https://any-skin.github.io

AnySkin: Plug-and-play Skin Sensing for Robotic Touch

Raunaq Bhirangi^1,2, Venkatesh Pattabiraman^1, Enes Erciyes^1, Yifeng
Cao^3, Tess Hellebrekers^4, Lerrel Pinto^1,
^1New York University, ^2Carnegie Mellon University, ^3Columbia
University, ^4Meta
Paper arXiv Request a sample! CAD Files Design Tool



Abstract

While tactile sensing is widely accepted as an important and useful
sensing modality, its use pales in comparison to other sensory
modalities like vision and proprioception. AnySkin addresses the
critical challenges of versatility, replaceability, and data
reusability, which have so far impeded the development of an
effective solution.

Building on the simplistic design of ReSkin, and decoupling the
sensing electronics from the sensing interface, AnySkin simplifies
integration making it as straightforward as putting on a phone case
and connecting a charger. Furthermore, AnySkin is the first sensor
with cross-instance generalizability of learned manipulation
policies.

This work makes three key contributions: first, we introduce a
streamlined fabrication process and a design tool for creating an
adhesive-free, durable and easily replaceable magnetic tactile
sensor; second, we characterize slip detection and policy learning
with a AnySkin sensor; and finally, we demonstrate the
generalizability of models trained on one instance of AnySkin to new
instances, and compare it with popular existing tactile solutions
like DIGIT and ReSkin.

AnySkin Figure 1

We present AnySkin, a skin sensor made for robotic touch that is easy
to assemble, compatible with different robot end-effectors and
generalizes to new skin instances.

AnySkin senses contact through distortions in magnetic field
generated by magnetized iron particles in the sensing surface. The
flexible surface is physically separated from its electronics, which
allows for easy replacability when damaged.

Policy Learning and Skin Replacability

In the videos below, you can see that learned Behavior Cloning
policies remain successful for three tasks even when the skin is
replaced.

Card Swiping

Plug Insertion

USB Insertion

Cross-Instance Generalization Results

Cross-instance Generalization

Slip Detection

AnySkin can be used to detect slippage of grasped objects. Our LSTM
model, trained with data from 30 daily objects, are able to predict
slip events with 92% accuracy.

Raw Signal Visualization

Sensing electronics consist of five magnetometers measuring magnetic
flux density in three axes. The following video shows a visualization
of the raw AnySkin signal:

Experiment Results

Comparison across sensors

Fabrication Process

AnySkin is made by mixing Smooth-On DragonSkin 10 Slow and MQFP-15-7
(25mm) magnetic particles in a 1:1:2 ratio, and curing it in the
two-part molds shown above. Cured skins are magnetized using a pulse
magnetizer. Our gripper tips' design files are open source and
available here.

Fabrication Process

This website is licensed under a Creative Commons
Attribution-ShareAlike 4.0 International License.

This means you are free to borrow the source code of this website, we
just ask that you link back to this page in the footer. Please
remember to remove the analytics code included in the header of the
website which you do not want on your website.