RIO: A Per vasive RFID-based Touch Gesture Interface
Swadhin Pradhan
UT Austin
swadhin@cs.utexas.edu
Eugene Chai
NEC Labs America
eugene@nec-labs.com
Karthikeyan Sundaresan
NEC Labs America
karthiks@nec-labs.com
Lili Qiu
UT Austin
lili@cs.utexas.edu
Mohammad A. Khojastepour
NEC Labs America
amir@nec-labs.com
Sampath Rangarajan
NEC Labs America
sampath@nec-labs.com
ABSTRACT
In this paper, we design and develop Rio, a novel battery-free touch
sensing user interface (UI) primitive for future IoT and smart spaces.
Rio enables UIs to be constructed using o-the-shelf RFID readers
and tags, and provides a unique approach to designing smart IoT
spaces. With Rio, any surface can be turned into a touch-aware
surface by simply attaching RFID tags to them. Rio also supports
custom-designed RFID tags, and thus allows specially customized
UIs to be easily deployed into a real-world environment.
Rio is built using the technique of impedance tracking: when a
human nger touches the surface of an RFID tag, the impedance
of the antenna changes. This change manifests as a change in the
phase of the RFID backscattered signal, and is used by Rio to track
ne-grained touch movement over both o-the-shelf and custom-
built tags. We study this impedance behavior in-depth and show
how Rio is a reliable UI primitive that is robust even within a multi-
tag environment. We leverage this primitive to build a prototype of
Rio that can continuously locate a nger during a swipe movement
to within 3
mm
of its actual position. We also show how custom-
design RFID tags can be built and used with Rio, and provide two
example applications that demonstrate its real-world use.
KEYWORDS
RFID; Touch Interface; Mutual Coupling; Impedance Tracking
1 INTRODUCTION
The future of IoT demands seamless, intuitive interaction between
users and smart devices. The vision is one of smart spaces (Fig. 1a),
where sensing and actuation interfaces are embedded into com-
mon objects, and can be controlled through touch, voice command,
or gestures. Examples of such input modalities include wireless
gesture sensing [
1
–
3
] which converts everyday body motions into
input, and capacitive touch [
4
,
5
] which recognizes physical actua-
tion between a user and the IoT device. Imagine if all these input
modalities operate without the need for any built-in battery or
power source, and are integrated into everyday devices such as
Permission to make digital or hard copies of all or part of this work for personal or
classroom use is granted without fee provided that copies are not made or distributed
for prot or commercial advantage and that copies bear this notice and the full citation
on the rst page. Copyrights for components of this work owned by others than the
author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or
republish, to post on servers or to redistribute to lists, requires prior specic permission
and/or a fee. Request permissions from permissions@acm.org.
MobiCom ’17, October 16-20, 2017, Snowbird, UT, USA
©
2017 Copyright held by the owner/author(s). Publication rights licensed to Associa-
tion for Computing Machinery.
ACM ISBN 978-1-4503-4916-1/17/10.. . $15.00
https://doi.org/.1145/3117811.3117818
cups, bowls, door knobs, mattresses, and built upon hardware so
cheap and simple that it can be installed or discarded easily. Any
physical space can be converted into a smart space simply by em-
bedding such input interfaces. The possibilities for such an input
primitive are clearly endless.
Kitchen
Living+room
ReaderAntenna
Reader
Tag-enabled
touch
-based+
toy
Tag-enabled
button
Reader+Antenna
Tag-enabled
Digital+piano
Tag-enabled
Dimmer+switch
Tag-enabled
button
(a) Rio-enabled home setup.
Swipe&Direction
Loop&Tag
(b) Custom Rio tag
for volume control.
Figure 1: Example applications of Rio.
Battery-Free Touch UI.
We explore the design of a battery-free
ne-grained touch gesture input interface using Radio Frequency
IDentication (RFID) technology. RFIDs provide a low-cost, battery-
free communication platform and have been used to develop sens-
ing, activity recognition and localization solutions [
6
–
11
]. Among
these notable works, machine learning techniques using the PHY-
layer features of both o-the-shelf [
8
] and custom-built tags [
9
]
have been successful in classifying several well-dened gestures
such as hand waving, touching and swiping. Other approaches such
as [
12
], have also designed custom backscatter capacitive measure-
ment circuits to detect touch events on the tag antenna.
We note that these works only detect isolated, coarse-grained
interactions and not ne-grained ones, such as the path traced by a
nger over the surface of a tag. Machine learning approaches [
8
,
9
]
also demand a high training overhead that limits its deployability.
For example, [
8
] uses 600 annotated interaction events to train and
evaluate its classier. and thus increase the cost and diculty of
large-scale integration into smart-spaces.
In this paper, we improve upon existing works by asking and
answering an important question: Can we use commercial o-the-
shelf (COTS) RFIDs as a battery-free, low-cost, ne-grained touch-
based user input primitive?
We design and build such an input primitive using COTS RFID
readers and tags. We call this primitive Rio, for
R
FID-based
I
nput
/
O
utput. Rio turns COTS RFID tags into touch interfaces: a user
interacts with Rio by touching the tag, and Rio accurately tracks
the touch as it moves over the surface of a tag. Rio uses a novel
technique of impedance tracking in backscatter communications.
The human body is conductive, with a capacitance on the order
Paper Session VI: Tag, You're It!
MobiCom’17, October 16-20, 2017, Snowbird, UT, USA
261
