拡散モデル方策に状態性を持たせるDiff-Control
Enabling Stateful Behaviors for Diffusion-based Policy Learning
拡散モデルベースの方策にベイズ的な状態性を導入し、一貫した行動生成とロバスト性を向上させる手法を提案した。
著者: Xiao Liu, Fabian Weigend, Yifan Zhou, Heni Ben Amor
分類: cs.RO
原文アブストラクト
While imitation learning provides a simple and effective framework for policy learning, acquiring consistent actions during robot execution remains a challenging task. Existing approaches primarily focus on either modifying the action representation at data curation stage or altering the model itself, both of which do not fully address the scalability of consistent action generation. To overcome this limitation, we introduce the Diff-Control policy, which utilizes a diffusion-based model to learn the action representation from a state-space modeling viewpoint. We demonstrate that we can reduce diffusion-based policies' uncertainty by making it stateful through a Bayesian formulation facilitated by ControlNet, leading to improved robustness and success rates. Our experimental results demonstrate the significance of incorporating action statefulness in policy learning, where Diff-Control shows improved performance across various tasks. Specifically, Diff-Control achieves an average success rate of 72% and 84% on stateful and dynamic tasks, respectively. Project page: https://github.com/ir-lab/Diff-Control
