Enabling Stateful Behaviors for Diffusion-based Policy Learning

Published: 09 Apr 2024, Last Modified: 10 Apr 2024ICRA 2024: Back to the FutureEveryoneRevisionsBibTeXCC BY 4.0
Keywords: Diffusion model, imitation Learning, State-space Modeling
TL;DR: This paper introduces the Diff-Control policy, which utilizes a diffusion-based model to learn action representation from a State-Space Modeling viewpoint.
Abstract: 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
Submission Number: 13