Transcript Bluetooth Localization Poster

Indoor Localization using Bluetooth RSSI
For Context Resolution
Jason Tam
Objectives
◊
Localization Algorithm Flow
◊
Localize Bluetooth capable
smartphones indoors
◊
Use localization for more
novel context aware
grouping
Approach
◊
Download
Self MAC
Address
Other MAC
Address
◊
Upload to data server
Server Side
◊
Reconstruction
vs.
Truths
Issues
Simultaneous discovery
◊
50 unit spacing; σ = 5;
range = 100
RSSI
Estimate Distance
◊
◊
Using test conditions:
◊
Client Side
◊
Results
Download data
◊
This
◊
Many additional/missing
environmental factors
Identify Robust Quadrilaterals
Construct quad using
trilateration
Localize
Update GCRS
Merge on 3 Common Nodes
Translation
Rotation
Flip will be
unambiguous
Status / Future
◊
Localization alg done when
given distances
◊
RSSI to distance conversion
needs help
◊
Integration with machine
learning
Sources
Merge on 2 Common Nodes
Translation
Rotation
Merge only no
flip ambiguity
◊
[1] Indoor Location Using Trilateration Characteristics, B Cook, G
Buckberry, I Scowcroft, J Mitchell, T Allen, 2005
◊
[2] Robust Distributed Network Localization with Noisy Range
Measurements, David Moore, John Leonard, Daniela Rus, Seth Teller
MIT Computer Science and Artificial Intelligence Laboratory; 2004
Example Trilateration cases
http://summer.winlab.rutgers.edu/projects/wiki/2012/Projects/MobilityFirst/Context
WINLAB