Tube Diffusion Policy: Reactive Visual-Tactile Policy Learning for Contact-rich Manipulation

TL;DR

This paper introduces Tube Diffusion Policy (TDP), a reactive visual-tactile learning framework that enhances contact-rich manipulation by enabling rapid, adaptive responses through generative models and tube-based feedback control.

Contribution

TDP combines diffusion-based imitation learning with tube-based feedback control to improve reactivity and robustness in contact-rich manipulation tasks.

Findings

TDP outperforms state-of-the-art imitation learning methods on multiple benchmarks.

Real-world experiments demonstrate TDP's robustness under contact uncertainty and disturbances.

Action tube mechanism reduces denoising steps, enabling real-time control.

Abstract

Contact-rich manipulation is central to many everyday human activities, requiring continuous adaptation to contact uncertainty and external disturbances through multi-modal perception, particularly vision and tactile feedback. While imitation learning has shown strong potential for learning complex manipulation behaviors, most existing approaches rely on action chunking, which fundamentally limits their ability to react to unforeseen observations during execution. This limitation becomes especially critical in contact-rich scenarios, where physical uncertainty and high-frequency tactile feedback demand rapid, reactive control. To address this challenge, we propose Tube Diffusion Policy (TDP), a novel reactive visual-tactile policy learning framework that bridges diffusion-based imitation learning with tube-based feedback control. By leveraging the expressive power of generative models, TDP learns an observation-conditioned feedback flow around nominal action chunks, forming an action tube that enables fast and adaptive reactions during execution. We evaluate TDP on the widely used Push-T benchmark and three additional challenging visual-tactile dexterous manipulation tasks. Across all benchmarks, TDP consistently outperforms state-of-the-art imitation learning baselines. Two real-world experiments further validate its robust reactivity under contact uncertainty and external disturbances. Moreover, the step-wise correction mechanism enabled by action tube significantly reduces the required denoising steps, making TDP well suited for real-time, high-frequency feedback control in contact-rich manipulation.