非一様時間スケジューリングと密ジャンプ積分によるロボット政策のフローマッチング
Dense-Jump Flow Matching with Non-Uniform Time Scheduling for Robotic Policies: Mitigating Multi-Step Inference Degradation
フローマッチング政策の推論時における多段積分の性能劣化を分析し、訓練時の非一様時間スケジューリングと推論時の密ジャンプ積分を提案して最大23.7%の性能向上を達成した。
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: Zidong Chen, Zihao Guo, Peng Wang, ThankGod Itua Egbe, Yan Lyu, Chenghao Qian
分類: cs.RO, cs.AI
原文アブストラクト
Flow matching has emerged as a competitive framework for learning high-quality generative policies in robotics; however, we find that generalisation arises and saturates early along the flow trajectory, in accordance with recent findings in the literature. We further observe that increasing the number of Euler integration steps during inference counter-intuitively and universally degrades policy performance. We attribute this to (i) additional, uniformly spaced integration steps oversample the late-time region, thereby constraining actions towards the training trajectories and reducing generalisation; and (ii) the learned velocity field becoming non-Lipschitz as integration time approaches 1, causing instability. To address these issues, we propose a novel policy that utilises non-uniform time scheduling (e.g., U-shaped) during training, which emphasises both early and late temporal stages to regularise policy training, and a dense-jump integration schedule at inference, which uses a single-step integration to replace the multi-step integration beyond a jump point, to avoid unstable areas around 1. Essentially, our policy is an efficient one-step learner that still pushes forward performance through multi-step integration, yielding up to 23.7% performance gains over state-of-the-art baselines across diverse robotic tasks.
