OntoNav: A Semantic Indoor Navigation System

1
OntoNav A Semantic Indoor Navigation System
C. Anagnostopoulos, V. Tsetsos, P. Kikiras, and
S. Hadjiefthymiades

• Pervasive Computing Research Group,
• Communication Networks Laboratory (CNL),
• Dept. of Informatics Telecommunications,
  University of Athens

1st Workshop on Semantics in Mobile Environments
- SME05 (in conjunction with MDM05) May 9 2005
Ayia Napa, Cyprus
2
Presentation Structure

• Introduction
• System Design
• Conclusions

3
Indoor Location Based Services

• Traditional LBS
• Navigation, find nearest POIs, etc.
• Based on geometric location modeling
• Semantic LBS
• Intelligent service provisioning based on
  ontological knowledge representation and hybrid
  location modeling
• Human-centered services, suitable for people with
  disabilities
• Can be deployed to pervasive environments

4
Motivation

• Complex and unknown built environments cannot be
  easily explored
• People with disabilities face additional
  difficulties and put increased effort when
  following paths that eventually become
  non-traversable
• Built environments are associated with rich
  semantics which may lead to intelligent services
  if exploited appropriately
• OntoNavs goal to assist the path selection and
  end-to-end guidance processes using semantic
  modeling techniques

5
Presentation Structure

• Introduction
• System Design
• Conclusions

6
OntoNav Architecture

• Navigation Service (NAV)
• Geometric Path Computation Service (GEO)
• Semantic Path Selection Service (SEM)

7
System Functionality
Building representation (graph)
Spatial DB
Graph creation algorithm
Feature Extraction
Building blueprints
Geometric path computation (graph traversal)
INO instances
Indoor Navigation Ontology (INO)
GEO
all walkable paths
User and destination locations
SEM
NAV
User profile (capabilities and preferences)
Best traversable path
8
Indoor Navigation Ontology (INO) I

• Represents complex built environments, along with
  user models, from a navigation perspective
• Imports concepts from indoor location ontology
• Building, Floor, Room, Corridor,
• Since no such well-established ontology exists,
  aggregation/merging and extensions of existing
  indoor location models are pursued
• INO currently undergoes a model-evaluate-reenginee
  r process

9
Indoor Navigation Ontology (INO) II
10
User profiles

• Describe the capabilities and preferences of
  users
• A user profile (UP) contains
• Physical navigation rules (e.g., wheelchair)
• Perceptual navigation rules (e.g., child)
• Routing preferences (e.g., calendar-driven)
• A user typically selects a predefined UP and
  further adjusts it
• UPs are implemented as sets of rules that use the
  INO vocabulary and are applied to INO instances
• e.g., if user x cannot walk and path p contains a
  vertical passage v of type stairs then p is
  excluded

11
NAV Service

• Provides the interface between end-users and
  OntoNav
• Receives user requests
• Retrieves user position and location of
  destination
• Handles path presentation issues

12
GEO Service

• Inputs (a) a planar graph that accumulates the
  floor sub-graphs, (b) user and destination
  locations
• Output all possible walkable paths
• Edgescorridor segments, verticesexits and
  passages (i.e., each location is reduced to a
  set of exits or passages)
• Performs a hierarchical clustering in the graph
  for more efficient path discovery
• Walkable paths are computed with a graph
  traversal algorithm, since no path can be
  excluded a priori
• Computational complexity might be a problem

13
SEM Service

• Inputs (a) user profile, (b) all walkable paths
• Output best traversable path (BTP) and its
  anchors
• The physical navigation rules and the routing
  preferences of the user profile are used for
  exclusion of non-traversable paths
• From the remaining paths, the shortest is the BTP
• The physical and perceptual navigation rules are
  applied to BTP in order to select the most
  appropriate anchors (landmarks) for its
  presentation
• E.g., for a blind or illiterate user,
  voice-enabled anchors should be selected along
  the BTP

14
Example GEO
Destination
5 walkable paths
15
Example SEM
Destination
2 traversable paths
BTP is not the shortest path
16
Implementation Issues

• OntoNav is currently in the development phase
  using
• Web Ontology Language (OWL-DL) - navigation
  ontology
• Semantic Web Rules Language (SWRL) - user
  profiles
• SweetRules v2.0 - SWRL rules engine
• Racer OWL reasoning engine
• PostGIS spatial database
• OntoNav is an advanced application in the
  Semantic Web domain with increased applicability
  in everyday life

17
Presentation Structure

• Introduction
• System Design
• Conclusions

18
Added Value of OntoNav

• A purely user-centric navigation system, that
  adheres to the Inclusive Design paradigm
• Based on a hybrid location model (geographic and
  semantic) that
• Enables more advanced interpretations of distance
  than the Euclidean one
• Introduces user-defined quality metrics to the
  path selection process
• Suitable for intelligent context-aware
  environments

19
Future Work

• Inference of user status for assistance during
  the navigation process
• e.g., identification of lost, wandering,
  stationary, or deviated users
• Decrease computational complexity
• GEO service integrates a graph traversal which is
  a greedy algorithm
• Further work bypass the GEO service and prune
  non-traversable paths using only the semantic
  model
• OntoNav URL http//p-comp.di.uoa.gr/projects/onto
  nav