Tagoram: Real-Time Tracking of Mobile RFID Tags to High-Precision Accuracy Using COTS Devices

Tagoram: Real-Time Tracking of Mobile RFID Tags to High-Precision Accuracy Using COTS Devices Xiang-Yang Li Lei Yang, Yekui Chen, Xiang-Yang Li, Chaowei Xiao, Mo Li, Yunhao Liu Sep. 9, 2014

Tagoram: Real-Time Tracking of Mobile RFID Tags to High-Precision Accuracy Using COTS Devices Xiang-Yang Li Lei Yang, Yekui Chen, Xiang-Yang Li, Chaowei Xiao, Mo Li, Yunhao Liu Sep. 9, 2014

Outline 01. 02. 03. 04. 05. 06. 07. 08. Motivation State-of-the-art Overview Movement with known track Movement with unknown track Implementation & Evaluation Pilot Study Conclusion

Motivation

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! Goal-line technology

Demonstration http://young.tagsys.org/tracking/t agoram/youtube

High-Precision RFID Tracking Using COTS Devices Drawing in the Air 40cm 30cm

TrackPoint Deployed at Airports Reader Industrial computer

State-of-the-art

RFID Tracking & Localization State-of-the-art LANDMARC [1] Lionel M. Ni, Yunhao Liu, etal LANDMARC: Indoor Location Sensing Using Active RFID Wireless Networks Lionel M. Ni 1120mm 2004 2010 2011 2013 2014

RFID Tracking & Localization State-of-the-art LANDMARC [1] Lionel M. Ni, Yunhao Liu, etal LANDMARC: Indoor Location Sensing Using Active RFID Wireless Networks Lionel M. Ni 1120mm Spatial based [3] P.Nikitin, etal Phase based spatial identification of uhf rfid tags. IEEE RFID 2010. P. Nikitin Diff based [2] C.Hekimian-Williams, elta Accurate localization of rfid tags using phase difference. IEEE RFID 2010. C. H.Williams 680mm 280mm 2004 2010 2011 2013 2014

RFID Tracking & Localization State-of-the-art [1] Lionel M. Ni, Yunhao Liu, etal LANDMARC: Indoor Location Sensing Using Active RFID Wireless Networks 1120mm AOA based [4] Salah Azzouzi, etal New measurement results for the localization of uhf RFID transponders using an angle of arrival (aoa) approach IEEE RFID S. 2011. Azzouzi Spatial based [3] P.Nikitin, etal Phase based spatial identification of uhf rfid tags. IEEE RFID 2010. P. Nikitin Holographic [5] R. Miesen etal. Holographic localization of passive uhf rfid transponders. IEEE RFID 2011. R. Miesen Diff based [2] C.Hekimian-Williams, elta Accurate localization of rfid tags using phase difference. IEEE RFID 2010. C. H.Williams 680mm 280mm 300mm 210mm 2004 2010 2011 2013 2014

RFID Tracking & Localization State-of-the-art [1] Lionel M. Ni, Yunhao Liu, etal LANDMARC: Indoor Location Sensing Using Active RFID Wireless Networks 1120mm [2] C.Hekimian-Williams, elta Accurate localization of rfid tags using phase difference. IEEE RFID 2010. AOA based [4] Salah Azzouzi, etal New measurement results for the localization of uhf RFID transponders using an angle of arrival (aoa) approach IEEE RFID S. 2011. Azzouzi [3] P.Nikitin, etal Phase based spatial identification of uhf rfid tags. IEEE RFID 2010. 680mm Holographic [5] R. Miesen etal. Holographic localization of passive uhf rfid transponders. IEEE RFID 2011. R. Miesen PinIt [6] Jue Wang, etal Dude, where's my card?: RFID positioning that works with multipath and non-line of sight ACM SIGCOMM Jue 2013Wang RF-Compass [7] Jue Wang, etal RF-compass: robot object manipulation using RFIDs ACM MobiCom 2013 Jue Wang 280mm 300mm 210mm 110mm 12.8mm 2004 2010 2011 2013 2014

RFID Tracking & Localization State-of-the-art [1] Lionel M. Ni, Yunhao Liu, etal LANDMARC: Indoor Location Sensing Using Active RFID Wireless Networks 1120mm [2] C.Hekimian-Williams, elta Accurate localization of rfid tags using phase difference. IEEE RFID 2010. [4] Salah Azzouzi, etal New measurement results for the localization of uhf RFID transponders using an angle of arrival (aoa) approach IEEE RFID 2011. [3] P.Nikitin, etal Phase based spatial identification of uhf rfid tags. IEEE RFID 2010. 680mm [5] R. Miesen etal. Holographic localization of passive uhf rfid transponders. IEEE RFID 2011. PinIt [6] Jue Wang, etal Dude, where's my card?: RFID positioning that works with multipath and non-line of sight ACM SIGCOMM Jue 2013Wang RF-Compass [7] Jue Wang, etal RF-compass: robot object manipulation using RFIDs ACM MobiCom 2013 Jue Wang BackPos [8] Tianci Liu, etal, Anchor-free Backscatter Positioning for RFID Tags with High Accuracy IEEE INFOCOM 2014 Tianci Liu RF-IDRaw [9] Jue Wang, etal, RF-Idaw: Virtual Touch Screen in the Air Using RF Signals IEEE INFOCOM 2014 Jue Wang 280mm 300mm 210mm 110mm 27.6mm 128mm 37mm 2004 2010 2011 2013 2014

RFID Tracking & Localization State-of-the-art [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. [3] P.Nikitin, etal Phase based spatial identification of uhf rfid tags. IEEE RFID 2010. [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 BackPos [8] Tianci Liu, etal, Anchor-free Backscatter Positioning for RFID Tags with High Accuracy IEEE INFOCOM 2014 Tianci Liu RF-IDRaw [9] Jue Wang, etal, RF-Idaw: Virtual Touch Screen in the Air Using RF Signals IEEE INFOCOM 2014 Jue Wang [2] C.Hekimian-Williams, elta Accurate localization of rfid tags using phase difference. IEEE RFID 2010. 680mm [7] Jue Wang, etal RF-compass: robot object manipulation using RFIDs ACM MobiCom 2013 280mm 300mm 210mm 110mm 27.6mm 128mm 37mm 7mm 2004 2010 2011 2013 2014 WE ARE HERE

State-of-the-art Techniques 1 RSS based Methods Orientation VS RSS RSS is not a reliable location indicator especially for UHF tags

State-of-the-art Techniques 2 Phase based Methods PinIt (SIGCOMM 2013) RF-Compass (MobiCom 2013) Needs to deploy dense reference tags

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 ofrfsignals varied orientation of tags Doppler effect

How Tagoram works? Overview the basic idea

Backscatter Communication ❸ Continuous wave ❷ Double distance ❶ Battery free ❹ Device diversity

COTS RFID Reader 0.0015 radians (4096 bits) 0. 038mm accuracy Impinj Reader

Problem definition M N { θ 1,1, t 1,1, (θ 1,2, t 1,2 ), (θ 1,N, t 1,N )} { θ 2,1, t 2,1, (θ 2,2, t 2,2 ), (θ 2,N, t 2,N )} { θ M,1, t M,1, (θ M,2, t M,2 ), (θ M,N, t M,N )} Surveillance region Reader antenna Utilizing antennas locations, sampled phase values and timestamps to find out the tag s trajectory f(t)?

Tagoram Case 1. Controllable Case Case 2. Uncontrollable Case

Movement with Known Track Controllable case

Virtual Antenna Matrix Inverse Synthetic Aperture Radar A 1 A 1,1 A 1,2 A 1,3 A 1,4 Conveyor V f(t 0 ) A 2 A 2,1 A 2,2 A 2,3 A 2,4 Initial position

RF Hologram W x w,l W L L Surveillance region W L grids RF Hologram W L pixels

The key is How to define the likelihood?

RF Hologram Naïve Hologram Augmented Hologram Thermal noise Device diversity Differential Augmented Hologram

Naïve Hologram e Jθ The real signal A T A e Jh(A,X) The theoretical signal X A A virtual interfered signal ej(h A,X θ) X

Naïve Hologram Sum of all signals Virtual interfered signal

Naïve Hologram Imaginary axis Real axis e J(h X,A 1,1 θ 1,1 ) e J(h X,A 1,2 θ 1,2 ) e J(h X,A 4,3 θ 4,3 ) e J(h X,A 4,4 θ 4,4 ) If X is the initial location, the waves add up constructively.

Naïve Hologram Imaginary axis e J(h X,A 1,2 θ 1,2 ) e J(h X,A 1,1 θ 1,1 ) Real axis e J(h X,A 4,3 θ 4,3 ) e J(h X,A 4,4 θ 4,4 ) If X is not the initial location, the waves canceled out.

Naïve Hologram High PSNR

Influence from Thermal Noise 100 tags 0 ~40 920 926 MHz 70 30dbm Experiment Modeling Observations CDF θ N(μ, σ) varying with d σ = 0. 1 F(θ; μ, σ)

How to deal with thermal noise? Augmented Hologram

Augmented Hologram A probabilistic weight h X, A θ N(0, 0. 1) Probability of T A

Augmented Hologram Shift Ground truth Result scattered

Influence from Tag Diversity 70 tags 100 times At same position Experiment Modeling Observations Random test 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 the difference of phase values

Differential Augmented Hologram Ground truth Result

Movement with Unknown Track Uncontrollable case

Overview 1 2 Estimating Speeds, Fitting tag s trajectory Selecting the optimal trajectory

Implementation & Evaluation Purely based on COTS devices

Hardware & Software Introduction Reader ImpinJ R420 reader. Tag Alien 2 2 Inlay Software EPCglobal LLRP 4 directional antennas Alien Squiggle Inlay Java

Linear Track A mobile object is emulated via a toy train on which a tag is attached. A camera is installed above the track to capture the ground truth. The system triggers the camera to take a snapshot on the train when firstly read.

Tracking Accuracy in Linear Track 4 13 14 DAH Improve the accuracy by 48, 30, 28 and 8. 5 in comparison to RSS, OTrack, PinIt and BackPos.

Controllable Case with Nonlinear Track The track s internal diameter is 540mm The distance varies from 1m to 15m

Nonlinear track 7. 29 4. 98 2. 95 DAH

Under Uncontrollable Case Achieve a median of 12.3cm accuracy with a standard deviation of 5cm.

Pilot Study In two airports

Current workflow Manual sortation It is error-prone step to find the baggage from the carousel in manual sortation. Sortation carousel Sorting baggage

Our system: TrackPoint Reader Industrial computer

Tracking 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.

Provides real-time tracking of mobile tags with accuracy to mm-level. Limits almost all negative impacts. Multipath effect Doppler effect Thermal noise Device diversity Conclusion Not well-studied before Implemented purely based on COTS RFID products. Systematically evaluated under indoor environment and at two airports.

Questions? Thank you