tagoram: real-time tracking of mobile rfid tags to high...

Tagoram: Real-Time Tracking of Mobile

RFID Tags to High-Precision Accuracy

Using COTS Devices

Xiang-Yang Li

Lei Yang, Yekui Chen Chaowei Xiao, Mo Li, Yunhao Liu

Tagoram: Real-Time Tracking of Mobile

RFID Tags to High-Precision Accuracy

Using COTS Devices

Xiang-Yang Li

Lei Yang, Yekui Chen Chaowei Xiao, Mo Li, Yunhao Liu

Known Track 04.

Outline

State-of-the-art 02.

Technique Overview 03.

Implementation & Evaluation 06.

Unknown Track 05.

Motivation 01.

Pilot Study 07.

Other Research 08.

Motivation

Portal

Real-time Tracking

Access control

Livestock

Payment devices

Logistics

Passport Automobile immobilizers

RFID Technology

RFIDs

5-cent stickers to tag any and every object

Reader’s range is ~15m

billions of RFIDs were deployed for inventory management and object tracking

Battery-free RF stickers with unique IDs Imagine you can localize RFIDs to within 10 to 15 cm!

No more customer checkout lines

If we can locate RFID to within 10 to 15cm

RFID Proximity as Indicator!

RFIDs on

Basket,

goods

Automatic production

Imagine you can localize RFIDs to within 0.1cm to 1 cm!

Goal-line technology

Imagine you can localize RFIDs to within 0.1cm to 1 cm!

Human-computer interface

Imagine you can localize RFIDs to within 0.1cm to 1 cm!

Baggage sortation in airport

Imagine you can localize RFIDs to within 0.1cm to 1 cm!

Demonstration http://young.tagsys.org/tracking/tagoram/youtube

High-Precision RFID Tracking Using COTS Devices

30cm 40cm

Drawing in the Air

TrackPoint Deployed at Airports

Reader

Industrial

computer

State-of-the-art

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm

LANDMARC Lionel M. Ni

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm

LANDMARC Lionel M. Ni

[3] P.Nikitin, etal

Phase based spatial identification of uhf

rfid tags.

IEEE RFID 2010.

680mm

[2] C.Hekimian-Williams, elta

Accurate localization of rfid tags using

phase difference.

IEEE RFID 2010.

280mm

Diff based C. H.Williams

Spatial based P. Nikitin

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm [3] P.Nikitin, etal

Phase based spatial identification of uhf

rfid tags.

IEEE RFID 2010.

680mm

[2] C.Hekimian-Williams, elta

Accurate localization of rfid tags using

phase difference.

IEEE RFID 2010.

280mm

Diff based C. H.Williams

Spatial based P. Nikitin

[4] Salah Azzouzi, etal

New measurement results for the

localization of uhf RFID transponders

using an angle of arrival (aoa) approach

IEEE RFID 2011.

300mm

210mm

[5] R. Miesen etal.

Holographic localization of passive uhf

rfid transponders.

IEEE RFID 2011.

AOA based S. Azzouzi

Holographic R. Miesen

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm

[4] Salah Azzouzi, etal

New measurement results for the

localization of uhf RFID transponders

using an angle of arrival (aoa) approach

IEEE RFID 2011.

300mm

210mm

[5] R. Miesen etal.

Holographic localization of passive uhf

rfid transponders.

IEEE RFID 2011.

AOA based S. Azzouzi

Holographic R. Miesen

[6] Jue Wang, etal

Dude, where's my card?: RFID positioning

that works with multipath and non-line of

sight

ACM SIGCOMM 2013

110mm

12.8mm

[7] Jue Wang, etal

RF-compass: robot object manipulation

using RFIDs

ACM MobiCom 2013

PinIt Jue Wang

RF-Compass Jue Wang

680mm

[2] C.Hekimian-Williams, elta

Accurate localization of rfid tags using

phase difference.

IEEE RFID 2010.

280mm

[3] P.Nikitin, etal

Phase based spatial identification of uhf

rfid tags.

IEEE RFID 2010.

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm

[4] Salah Azzouzi, etal

New measurement results for the

localization of uhf RFID transponders

using an angle of arrival (aoa) approach

IEEE RFID 2011.

300mm

210mm

[5] R. Miesen etal.

Holographic localization of passive uhf

rfid transponders.

IEEE RFID 2011.

[6] Jue Wang, etal

Dude, where's my card?: RFID positioning

that works with multipath and non-line of

sight

ACM SIGCOMM 2013

110mm

27.6mm

[7] Jue Wang, etal

RF-compass: robot object manipulation

using RFIDs

ACM MobiCom 2013

[8] Tianci Liu, etal,

Anchor-free Backscatter Positioning for

RFID Tags with High Accuracy

IEEE INFOCOM 2014

128mm

[9] Jue Wang, etal,

RF-Idaw: Virtual Touch Screen in the Air

Using RF Signals

IEEE INFOCOM 2014

37mm

BackPos Tianci Liu

RF-IDRaw Jue Wang

[3] P.Nikitin, etal

Phase based spatial identification of uhf

rfid tags.

IEEE RFID 2010.

680mm

[2] C.Hekimian-Williams, elta

Accurate localization of rfid tags using

phase difference.

IEEE RFID 2010.

280mm

PinIt Jue Wang

RF-Compass Jue Wang

RFID Tracking & Localization State-of-the-art

2004 2014 2013 2011 2010

[1] Lionel M. Ni, Yunhao Liu, etal

LANDMARC: Indoor Location Sensing

Using Active RFID

Wireless Networks

1120mm

[4] Salah Azzouzi, etal

New measurement results for the

localization of uhf RFID transponders

using an angle of arrival (aoa) approach

IEEE RFID 2011.

300mm

210mm

[5] R. Miesen etal.

Holographic localization of passive uhf

rfid transponders.

IEEE RFID 2011.

[6] Jue Wang, etal

Dude, where's my card?: RFID positioning

that works with multipath and non-line of

sight

ACM SIGCOMM 2013

110mm

27.6mm

[7] Jue Wang, etal

RF-compass: robot object manipulation

using RFIDs

ACM MobiCom 2013

[8] Tianci Liu, etal,

Anchor-free Backscatter Positioning for

RFID Tags with High Accuracy

IEEE INFOCOM 2014

128mm

[9] Jue Wang, etal,

RF-Idaw: Virtual Touch Screen in the Air

Using RF Signals

ACM SigComm 2014

37mm

BackPos Tianci Liu

RF-IDRaw Jue Wang

WE ARE HERE

7mm

[3] P.Nikitin, etal

Phase based spatial identification of uhf

rfid tags.

IEEE RFID 2010.

680mm

[2] C.Hekimian-Williams, elta

Accurate localization of rfid tags using

phase difference.

IEEE RFID 2010.

280mm

State-of-the-art Techniques

RSS based Methods 1

RSS is not a reliable location indicator especially for UHF tags

RSS Orientation VS

Phase based Methods 2

PinIt (SIGCOMM 2013) RF-Compass (MobiCom 2013)

Needs to deploy dense reference tags

State-of-the-art Techniques

Summary of Challenges

Need mm-level localization accuracy achieved • especially for mobile tags.

Small overhead, COTS devices • infeasible for using many references for a tracking

system spanning a long pipeline.

Fast-changing environment • multipath reflection of RF signals • varied orientation of tags • Doppler effect

How Tagoram works? Overview the basic idea

Backscatter Communication

COTS RFID Reader

0.0015 radians (4096 bits)

Problem definition

Surveillance region

Reader antenna

Bird’s Eye View of Tagoram

Surveillance region

Reader antenna

Tagoram

Controllable Case Case 1.

Uncontrollable Case Case 2.

Movement with

Known Track Controllable case

Trajectory

Track

Track vs. Trajectory

A function of time–space relationships

A function of geometric relationships

VS

Virtual Antenna Array

Conveyor

Inverse Synthetic Aperture Radar

Initial

position

RF Hologram

How to define the likelihood?

The key is

RF Hologram

Naïve Hologram

Augmented Hologram

Differential Augmented Hologram

Thermal noise

Device diversity

Naïve Hologram

The real signal

The theoretical signal

A virtual interfered signal

Naïve Hologram

Virtual interfered signal

Sum of all signals

Naïve Hologram

Real axis

Imaginary axis

Naïve Hologram

Real axis

Imaginary axis

Naïve Hologram

High PSNR

Influence from Thermal Noise

Experiment Observations

CDF Modeling

How to deal with thermal noise?

Augmented Hologram

Augmented Hologram

A probabilistic weight

Augmented Hologram

Ground truth Result

Shift

scattered

What is missing again? Tags are different!

Tag diversity

Influence from Tag Diversity

Experiment

Observations

Random test

Modeling

At same position

Tag diversity

Pass KS-test to be verified over a uniform distribution with 0.5 significant level.

How to eliminate tag diversity?

Differential Augmented Hologram

Differential Augmented Hologram

Using difference of difference of phase values

Differential Augmented Hologram

Result

Ground truth

How to achieve the real-time?

Incremental computations

Saving Computations in Spatial Domain

Observation: The computations on blue pixel (low level PSNR) are totally wasted

Movement with

Unknown Track Uncontrollable case

Overview

Estimating Speeds,

Fitting tag’s trajectory

1

Selecting the optimal trajectory 2

Observations

Fitting tag’s trajectory

More complicate cases are discussed in our paper.

Fitting Tag’s Trajectory

Fitting the speed using NLS

Fitting Tag’s Trajectory

Trajectory

Speed Chain

Selecting the Optimal Trajectory

Unknown!

Implementation & Evaluation Purely based on COTS devices

Hardware & Software Introduction

ImpinJ R420 reader.

4 directional antennas

Reader Tag

Alien 2 × 2 Inlay

Alien Squiggle Inlay

Software

EPCglobal LLRP

Java

Linear Track

• A toy train on which a tag is attached.

• The system triggers the camera to take a snapshot on the train when firstly read.

• A camera is installed above the track to capture the ground truth.

Tracking Accuracy in Linear Track

DAH

Impacts of frequency and orientation

Both frequency and orientation take limited impacts on tracking accuracy.

Impact of frequency Impact of orientation

Real-time evaluation

Read-time Accuracy vs. Real-time

100 reads (~ 3.3s)

Impact of distance

No obvious pattern between distance and accuracy

Controllable Case with Nonlinear Track

• The track’s internal diameter is 540mm

Nonlinear track

DAH

Under Uncontrollable Case

A median of 12.3cm accuracy with a standard deviation of 5cm ---- better method proposed later, with about 1cm accuracy

Pilot Study In two airports

TagAssist: RFID assisted baggage sortation

Automatic Track & Check Service Collaborated with Hainan Airline

Where baggage lost?

Main factors to baggage loss

Relevant to baggage tracking

Current workflow – Manual sortation

Sortation carousel Sorting baggage

It is error-prone step to find the baggage from the carousel in manual sortation.

How to assist sorter quickly find and sort baggage?

Step 1: Upgrade Printer

We upgraded the tag printer by embedding a module of RFID reader in printer and an inlay inside each baggage tag.

Step 2: TrackPoint

Reader

Industrial

computer

Step 3: Visualization

Pilot site

Beijing Capital International Airport

Sanya Phoenix International Airport

Setup

• Each airport contains 5 TrackPoints, 4 visualization screens, and 22 RFID Printers.

• The two-year pilot study totally spent more than $600,000

Setup

•Consumed 110,000 RFID tags.

• Involved 53 destination airports, 93 air lines, and 1,094 flights.

Tracking Accuracy

Tagoram achieves a median accuracy of 6.35cm in practice.

Efficiency Improvement

Sorting carousel

Tagoram decreases the mean distance by 30%.

Tolerance to multipath

Tagoram has strong tolerance to multipath effect

Top four multipath cases Tracking accuracies

Other Research

88

OceanSense GreenOrbs CitySee

Networking observations

ZIMO:

Coexistence

Capacity: Large

scale

CitySee System (2011--)

Sensor nodes, mesh routers

90

Cyber Physical Systems

Cognitive Radio Networks

92

Capacity of Large Scale Networks

Our iGaze Glasses

Acknowledgments

PhD Students (alumni 10)

96

UNCC GSU Google W. Oregon

Tsinghua Motorola financial

financial

UT Dallas Toledo

Current PhD Students

97

MS Students

98

Students

99

100

100

Demo Video

Airport Video

Thank you !

Xiang-Yang Li Professor, IIT, USA

www.cs.iit.edu/~xli

xli@cs.iit.edu

Influences from other factors

1

2 Why tolerate NLOS?

Why tolerate Doppler effect?