projekt User location estimation by means of WLAN Carl-Friedrich-Gauss-Str Kamp-Lintfort Germany Dennis Vredeveld IMST GmbH IMST ipos

projekt 2 User location estimation by means of WLAN / DV Contents Location-aware applications Indoor positioning: IMST ipos Experimental testbed Deterministic and probabilistic approach Software design Summary Outlook

projekt 3 User location estimation by means of WLAN / DV Location-aware Applications Locate people and nearby resources Product location information Example: Metro Future Store, Rheinberg Tracking Who/what is close? Navigation How do I get there?

projekt 4 User location estimation by means of WLAN / DV = AP Experimental testbed IMST 1st floor StandardIEEE b # of AP‘s7 Dimensions69 x 22 m OSLinux/Windows Hardwarehp iPAQ Lucent ORiNOCO IMST ipos

projekt 5 User location estimation by means of WLAN / DV Experimental testbed (2) Example for 1 AP Colour indicates measured average signal strength Calibrated radio map Orientation matters

projekt 6 User location estimation by means of WLAN / DV ipos WLAN overview Determine signal strength from beacons received from „visible“ access points Average of k Nearest Neighbours in Signal Space (k- NNSS) Deterministic Data base contains averaged signal strength values Determine smallest Euclidean distance Probabilistic Data base contains histograms of signal strengths Determine largest joint probability Postprocessing (averaging, etc)

projekt 7 User location estimation by means of WLAN / DV Simplified example 3 visible AP‘s Only 1 NNSS used Table Room 117! Signal Strength Measurements WLAN IEEE b beacon

projekt 8 User location estimation by means of WLAN / DV Deterministic approach Data base with measured average values for each calibrated location: ss 1, ss 2,… ss n Average k NN to obtain location estimation Mobile station with real time signal strength measurements from n Access Points: ss 1 ’,… ss n ’ Nearest neighbours are calibrated values with minimal Euclidean distance in signal space:

projekt 9 User location estimation by means of WLAN / DV Probabilistic approach Data base with histograms instead of averages with Estimated joint probability: Assume AP‘s are independent:

projekt 10 User location estimation by means of WLAN / DV ipos system design wireless techn. dependent independent of wireless techn. Location estimation Display location Powerpoint GUI Building map HTML Control Interface Postprocessing / filtering Floorplan checker Sliding window average Location profile Kalman filtering Trajectory prediction... Data Distribution WLAN module Preprocessing Raw WLAN data CE1 LCF1 LCF = Location Calculation Filter Interface New technology module Raw... data Preprocessing CE1 LCF1 Raw UWB data Preprocessing CE1 LCF1 UWB module

projekt 11 User location estimation by means of WLAN / DV Technology dependent Technology independent Location calculation filter Location Estimation Raw data Data Collection Raw data Store3 Store1 Store2 Preprocessing/ Filtering Raw data A1A3 A2‘A1‘ Postprocessing Location Estimation P1 P2P3 P2‘P1‘ P4 Data Distribution Location Estimation Dist3 Dist2 Dist1 ipos data processing

projekt 12 User location estimation by means of WLAN / DV Example: user tracking

projekt 13 User location estimation by means of WLAN / DV Summary Use existing WLAN infrastructure Find best match of AP beacons‘ signal strength measurements to a calibrated radio map Realtime positioning with average error of 1-3 meter in testbed

projekt 14 User location estimation by means of WLAN / DV Outlook Identify and resolve error sources Influence of environmental changes (number of persons, etc) Differences between WLAN hardware Design and implement ipos-software Research into new data sources and calculation algorithms

projekt 15 User location estimation by means of WLAN / DV Questions?

projekt 16 User location estimation by means of WLAN / DV Thank you for your attention! ✉