門家を暗黙的最大尤度推定で単一ステップの生徒モデルに蒸留し、多様な動作モードを保ちながらリアルタイムな閉ループ制御を可能にした。
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: Ju Dong, Liding Zhang, Lei Zhang, Yu Fu, Kaixin Bai, Zoltan-Csaba Marton, Zhenshan Bing, Zhaopeng Chen, Alois Christian Knoll, Jianwei Zhang
分類: cs.RO, cs.AI
原文アブストラクト
Generative policies based on diffusion and flow matching achieve strong performance in robotic manipulation by modeling multi-modal human demonstrations. However, their reliance on iterative Ordinary Differential Equation (ODE) integration introduces substantial latency, limiting high-frequency closed-loop control. Recent single-step acceleration methods alleviate this overhead but often exhibit distributional collapse, producing averaged trajectories that fail to execute coherent manipulation strategies. We propose a framework that distills a Conditional Flow Matching (CFM) expert into a fast single-step student via Implicit Maximum Likelihood Estimation (IMLE). A bi-directional Chamfer distance provides a set-level objective that promotes both mode coverage and fidelity, enabling preservation of the teacher multi-modal action distribution in a single forward pass. A unified perception encoder further integrates multi-view RGB, depth, point clouds, and proprioception into a geometry-aware representation. The resulting high-frequency control supports real-time receding-horizon re-planning and improved robustness under dynamic disturbances.
