行動デノイジング:閉形式拡散ポリシーに着想を得た非線形行動制御の新視点
Behavioral Denoising: A New Perspective on Nonlinear Behavioral Control Inspired by Closed-Form Diffusion Policies
閉形式拡散ポリシーの重みが正則化行動制御問題の一意解であることを示し、外挿を制限しつつ近傍軌道データを組み合わせる学習不要のχ²射影行動デノイジングを提案した論文。
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: Lucas Y. Jia, John Z. Zhang, Zachary Manchester
分類: eess.SY
原文アブストラクト
Diffusion policies have become a dominant approach to imitation learning in robotics. Recent work suggests that, in the low-data regime, they largely retrieve or combine the demonstrated actions, which the closed-form diffusion policy does explicitly. This closely resembles behavioral control, where future inputs are formed as linear combinations of recorded trajectories. In this work, we make this connection precise: we show that the weights with which the closed-form diffusion policy combines the demonstrated actions are the unique solution of a regularized behavioral control problem. Building on this connection, we propose an algorithm, termed $χ^2$-projected behavioral denoising, which is a training-free method that combines nearby trajectory data with a limit on extrapolation when the data offer little support. It shows encouraging results on four nonlinear control tasks compared to recent nonlinear behavioral control methods. We hope that this connection offers a useful perspective for understanding both data-driven control and diffusion policies. Code and more visualizations can be found at https://github.com/RoboticExplorationLab/behavioral-denoising.
