28 PERVASIVE computing Published by the IEEE CS n 1536-1268/10/$26.00 © 2010 IEEE
L O CAT I O N - B A S E D S E R V I C E S
L
ocation is a core concept in most
pervasive computing systems.
Beyond simple uses such as pin-
pointing an individual’s position
or identifying a region’s occupants,
location is a key index for richer querying of an
individual’s or environment’s context.
Although at first glance a simple concept, lo-
cation information’s representation has many
forms and subtleties, each suited to particu-
lar application classes.1 To provide application
developers with easy access
to location information, we
must support different posi-
tioning systems with varying
data formats as well as fusion
algorithms to estimate posi-
tion from multiple readings.
We also need a data access ap-
proach that hides this complex-
ity and heterogeneity from the
developer. This problem has no
general solution, necessitating specific frame-
works for working with specific kinds of data.
To meet the needs of location-based applica-
tions, we’ve developed lightweight space and
sensing models and a set of extensible compo-
nents that support customization and emerging
technologies. The space model supports a range
of geometric and relative-spatial-positioning
descriptions found in the literature. The sens-
ing model abstracts over various types of posi-
tioning systems and incorporates the capture of
uncertainty, serving as a foundation on which
developers can apply sensor-fusion techniques.
Our programming framework, LOC8, sits atop
the space and sensing models, providing a rich
API for querying location data and exploring its
many representations.
Requirements
A location model should support location data
representations from different positioning tech-
nologies and extensible metadata descriptions.
Many well-known systems can report an enti-
ty’s coordinate or symbolic position, from GPS
and Active Badge to more recent systems such
as Ubisense and the fingerprint-based position-
ing system.2 Beyond these are less conventional
and less expensive methods of reporting an en-
tity’s location. For example, a Bluetooth spot-
ter, which can detect the presence of mobile
phones, PDAs, and laptops, might position a de-
vice within 10 meters of a known point. We can
use this information to infer the device owner’s
position.
Using a location model supporting a range of expressive representations
for spaces, spatial relationships, and positioning systems, the authors
created LOC8, a programming framework for exploring location data’s
multifaceted representations and uses.
Graeme Stevenson
and Juan Ye
University College Dublin
Simon Dobson
University of St. Andrews
Paddy Nixon
University College Dublin
LOC8: A Location
Model and Extensible
Framework for
Programming
with Location