location aware computing l.
Download
Skip this Video
Loading SlideShow in 5 Seconds..
Location-Aware Computing PowerPoint Presentation
Download Presentation
Location-Aware Computing

Loading in 2 Seconds...

play fullscreen
1 / 46

Location-Aware Computing - PowerPoint PPT Presentation


  • 154 Views
  • Uploaded on

Location-Aware Computing. John Krumm Microsoft Research Redmond, Washington, USA. Thank You. Toshio Hori Takeo Kanade Chie Nakamura. Digital Human Research Center. Location. Why Bother to Sense Location?. Find conference room near me Who is in this meeting with me?

loader
I am the owner, or an agent authorized to act on behalf of the owner, of the copyrighted work described.
capcha
Download Presentation

PowerPoint Slideshow about 'Location-Aware Computing' - sook


An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -
Presentation Transcript
location aware computing

Location-Aware Computing

John KrummMicrosoft ResearchRedmond, Washington, USA

thank you
Thank You
  • Toshio Hori
  • Takeo Kanade
  • Chie Nakamura

Digital Human Research Center

why bother to sense location
Why Bother to Sense Location?
  • Find conference room near me
  • Who is in this meeting with me?
  • Where are the people who are supposed to be here?
  • If I’m in conference room, don’t allow cell phone, alerts, or IM
  • How long will it take to get from here to next appointment?
  • Route planning in strange buildings
no really why bother
No Really, Why Bother?
  • Remind me when I’m near a certain customer
  • Where are my kids, buddies, colleagues?
  • Index my documents (email, photos) by location
  • Change default printer and network settings based on location
  • Electronic graffiti, e.g. “There’s a better Thai restaurant one block north.”
why not use gps
Why Not Use GPS?
  • Does not work indoors
  • Needs view of satellites
location sensing
Location Sensing

Rosum, promising but where is it going?

Indoor/outdoor, coverage spreading

Still a hard problem, can give much more than location (good & bad)

Hazas, Scott, Krumm, “Location-Aware Computing”, IEEE Computer Magazine, February 2004.

beyond location
Beyond Location

sensors → location → context

Patterson, Liao, Fox, Kautz, “Inferring High-Level Behavior from Low-Level Sensors”, 2003

Use GPS tracking to infer user’s mode of transportation as (car, bus, walk)

Sparacino, “Sto(ry)chastics: A Bayesian Network Architecture for User Modeling and Computational Storytelling for Interactive Spaces”, 2003

Use indoor location sensing in MIT museum to classify visitor into (greedy, busy, selective)

outline
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
video tracking
Video Tracking

EasyLiving Project

Steve Shafer

Barry Brumitt

Steve Harris

Brian Meyers

Greg Smith

Mike Hale

John Krumm

video tracking is very
Video Tracking Is Very …
  • … accurate (centimeters)
  • … easy for user (no devices to carry)
  • … hard to set up (camera calibration)
  • … hard to get right (live demos still rare)
  • … CPU intensive (one PC per camera)
  • … intrusive

Research can solve

outline12
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
smartmovex
SmartMoveX

Microsoft Research’s entry into the active badge space (along with Xerox PARC, UW, Intel, AT&T Cambridge, MIT, etc.)

Receiver

Multiple receivers for position triangulation from signal strengths

Transmitter

Hardware: Lyndsay Williams (Microsoft Research Cambridge UK)

Software: John Krumm & Greg Smith (Microsoft Research Redmond)

receiver network

RX

RX PC

RX PC

RX

RX PC

DB PC

RX PC

RX

RX

Receiver Network
graph algorithm
Graph Algorithm
  • Compute path instead of single locations
  • Constrain path to allowable routes
  • Process with Hidden Markov Model (HMM – same as used for speech recognition)
  • Average error 3.05 meters

Constraints make things easier

smartmovex evaluation
SmartMoveX Evaluation

Good

  • Cheap hardware
  • Uses existing network infrastructure
  • Graph algorithm imposes natural constraints on paths

Needs Improvement

  • Privacy – depends on central server
  • Convenience
    • Extra device to wear
    • No display on device
  • Infrastructure – requires special receivers
outline17

Active Badge

Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
here i am coarse location
“Here I Am” – Coarse Location

With Steve Shafer (Microsoft Research)

here i am
“Here I Am”

Room Numbers Hand-Entered from Maps

802.11 Access Point Data

“Here I Am” returns position of strongest access point

outline20
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
location from 802 11 with l ocadio
Location from 802.11 with LOCADIO*

John Krumm & Eric Horvitz

Wi-Fi (802.11) access point

  • Mobile device measures signal strengths from Wi-Fi access points
  • Computes its own location

*Location from Radio

l ocadio fine location
LOCADIO - Fine Location

Radio survey to get signal strength as a function of position

l ocadio constraints
LOCADIO - Constraints

Make the client as smart as possible to reduce calibration effort

No passing through walls

No speeding

We know when you move

l ocadio results
LOCADIO - Results

Hidden Markov model gives median error of 1.53 meters

outline25
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
spot watch
SPOT Watch

traffic

weather

dining

movies

Commercial FM: transmit new data every ~2 minutes

Filter on watch to take what it wants

Watch displays “personalized” data

location sensitive features
Location-Sensitive Features
  • Nice to have
  • Local traffic
  • Nearby movie times
  • Nearby restaurants

Need to know location of device …

use fm radio signal strengths
Use FM Radio Signal Strengths

Scan signal strengths of 32 FM radio stations at 1 Hz

clustering approach

Sammamish

Woodinville

Redmond

Bellevue

Seattle

Clustering Approach

KMTT

Measured RSSI

A

B

C

KPLU

Input Power

  • But
  • Each watch scales signal strengths differently
  • Impractical to calibrate every watch
ranking approach
Ranking Approach

Any monotonically increasing function of signal strength preserves ranking

Redmond: KPLU < KMTT < KMPS

Bellevue: KMTT < KPLU < KMPS

Issaquah: KMTT < KMPS < KPLU

n radio stations  n! possible rankings

e.g. s = (12, 40, 38, 10)

r = (2, 4, 3, 1)

f = (f1, f2, f3, …, fn) = scanned frequencies

s = (s1, s2, s3, …, sn) = signal strengths

r = (r1, r2, r3, …, rn) = ranks of signal strengths

R(r) = permutation hash code = [0, 1, 2, … n!-1]

slide31
Test

Six suburbs and six radio stations

81.7% correct from 8 radio stations

avoid manual training
Avoid Manual Training

Seattle

KMPS 94.1 MHz

KSER 90.7 MHz

classify into grid cell
Classify Into Grid Cell
  • Find location in grid
  • Use predicted signal strengths to avoid manual training

≈ 8 kilometers average error

Summer intern Adel Youssef, U. Maryland

outline34
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
nearme
“NearMe”

Find people and things nearby

printers

people

reception desk

bathroom

conferencerooms

nearme basic idea
NearMe Basic Idea

802.11 Access Points

NearMe Server

nearme location
NearMe ≠ Location

Why compute absolute locations when you only need relative locations?

Tomasi, Kanade, “Shape and Motion from Image Streams: a Factorization Method”, 1991

Hightower, Fox, Borriello, “The Location Stack”, 2003

short circuit

Get location

Compare

Get location

Compare

Short Circuit

Get signal strengths

Get signal strengths

nearme screen shots
NearMe Screen Shots

1. Register with server

2. Report Wi-Fi signals

  • NearMe Server
  • SQL Server
  • .NET Web Service

3. Nearby people

4. Nearby printer(s)

nearme distance estimate
NearMe Distance Estimate

Estimate distance between two clients by comparing “Wi-Fi signatures”

15 meters rms error

Distance = f(n∩,ρs)

n∩ = number of access points seen in common

ρs = Spearman rank correlation of signal strengths

nearme applications
NearMe Applications

Device association (with Ken Hinckley, Microsoft Research)

Look up URLs of nearby people/things

Send email to people nearby

outline42
Outline
  • Introduction
  • Video Tracking
  • Active badge – SmartMoveX
  • Coarse Wi-Fi location – “Here I Am”
  • Fine Wi-Fi location – LOCADIO
  • SPOT Wristwatch Location – RightSPOT
  • Wi-Fi proximity – NearMe
  • “Longhorn” Location Service – Sensor Fusion
longhorn location service
“Longhorn” Location Service

“Longhorn” PC knows its location

GPS

your location

cell phone

Location Service

Wi-Fi

Bluetooth

other unanticipated

AN/PLR-3 Helmet-Mounted Radar

(I am not making this up.)

other location resolvers

longhorn location service44
Longhorn Location Service

Mgmt App (shell, netxp, OEM)

User Pref. Db.

LocMgmt API

User Resolver

Cache

App(Shell, OEM)

Notification Service

MasterResolver

Fuser

AD Resolver

Location API

AD

WinFS

PluginManager

Map Point Resolver

LocProv API

MapPoint Db / Serv.

Blue Tooth Provider

802.11 Provider

OEM Provider

Tracey Yao, PM

Florin Teodorescu, Dev

Vivek Bhanu, Dev

Jim Seifert, Test

Madhurima Pawar, Test

OEM Service

Wireless (802.11) Zero Configuration Service

BT Configuration Service

fusion
Fusion

Proper fusion of measurements depends on knowledge of uncertainty

Metric Measurements

Hierarchies

Weighted Hierarchical Voting

Kalman Filter