ReSkin: versatile, replaceable, lasting tactile skins

Despite various advancements of AI, it still struggles with dexterous manipulation. Current tactile sensing solutions lack multiple dimensions and fail to scale up.

A recent paper on arXiv.org proposes ReSkin – an inexpensive, replaceable, compact, versatile, and long-lasting tactile soft skin. It is composed of soft magnetized skin and a flexible magnetometer-based sensing mechanism.

Replacement of the tactile soft skin, ReSkin.

Replacement of the tactile soft skin, ReSkin. Image credit: arXiv:2111.00071 [cs.RO]

The deformation of the skin caused by normal/shear forces is read via distortions in magnetic fields. The distortions are mapped back to estimate the contact points and forces on the original skin using a learned machine learning model. A self-supervised adaptation procedure is created to further refine the models for new skins. Therefore, the skin is easily replaceable and can be used right away.

Several applications are proposed, such as grasping delicate objects, measuring forces exerted by dog feet, or measuring contact forces in the wild.

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.

Research paper: Bhirangi, R., Hellebrekers, T., Majidi, C., and Gupta, A., “ReSkin: versatile, replaceable, lasting tactile skins”, 2021. Link: https://arxiv.org/abs/2111.00071