ReSkin: versatile, replaceable, lasting tactile skins

TL;DR

ReSkin addresses the fragility and poor cross-sensor transfer of soft tactile skins by combining a magnetically actuated elastomer skin with a magnetometer array and data-driven models. A multi-sensor learning framework plus a self-supervised triplet loss enables generalization across skins and boards, while a lightweight self-calibration procedure adapts models to new skins with minimal unlabeled data. The approach achieves high localization accuracy and force sensing, remains inexpensive (<$30 per skin), and supports replaceable, versatile form factors from gloves to sleeves and dog footwear. This work could democratize tactile perception in robotics by enabling scalable, long-lasting tactile skins that are easy to replace and adapt. The demonstrated demonstrations across diverse applications attest to practical impact and potential for wide adoption.

Abstract

Soft sensors have continued growing interest in robotics, due to their ability to enable both passive conformal contact from the material properties and active contact data from the sensor properties. However, the same properties of conformal contact result in faster deterioration of soft sensors and larger variations in their response characteristics over time and across samples, inhibiting their ability to be long-lasting and replaceable. ReSkin is a tactile soft sensor that leverages machine learning and magnetic sensing to offer a low-cost, diverse and compact solution for long-term use. Magnetic sensing separates the electronic circuitry from the passive interface, making it easier to replace interfaces as they wear out while allowing for a wide variety of form factors. Machine learning allows us to learn sensor response models that are robust to variations across fabrication and time, and our self-supervised learning algorithm enables finer performance enhancement with small, inexpensive data collection procedures. We believe that ReSkin opens the door to more versatile, scalable and inexpensive tactile sensation modules than existing alternatives.

Figures (6)

• Figure 1: A) ReSkin is easy to fabricate and the size of a penny, enabling a wide range of applications. B) Robot gripper using tactile feedback from ReSkin sensors to hold a blueberry without squishing it. C) Dog shoe with an embedded ReSkin sensor; (inset) visualization of sensor measurements. D) Contact localization on a new ReSkin sensor using our self-supervised adaptation procedure. E) Contact localization on a ReSkin curated into a fabric sleeve as a 2in x 4in contiguous skin. F) ReSkin sensor as a fingertip sensor to record forces and contacts while folding a dumpling
• Figure 2: ReSkin is replaceable!
• Figure 3: A) Experimental setup for data collection with Dobot Magician, ATI Nano 17 (inset), and six sensor boards streaming to a control computer. B) Mold for curing elastomer along with magnet holders. C) Two types of circuit boards -- rigid and flexible -- designed to be used with ReSkin.
• Figure 4: Variation in magnetic field over time and across different sensors. Each tick on the x-axis corresponds to a component of the magnetic fields measured by the sensor. While the general properties of the individual sensors overlap, there is still obvious variation across the samples.
• Figure 5: Model performance with increasing number of interactions