Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

TL;DR

This paper introduces a portable visuo-tactile gripper and a cross-modal learning framework that enhances robotic manipulation by integrating visual and tactile data, leading to more precise and robust tasks in real-world settings.

Contribution

The work presents a novel lightweight tactile-enabled gripper and a cross-modal representation learning method that improves manipulation performance in diverse environments.

Findings

Enhanced accuracy in fine-grained tasks

Robustness to external disturbances

Effective multimodal policy learning

Abstract

Handheld grippers are increasingly used to collect human demonstrations due to their ease of deployment and versatility. However, most existing designs lack tactile sensing, despite the critical role of tactile feedback in precise manipulation. We present a portable, lightweight gripper with integrated tactile sensors that enables synchronized collection of visual and tactile data in diverse, real-world, and in-the-wild settings. Building on this hardware, we propose a cross-modal representation learning framework that integrates visual and tactile signals while preserving their distinct characteristics. The learning procedure allows the emergence of interpretable representations that consistently focus on contacting regions relevant for physical interactions. When used for downstream manipulation tasks, these representations enable more efficient and effective policy learning, supporting precise robotic manipulation based on multimodal feedback. We validate our approach on fine-grained tasks such as test tube insertion and pipette-based fluid transfer, demonstrating improved accuracy and robustness under external disturbances. Our project page is available at https://binghao-huang.github.io/touch_in_the_wild/ .