ノイズ除去が再計画のタイミングを教える:フローベースロボットポリシーのためのノイズ除去分散適応チャンキング
Denoising Tells When to Replan: Denoising-Variance Adaptive Chunking for Flow-Based Robot Policies
フローベースのロボットポリシーにおいて、ノイズ除去過程の分散を監視し、安定した動作部分だけを実行して高分散の接触・精密動作前に再計画する適応的チャンキング手法DVACを提案した。
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: Xiangdong Feng, Yuxuan Cheng, Chen Shi, Boyao Han, Yuxuan Yan, Yitong Hong, Zhuotao Tian, Li Jiang
分類: cs.RO
原文アブストラクト
Action chunking has become a common inference strategy for flow-based robot policies, improving action coherence by modeling multi-step temporal dependencies in demonstrations. However, the execution horizon is still typically set as an empirical fixed value, overlooking that predictable free-space motions and precision-critical interaction phases often require different replanning frequencies. In this work, we first show that the denoising process of flow-based policies contains an intrinsic signal of task phases: clean-action estimates remain stable during predictable motion phases, but fluctuate more strongly around contact-rich or precision-sensitive operations. Motivated by this observation, we propose DVAC (Denoising-Variance Adaptive Chunking), a test-time method that adaptively determines how many actions to execute from each predicted chunk. DVAC measures the variance of clean-action estimates over the final denoising steps, executes the stable low-variance prefix, and replans before high-variance future actions are committed. To transfer across tasks and rollouts, DVAC further calibrates the threshold with a rolling estimate of the local variance scale. Experiments on LIBERO, RoboTwin, CALVIN, and real-world manipulation show that DVAC improves task success while reducing replanning frequency. With a $\pi_{0.5}$-based policy, DVAC improves LIBERO success from 94.75% to 98.00% and reduces replanning by 43.0%, while also yielding aggregate gains on RoboTwin and CALVIN and improving real-world execution efficiency.
関連論文
- AURA: ロボットポリシーのためのアクションゲート型メモリ(VRAM一定)ロボットポリシー
- チャンクベースロボットポリシーのための動的実行ホライズン予測ロボットポリシー
- ガイド付きストリーミング確率的補間ポリシーロボットポリシー
