BayesFP: フローベース方策のためのFeynman-Kacサンプリングによる事後推定
BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling
事前学習済みの拡散・フローマッチング方策を事前分布とし、推論時に与えられるコストを尤度として事後サンプリングすることで、安全制約やタスク目的を満たす軌道生成を行う再学習不要の推論時サンプラーを提案した。
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: Sreevardhan Sirigiri, Weiming Zhi, Fabio Ramos
分類: cs.RO
原文アブストラクト
Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives specified only at inference time. We formulate constrained trajectory generation for pretrained diffusion and flow-matching policies as Bayesian posterior sampling, with the learned demonstration distribution as a prior and an inference-time, cost-derived likelihood tilting it toward feasible, optimal trajectories. To sample from this posterior without any retraining of the base policy, we leverage the Feynman--Kac corrector framework, originally formulated for diffusion models, and extend it to deterministic flow-matching policies. The result is a unified, inference-time, retraining-free sampler for diffusion and flow policies. We validate the approach on pretrained Diffusion Policy, GR00T-N1.6, and $\pi_{0.5}$ checkpoints across simulated and real-world manipulation tasks, including planning around non-convex obstacles introduced at inference time, and show improvements over the base $\pi_{0.5}$ on zero-shot tasks.
