1. Unsupervised Indoor Localization
No Need to WarDrive …
Unsupervised Indoor Localization
Duke University, USA
E-JUST, Egypt

2. Where am I in a hotel, mall, office, cruise ship?

3. Why not outdoor localization technology?
GPS
GPS satellite
Why not outdoor localization technology?

4. Periodic calibration needed
Wi-Fi
(x1,y1)
(x2,y2)
(x3,y3)
AP 3
AP 1: -65
AP 2: -50
AP 3: -80
AP 4: -85
AP 1: -60
AP 2: -62
AP 3: -55
AP 4: -50
AP 1: -90
AP 2: -90
AP 3: -53
AP 4: -50
AP 1: -90
AP 2: -90
AP 3: -53
AP 4: -50
AP 1: -65
AP 2: -50
AP 3: -80
AP 4: -85
AP 1: -60
AP 2: -62
AP 3: -55
AP 4: -50
AP 2
AP 4
AP 1
Periodic calibration needed

5. Installation and maintenance costs
Beacon
sound beacon
Bluetooth beacon
listener
Installation and maintenance costs

6. We do not want to rely on infrastructure
We want a scalable software solution

7. Infrastructure-less Localization
accelerometer
compass
gyroscope

8. Dead reckoning
estimated path
actual path

9. Charles Lindbergh landed in Paris from New York.
No GPS
He used dead reckoning
and obtained fixes from the stars.

10. Dead reckoning No stars indoors estimated path actual path
corrected path
actual path

11. What if we “see” through sensors? At first, we could not see any …
Magnetic fluctuation
What if we “see” through sensors?
At first, we could not see any …

12. Acceleration pattern
Pressure change

13. Cellular pattern

14. We use this core idea to design
UnLoc: Unsupervised Indoor Localization

15. We use this core idea to design
UnLoc: Unsupervised Indoor Localization
3 main design questions:
How to automatically detect landmarks
How to localize the landmarks
How to localize users

16. How to automatically detect landmarks

17. <location, sensor data>
Raw Sensor  Landmarks
<location, sensor data>
Rough estimate

18. Raw Sensor  Landmarks Clustering sensor space
<location, f1, f2, f3, …>
Feature
Extraction
<location, sensor data>

19. Raw Sensor  Landmarks Clustering sensor space
<location, f1, f2, f3, …>
<location, f1, f2, f3, …>
Feature
Extraction
<location, sensor data>

20. Raw Sensor  Landmarks Landmark Clustering sensor space
<location, f1, f2, f3, …>
Feature
Extraction
Landmark
<location, sensor data>

21. Landmarks from Multiple Sensors
sensor space
Inertial, Magnetic, Wi-Fi
Clustering
<location, f1, f2, f3, …>
Feature
Extraction
<location, sensor data>

22. Indoor environments have adequate landmarks.
Our Hypothesis
Indoor environments have adequate landmarks.

23. We have found “stars”!
estimated path
corrected path
actual path

24. But, wait … We assumed dead reckoning is not too bad …
But in reality it diverges poorly.
What happens then?

25. origin
landmark 1
landmark
Uncorrelated errors
landmark

26. origin
landmark 1
landmark 2
landmark

27. origin
landmark 1
landmark 2
landmark 3

28. origin
landmark 1
landmark 2
landmark 3

29. Growing landmarks gradually

30. Growing landmarks gradually

31. Recursive Algorithm using existing landmarks Dead Reckon User Location
Users’ motion traces
<time, sensor value>
User
Location
Error
Dead Reckon
using existing landmarks
Landmarks
Landmark
Location
Error
Unique Sensor
Fingerprint?
Find Landmark
Location
Update
Landmark list

32. Performance Experimentation on 8000 sq. meters
Shopping mall, ECE and CS buildings
(1.63m, 50%)

33. Indoor environments rich in landmarks
1.63m accuracy
No infrastructure cost
No calibration needed