ppt - Northwestern Networks Group

Vision-aided Landmark Routing and
Localization
Aaron Ballew
Aleksandar Kuzmanovic
C. C. Lee
Shiva Srivastava
Nikolay Valtchanov
Northwestern University, Evanston IL, USA
Dept. of Electrical Engineering and Computer Science
July 4th 2012
Aaron Ballew – IMIS, July 4th 2012
Indoor GPS
● Many facilities publish free floor plans online
Hyatt
Regency
O’hare
2
Aaron Ballew – IMIS, July 4th 2012
RF-derived approaches
● Triangulation
■ Delay, Angle, RSSI
● RF Signatures
■ Beacons
■ Impulse response
3
Aaron Ballew – IMIS, July 4th 2012
Use logic
● What happens in practice?
● A person reports what they see
● Take advantage of relationships among identifiable features of a room
● Absolute precision is not as important as a person comprehending
where he is
Olives
Olives
Wine
Self-Serve Counter
4
Aaron Ballew – IMIS, July 4th 2012
Important Definitions
●
Isovist: The visible area from a location’s perspective
■
■
Vi,j = {…}, set of coordinates visible from point (i,j)
V’i,j = {…}, set of coordinates invisible from point (i,j)
G
B
Isovists
G, B, and R
R
●
●
Feature: An identifiable landmark, e.g. cash register, bathroom, elevator…
Feature Vector: [f1 f2…fh], where fi Î{0,1}
■
■
●
fi == 1, fi is visible
fi == 0, fi is invisible
Region: Subset of coordinates sharing an identical feature vector
5
Aaron Ballew – IMIS, July 4th 2012
A simple example: 3 features
●
If feature A ÎVi,j, then point (i,j) ÎVA
■
i.e. if you can see a feature, then that feature can see you.
User: I see A and B, but not C
[A B C’]
You are Here
●
In general, for all features fp reported visible, and all fq reported invisible:
■
Location
■
2h (or 2h-1) locatable regions, for h total features in the environment
6
Aaron Ballew – IMIS, July 4th 2012
4 features
●
In general, for all features fp reported visible, and all fq reported invisible:
■
Location
● 2h possible vectors, so locatable regions grow in O(2h)
■ Corollary: Average region size decreases as h increases
User: I see A and B, but
not C or D
[A B C’ D’]
● |region| = 11 < 2h-1 = 15
■ Conjecture: For h>3, there is no 2D arrangement of features that
generates all 2h-1 locatable regions
7
Aaron Ballew – IMIS, July 4th 2012
User error
● Mistakes happen
■
Type I Error: Report an invisible feature is visible
− Possible, but rare
− Example: confusing “stairs” with “escalator.”
■
Type II Error: Report a visible feature is invisible
− Not only possible, it’s probable
− Our study revealed ~50% hit-rate on noticing features
● Assume positive sightings are trustworthy, and negative
sightings are completely untrustworthy
■
■
Sacrifice all info gained from unsighted features
All information comes from accumulation of positive sightings
8
Aaron Ballew – IMIS, July 4th 2012
Avg. located area vs. h features
Exponential
& Perfect
Accumulative 2
to 5 reports
Accumulative
Accumulative up
full rangeto 5 reports
● Important result
■ The plausible range of operation (2:5 sightings) performs in line with the
unlimited range of operation
9
Aaron Ballew – IMIS, July 4th 2012
Finding your way
●
Model environment as a network
■
■
●
At each hop, report what you see
■
●
app recommends a new next hop
Only adjacent subset of features are
offered at each hop
■
●
nodes (features) and
links (intervisibilities)
Makes the list much smaller
If you don’t sight a feature, the link is
down
■
Ineligible as a next hop
10
Aaron Ballew – IMIS, July 4th 2012
Hop-by-Hop SPF Routing
● Measurements of Characteristic Distance and Infinite Paths
● The more sensitive behavior is infinite paths, not hop count
11
Aaron Ballew – IMIS, July 4th 2012
Hop-by-Hop SPF Routing
● Sharp transition where the graph is connected “almost surely”
● The threshold corresponds to
12
Aaron Ballew – IMIS, July 4th 2012
Characteristic dist. and Infinite paths
● Example of agreement between simulated random graph and a real graph
of a test location
● The more sensitive behavior is infinite paths, not hop count
Simulated Random Network h = 40, p = 0.25
Real Test Network h = 38, p = 0.283
13
Aaron Ballew – IMIS, July 4th 2012
Field Study
●
Large Hotel/Convention Center (with
permission)
■
■
h = 38 features
p = .283 edge density
●
10 volunteers with no prior knowledge
●
Test 1 – sighting features
■
■
●
Each subject tested from multiple
vantage points
Positive sightings rate pv = 0.496, with
90% confidence pv > 0.46
Test 2 – usability
■
■
Wayfinding task A  B
Tracked user experience
−
−
−
Willingness to use the tool
Ability to use the tool
Feedback & suggestions
14
Aaron Ballew – IMIS, July 4th 2012
User/App interaction
● Based on your input to Part I
■ I know where you are
■ More important – I know
what you see
Company
Website
● Knowing what you see, I can
NU Networks
Group
Internet
tell you to walk over to it
■
■
Application picks the best
“next hop” on the way to
the destination
Repeat this in a simple way
until the user is within
L.O.S. of destination
What do you see?
Check all that apply
Food Mart
Cash Register
Exit
Escalator
Submit
?
15
Aaron Ballew – IMIS, July 4th 2012
Conclusions
● More features in the environment gives better location
precision, even with the same number of sightings
● Constraining to 2:5 sightings behaves similarly to
unconstrained case, i.e. plausible tracks feasible
● Number of hops is less important than whether you get
there
● p*pv > (ln n)/n is an indication of high success rate
16
Aaron Ballew – IMIS, July 4th 2012
Vision-aided Landmark Routing and
Localization
Aaron Ballew
Aleksandar Kuzmanovic
C. C. Lee
Shiva Srivastava
Nikolay Valtchanov
Northwestern University, Evanston IL, USA
Dept. of Electrical Engineering and Computer Science
July 4th 2012
Aaron Ballew – IMIS, July 4th 2012