=Paper=
{{Paper
|id=None
|storemode=property
|title=BDI Intelligent Agents for Augmented Exploitation of Pervasive Environments
|pdfUrl=https://ceur-ws.org/Vol-741/ID16_AmatoDiMartinoVenticinque.pdf
|volume=Vol-741
|dblpUrl=https://dblp.org/rec/conf/woa/AmatoMV11
}}
==BDI Intelligent Agents for Augmented Exploitation of Pervasive Environments==
https://ceur-ws.org/Vol-741/ID16_AmatoDiMartinoVenticinque.pdf
BDI Intelligent Agents for Augmented Exploitation of Pervasive Environments
Alba Amato, Beniamino Di Martino, Salvatore Venticinque
Dep. of Information Engineering
Second University of Naples - Aversa, Italy
Email: {alba.amato,salvatore.venticinque}@unina2.it
beniamino.dimartino@unina.it
Abstract—Agents based application should be able to use personalized information. Personalization and adaptation are
pervasive sensors as their own perceptors in order to let the a key concept in this field because it is really difficult for
users benefit of context awareness in services exploitation and a mobile tourist in a dynamic environment to browse and
in order to make mobile services really useful and profitable.
The agents described in our approach adapt themselves in search desired information and services. In this kind of
response to a changing environment and are able to respond contests, personalization and adaptation allow the system to
differently, creating entirely new plans, and thus changing became a sort of intelligent personal assistant characterized
their own behavior depending on their past experience. We of being proactive and autonomously providing suggestions
present a framework that implements the model to supports and support.
experts in the domain of the Cultural Heritage to augment the
archaeological site with a set of multimedia contents which are II. BDI AGENTS IN PERVASIVE ENVIRONMENTS
delivered by intelligent services to the visitors in order to guide
their tour and to enhance their perception of the reality. The agent-oriented paradigm is highly suited for applica-
tions dealing with complex and dynamic environments, that
Keywords-Intelligent Agents; BDI Agents; Context Awarness;
Mobile Augmented Reality are usually unpredictable (it is not possible to predict the
future state of the environment), unreliable (the action of
I. I NTRODUCTION the agent can fail because of factors beyond its control).
Pervasive environments are really dynamic and enable In [2] an agent is defined as a computer system that
software applications to access to large amounts of informa- is situated in some environment, and that is capable of
tion from anywhere. However, context awareness involves autonomous action in this environment in order to meet its
capturing and making sense of imprecise and sometimes design objectives. An intelligent agent is further required to
conflicting data and uncertain physical worlds [1]. Different be
types of entities (software objects) in the environment must • reactive: the agent notices and reacts to changes in the
be able to reason about uncertainty. Here we deal with environment,
the exploitation of intelligent agents technology in order to • proactive: the agent is goal directed and takes the
create and deploy various ubiquitous services for a mobile initiative persisting in trying to achieve the goal,
audience in pervasive environments. Agents based applica- • social: the agent interacts with other agents to achieve
tion should be able to use pervasive sensors as their own per- the goal.
ceptors in order to let the users benefit of context awareness In particular BDI agents are a type of intelligent agents
in services exploitation and in order to make mobile services characterized by flexibility with particular mental attitudes
really useful and profitable. An application in the domain of based on human concepts, such as beliefs, goals and inten-
tourism is provided because museums, archaeological parks tions.
and historical cities represent environments within which In BDI architecture [3],Beliefs, Desires, Intentions are
visitors move. They are rich of pervasive artworks, buildings, the basic components of an agent that should be able to
monuments and general points of interest which can be part operate in a dynamic, uncertain world. Beliefs represent
of the Internet of things once they can be perceived and agent’s knowledge of the world, Desires (or goals) represent
recognized by applications. Then their perception can be what the agent wants and Intentions are a set of plans used
used to support the user during his visit by enriching his own to describe how an agent achieve its goals. BDI agents are
knowledge of the environment by augmenting the reality adaptive in the sense that they can quickly reason and react
with digital information that is available in the web and is to asynchronous events acting accordingly to them.
relevant to the context. Beside intelligence is also provided from the capacity
In this area the tourist guide plays an important role be- to quickly adapt its behavior so an intelligent agent needs
cause of the increasing of more exigent audience leading to a knowledge about the environment to take decision finalized
request of more professional services for any kind of tourist to reach the goal. In fact an agent can be defined intelligent
which best fit his needs and desire of gaining satisfying and if has a Knowledge Base. The elaboration of intelligent
plans needs a basic knowledge for interpreting perceptions The knowledge of the environment acquired by the agent
and for relating them to previous ones, to infer new or represents part of its own beliefs.
hidden knowledge combining previous and new perceptions. In Figure 1 an high level representation of this model is
The capacity of reasoning of an intelligent agent is directly shown.
proportional to the information included in the knowledge
base (KB), so is desirable to have a wide KB.
In our approach an intelligent agent executes on the
user’s device to support services exploitation. It percepts
the surrounding environment using the on-board peripherals
and executes plans which are chosen by an ad-hoc reasoning
to optimize the user’s satisfaction. Besides as the device is
a PDA (Personal Digital Assistant), it has limited battery,
storage and computation capacities so also the agent running
on it has limited capacities. In order to extend the agent’s
Figure 1. Problem model
capability another remote intelligent agent interacts with
the local one to achieve individual or shared goals. This
two-agent system is part of a loosely coupled network of The environment will be modeled as a geo-referred map
problem-solver entities that work together to find solution with itineraries, landmarks and points of interest. Of course
to problems that are beyond the individual capabilities or localization of users and objects is possible according to
knowledge of each entity [4]. In fact the agent running on the the device technology, the available infrastructures and the
local device is able to collect perceptions, to communicate kind of environment. Indoor or outdoor localization can be
believes and to execute actions locally. The remote one can implemented using heterogeneous technologies, and often
access a wide knowledge base and can perform a more absolute localization could not be performed, but only
complex reasoning. nearby landmarks or object can be detected.
The agents described in our approach are developed using In our model another set of believes describes user’s
Jadex 2.0 and adapt themselves in response to a changing knowledge about the surrounding environment that can be
environment and are able to respond differently, creating acquired by using peripherals of his personal mobile device,
entirely new plans, and thus changing their own behavior by recording and evaluating user actions or explicitly asking
depending on its past experience. Agents also have a library for user feedbacks. Some examples are user’s position,
of predefined plans that are invoked by events like the add or interest, nearby objects, landscape, etc. Interaction with the
removal of a belief, the reception of a message, and the add environment and presentation of contents can be done again
of a desire. Besides each plan might consist of several sub- using user’s device and his peripherals.
plans to achieve the intention. In fact, to satisfy a specific Of course different components of the user’s knowledge
desire, it is necessary a plan that allows to reach that goal could have different weights according to their relevance or
starting from given beliefs. the time of perception. We could consider the knowledge at
The interaction between the two agents has been modeled the current time, in a time window, or the complete history.
according to a learning by teaching approach: a student on Finally another set of believes is composed of contents in
the device and a teacher in remote. The student agent learns the knowledge base of the teacher agent. But to maximize
from the teacher and the learning process can be started from the user’s satisfaction it is relevant the way they will be
both of them. As PDA has limited capacities the teacher give delivered, to be used for augmenting the reality perceived by
to the student a new plan directly and it will be stored in the the user. Services, in order to augment the user’s knowledge
agents plan library. The common goal is the maximization and the their/user’s capability to interact with the environ-
of the expected satisfaction of the user. ment, have to choose, according their context awareness:
III. P ROBLEM MODELING • what content and application should be delivered;
The first thing to be considered when modeling this kind • when it needs to execute the application or to present
of problem is the environment. In fact we have to model the a specific content;
• how this should be done.
environment where the user is moving and to reconstruct the
perceptions of the user himself in order to get his particular Plans are queries in knowledge base that select the opti-
vision about what is surrounding him. A real representation mal set of contents and organize them according to user’s
of the environment is necessary to identify landmarks and profile, device and time availability. The optimal set, and its
possibilities of intervention using pervasive actuators and organization, is chosen to optimize the user’s satisfaction.
sensors whose input will be stored in the memory of the The maximization of user satisfaction represent the desire
agent and will be updated as the environment changes. to reach.
IV. O NTOLOGY BASED KNOWLEDGE REPRESENTATION environment (indoor or outdoor);
AND REASONING • Pervasive objects. They are dynamically discovered
by the device. They can be sensors which provide
In a multi-agent system agents communicate among them
information about the environment or actuators. They
in order to reach the global goal or their local goals but
can be accessed and used by the services themselves
they can disagree about what that knowledge means. For
using the device or eventually using the network if
this reason, ontology is used to enable knowledge sharing
pervasive objects are directly connected;
among different agents and to improve the quality of the
• Time information. We intend the current time at user
service provided by agents.
side and the time that the user is spending, or has spent
An ontology implements the representation of the global within the environment.
knowledge. It is necessary to share a common dictionary • User’s interests. This part of the knowledge could be
and to describe the relationships among the entities/objects dynamically changed by the application according to
which are part of the model. In our model a common user’s behaviors and to his feedbacks. The user could
ontology includes all the general concepts which are useful choose to start from an empty or a standard profile, to
to describe a pervasive environment where mobile users are change it or to lock some properties interactively.
moving, using their devices and interacting with available
facilities and other users. The general ontology is comple- Semantic techniques are used for intelligent content and
mented with a domain ontology that is designed by an expert application discovery and delivery. Knowledge representa-
of the specific application field. Concepts of the ontology tion, ontology and annotations of digital resources are used
are used on client side to describe a representation of the to filter, organize and deliver contents and software to the de-
reality as it is perceived by the user. On the back-end vice. Different techniques for reasoning can be experimented
the ontology is used to annotate digital resources like POI such as graph matching, description logics, neural networks
(point of interests), contents, applications. It is also used or more simple ones like SPARQL (SPARQL Protocol and
to support reasoning. Each agent knows how to translate RDF Query Language) queries. Furthermore semantic can
its knowledge into the common ontology before sending be integrated with other kinds of techniques to take into
a message and after receiving a message from another account constraints such as user’s position and available time
agent. Users’ behaviors, information from pervasive devices for exploitation.
or from other users, device properties, external events are V. R EQUIREMENTS AND DESIGN
heterogeneous data are used to build a dynamic changing
representation of the user knowledge about the reality within In Figure 2 the architectural solution of a framework that
which he is moving. The applications are knowledge driven. allows to apply the described approach is shown.
The user’s knowledge can be used by the application that
is running on the device to adapt its logic locally and is
updated remotely to improve the awareness of services at
server side.
Applications are events based. Events can be updates of
the user’s knowledge or can be explicit service requests
raised by the user. At each invocations some semantic
queries, that depend on the user’s knowledge, are built and
processed to get the action to be performed and the contents
to be delivered. Results of the query are individuals of the
ontology that are described by semantic annotation.
The user’s knowledge is composed of many semantic
concepts with static, dynamic or locked properties.
Components of the knowledge are:
• Device technology and capability. Among the static
properties here we means hardware resources, on board
peripherals, display size, total memory and storage. Figure 2. Architecture and roles
Dynamic ones can be power level, available memory
and storage and bandwidth ; Users, agents, services and producers are actors in this
• User’s position. It is a dynamic property that can scenario.
change over the time and can be evaluated using On the left side the user is using his device that hosts an
different techniques and technologies, depending on the agent that is able to perceive information from the field by
devices, on the available infrastructures and the kind of pervasive sensors.
The agent student executes autonomously and proactively for the specific case study. They use or design a map to
in order to support the users’ activity within the environment represent the environment. They add POIs to the map to geo-
he is moving. It discovers surrounding objects, uses them to refer multimedia contents and can link them to a concept
update the representation of user’s knowledge, reacts using of the ontology. Furthermore they select relevant contents
the local knowledge to organize and propose the available and annotate them using concept and individuals from the
contents and facilities by an interactive interface. It could ontology.
also communicate with close devices. If the connection Remote applications implement context aware services.
works the device can access remote services which can They use personal devices to collect perceptions and for
exploit a wider knowledge and reasoning capabilities to look content delivery.
for additional contents and applications. In order to support these activities in a real scenario we
The agent teacher runs different reasonings, according to need to provide:
user’s profile, that make queries to the Fedora1 repository • back-end tools for enabling content production, their
and returns the selection of contents that best fit user’s semantic annotation publishing and retrieval;
needs of information. Teacher’s beliefs are the ontology, a • services for content discovery, adaptation and delivery;
repository of semantically annotated content, and the beliefs • a client application to support user interaction with
sent by the agent student. During the deliberation process a services, with the environment and with available con-
SPARQL query is generated. The SPARQL client submits tents.
it to the SPARQL engine of the Fedora repository in order
to collect a set of structured and organized media contents VI. A REAL CASE STUDY
representing the plan that student agent has to execute. The Exploitation of archaeological sites can be very diffi-
execution of a plan by the student agent supports the user in cult because of a lack of supporting infrastructures and
the exploitation of the pervasive environment by augmenting because of the complex recognition and comprehension of
his itinerary with media contents. The agent student has a the relevant ruins, artworks and artifacts. The availability of
limited intelligence so his task is to organize and propose personal devices can be used to plan and support the tourist
the available contents according to its beliefs. by suggesting him the visit tours, the point of interest and by
In Figure 3 is described the interaction between agent providing multimedia contents in the form of digital objects
student and teacher student. which can semantically augment the perceived reality.
In this context a relevant issue is the profiling of the
user, the selection and the presentation of the contents
which can improve the user’s satisfaction, by providing new
models of interactions with reality, trough his device. In
this context the Second University of Naples is engaged
on a multidisciplinary project with both cultural and a
technological aims [9].
Following the approach defined above we are implement-
ing a technological framework that supports the experts
in the domain of the Cultural Heritage to augment the
archaeological site with a set of multimedia contents which
are delivered by innovative services to the visitors through
their mobile devices in order to guide their tour and to
enhance their perception of the reality and learning.
Three case studies have been chosen to test the approach
and the framework. The S. Angelo in Formis Basilica, in
Campania, near S. Maria Capua Vetere, the ancient town of
Norba and on the amphitheater of Capua.
To satisfy the requirements of the presented case studies
we need to provide a technological solution that does not
need infrastructures for letting the software know the user
location and his feeling about the environment. It means
Figure 3. Interaction between agents that Bluetooth, RFID (Radio Frequency Identification), GPS
(Global Positioning System ), electronic compass, camera,
Experts of the application domain define the ontology network connection and others are the technologies which
can be used together or independently to get information
1 http://fedora-commons.org/ about the user perceptions and to augment his exploitation
of the archaeological site. The user will be able to download
at home, before to leave, or on site, if the network will be
available, the map of the area to be visited. The map will
include all the points of interest that identifies the relevant
objects of that area and different cultural itineraries which
could be exploited on site. Also contents can be discovered
and downloaded in advance. On board software and remote
services will assist the cultural visit by augmenting the
reality by the user’s personal device. In the following we
detail the technological choices which have been taken to
implement each component of the framework.
A. Environement Map
To provide a description of the environment within which
the user is moving we need a geo-referenced map that
describes buildings, roads, bans, itineraries and Points of
Interest. We used the OpenStreetMap format to design open
maps. In Figure 4 the map of the S. Angelo in Formis
Basilica is shown. It has been built by exporting a model
that was originally built by Autocad and has been exported
into a GPX format. The JSON (JavaScript Object Notation)
tool allowed us to import the GPX trace and to add manually
details and POIs. Each point represents an artifact, a ruin or
any other entities of cultural relevance and can be described
using a list of key-value pairs. Some of them have been
used to link the POIs to URLs of multimedia information,
or to provide a semantic description of the POIs itself. The
tool allow to export the map in an open format that can be
read and used by the client application that is presented in
Section VI.F.
Figure 4. S. Angelo in Formis map
B. Ontology and annotation
An ontology has been designed to describe the sites The output produced by the annotator is an RDF file that
of interest and to annotate the related media. A general use concepts and properties of the AktiveMedia ontology
part include the concepts which are common to all the and of the domain ontology.
class of applications that can be modeled according the
proposed approach. Among the others the Time class and C. Digital repository and semantic discovery
his properties (CurrentTime, AvailableTime, ElapsedTime, The Fedora repository 3.4.2 is used to store digital objects
ExploitationTime) allow to organize and assist the visit and supports their retrieval. Into the Fedora repository a
taking into account time information and handling time digital object is composed of a set of files which are:
constraints. Position class and its properties allow to localize
• object metadata: used by the client application to
the user and objects around him. An application specific
part of the ontology include the concepts that belong to the understand how to deliver the content;
• binary streams: which are images, video, text ... any
domain of the cultural heritage and additional classes and
individual which are proper of the case studies introduced kind of raw information to be delivered;
• RDF annotation: that describe the semantic of the
in the previous section.
object according to the ontology;
The ontology is used also for annotating the multimedia
• disseminations: filters to be eventually used for adapt-
contents. To annotate texts, images and any kind of contents
ing the object according to the target client.
we chose the AktiveMedia tool2 . In Figure 5 a picture of
the Amphitheater of S. Maria Capua Vetere is annotate with We loaded the Aktive-Media ontology and the domain
the Column and the Arc classes which are part of this kind ontology into the Fedora repository in order to exploit
of building. its embedded SPARQL engine that is used to select the
optimal set of individuals that means contents. Multimedia
2 http://sourceforge.net/projects/aktivemedia/). contents are automatically stored into the repository after
Figure 5. The annotator
Figure 6. Synchronized video
the annotation phase. The RDF output is automatically
processed using an XSL transformation to make it compliant For example a change of the user position is used to
with the format required by the Fedora repository. filter POIs which are close to him or are relevant to his
position. For example we could get information about a
D. Content types building located close to the user or about some other
Different types of content models have been defined and building located elsewhere but which have been designed
simple examples have been produced. by the same architect.
• Multiple images whose transparency can be graduate by When the user shoots a new picture, a search by sample
the user to compare changes in different periods. In the facility is used to find the image which are similar to the
same way real picture can be compare with paintings. the current subject. This can be used to suggest a new set
Old picture can be compared with what is seen by the of contents which relevant to what the user is looking at.
camera. Each time the interest of the users changes, or also
• Part of the image acquired by the camera are recognized when any other event occur, a reasoner generates dynamic
and linked to related multimedia contents; SPARQL queries, by which the repository is searched, and
• Virtual reconstructions which are synchronized with the organizes the retrieved contents according to their relevance.
camera output or the detected RFIDs; The ontology is used to perform additional reflexive reason-
• Text, audio, video and composite media. ing.
A content descriptor is attached to every digital object. It Additional filtering rules can be implemented using time
is used by the device when the content must be delivered. information if they are available. For example it could be
The descriptor defines the right player for that media, relevant to know the current time (to suggest a sunshine
configuration parameter and necessary input. rather than to avoid a closed attraction or museum). The
In Figure 6 an example of delivered content is shown. available time for the visit is important to limit the number
The user focus the camera on a particular view of the S. of contents and to plan an itinerary. A delay is important to
Angelo in Formis Basilica and sees the original temple of dynamically cut what is less relevant and cannot be exploited
Diana Tifatina. In particular the perspective viewed by the anymore.
camera is the same shown by the video. We implemented a search by sample filter that exploit the
position of the user to select all the picture which represent
E. Remote services the subjects he shoot, such as landscapes, monuments or
A remote service has been conceived to support content buildings around him. Within this set a matching algorithm
discovery and delivery. is able to identify an image that is the most similar to the
It uses multiple criteria to discover and filter relevant picture. All the annotation for that image are also matched
multimedia contents. Some criteria are the available time with on the display of the user’s device.
for the visit, the user’s position, the device technology, the Let us suppose that one of agent’s goals is to augment the
user interests. The service is implemented by independent visitor’s itinerary with multimedia streams, supported by his
filters. Filters are executed on the occurrence of such event device and relevant to his interest. We have to search for all
that update the user knowledge, or by direct asynchronous multimedia contents that are compliant with the encoding
request from the user himself. supported by the user’s device and describe the specified
architectural element of a particular historical period. An On the other hand a list of functionalities are provided to
example is provided in the following: deliver contents and to guide the visit. Content management
PREFIX device: (discovery client,organization and fruition) is supported both
at client side and at server side. Knowledge visualization
PREFIX prist:
and management to allow the explicit specification of user’s
SELECT ?a own interest is provided. The output of the camera is used
FROM <#ri>
WHERE {?a prist:hasConcept "Arcata"} as a component of the user’s knowledge as well as a
OR {?a prist:annotationText "Arcata"} map on which semantic additions are anchored, not simply
AND {?a prist:hasInstance "96-217_DC"}
AND {?a device:hasEncoding "mpeg"} superposed.
The user will be able to ask for and exploit available
Obviously the list of retrieved objects will be also filtered multimedia contents, which are related to points of interest,
and ordered according to other criteria like time availability or to personal interests expressed by semantic concepts.
and semantic relevance. Multimedia content will be adapted at server side according
to the device/user/session profile to provide to the user the
F. A Mobile Archaeological Guide best quality of service.
At client side we extended an open source software nav- Figure 7 shows the output of the result of the content
igator called Navit 2.0 3 . We extended the android version. discovery service. The service invocation starts the camera
The navigator provides basic facilities for map visualization that is used to take a photo of the landscape or of a subject
and to guide the user along some pre-defined itineraries of interest. Image upload, discovery of relevant contents and
by using the on-board GPS receiver. By new extension the download of retrieved information run in background mean-
guide is able to sense the environment by the available while the user is interacting with other facilities provided
peripherals, to understand the situations according to which by the client. The list of contents is presented to the user
the visit will be adapted, and to enhance the user experience. when it is available. Other events which open dialog for
Even if many experiences on augmented reality are proposed suggesting action, itineraries, POIs or media can be related
nowadays, the exploitation of vision is used only to overlap to new perceptions.
real and virtual images. The extensions provide the following
functionalities:
• access to device peripherals to sense the environment
and to update the representation of the user’s knowledge
about the reality around him;
• access to remote services to update the user knowledge
and to ask for available contents
• a local cache of objects for exploiting the visit without
connection;
• a limited reasoner that is able to organize the content
by itself when the connection does not work.
Perceptors are implemented by:
• GPS positioning to localize the user in open spaces and
to guide him on cultural itineraries;
• RFID for positioning and detection of nearby POIs.
This technology can be used to alert the user but also
for his positioning in indoor environments;
• CODBAR recognition to get information about artifact,
monuments, ... when a RFID reader is not available; Figure 7. Content retrieval
• image recognition by search by sample techniques
which are speed-up and improved using a position
based filtering; VII. R ELATED WORK
• monitoring of device resources and configuration; Many research contributions focus on the development of
• collection of user interest by feedback and by an software/hardware architecture and frameworks for mobile
analysis of his behaviour; context-aware tourist guide, also based on agent technology
• time monitoring and semantic techniques. In [5] authors present iJADE Free-
Walker, a framework that integrates GPS, ontology and agent
3 http://www.navit-project.org/ technologies to support location awareness for providing
assisted navigation and classification of tourist information innovative services to the visitors in order to guide their
for the users. The system implements a context-aware tourist tour and to enhance their knowledge of the reality.
guide for the city of Hong Kong. The ontology is extracted
ACKNOWLEDGMENT
using structural information from travel websites. CRUM-
PET, Creation of User Friendly Mobile Services Person- This work has been supported by PRIST 2009, Fruizione
alised for Tourism [6], is an agent based framework that pro- assistita e context aware di siti archelogici complessi me-
vides a context-aware tourist guide adapting the information diante terminali mobile, founded by Second University of
content and presentation according to user profile, device Naples.
and connection characteristics. It is developed in microFIPA- R EFERENCES
OS, an agent platform based on the FIPA-OS that is an Open
Source implementation of the FIPA standard4 . CRUMPET [1] A. Ranganathan, J. Al-Muhtadi, and R.H. Campbell, Reasoning
about Uncertain Contexts in Pervasive Computing Environ-
is modeled as a multi-agent system (MAS) whose agents ments., IEEE Pervasive Computing, 2004
are autonomous and share their knowledge using FIPA-
ACL (Agent Communication Language). The agents use [2] M. WOOLDRIDGE, An Introduction to MultiAgent Systems.,
a common ontology in order to understand each other. John Wiley & Sons, 2002
[7] describes Gulliver’s Genie: an ubiquitous computing
[3] M. Kinny, M. Gergeff and A. Rao, A Methodology and
application that has been designed as an agency. Mobility Modelling technique for systems of BDI Agents, In: Proc. 7th
and adaptivity are exploited provide value added services. European Worksho on Modelling Autonomous Agents in a
The framework is structured as a multi-agent system (MAS) Multi-Agent World, Springer Verlag Lecure Notes in Artificial
in which agents are designed according to the BDI model Intelligence, vol. 1038, 1996, pp.56-71
[3]. Agents are hosted both at server side and on the device
[4] V.R. Durfee, E.H. Lesser and D.D. Corkill, Trends in Co-
and communicate each other using Agent Factory ACL. The operative Distributed Problem Solving, IEEE Transactions on
framework we proposed support assisted navigation, but by Knowledge and Data Engineering, vol. March 1989, pp. 63-83
integrating heterogeneous technologies, not only GPS. In our
approach semantic is used for knowledge representation and [5] Toby H.W. Lam and Dr. Raymond S.T. Lee, iJADE FreeWalker
management but, differently from the framework above, the - An Intelligent Ontology Agent-based Tourist Guiding System,
2007
ontology is designed by experts of the application domain. It
is used both as a common vocabulary for agents organization [6] S. Poslad, H. Laamanen, R. Malaka, A. Nick, P. Buckle and A.
and for intelligent discovery of media contents. Zipf, CRUMPET: CREATION OF USER-FRIENDLY MOBILE
Beside pervasive technologies and augmented reality are SERVICES PERSONALISED FOR TOURISM, 2001
used to enhance the visit experience and enabling visitors to
[7] M.J. O’Grady and G.M.P. O’Hare, Gulliver’s Genie: Agency,
explore easily the museum according to their interests. mobility & adaptivity, Computers & Graphics, 2004, pp.677-
689
VIII. C ONCLUSION
In this paper we presented an approach for exploitation [8] G.M.P. O’Hare, M.J. O’Grady, S. Poslad and L. Titkov, Ex-
ploiting Multi-Agent Systems in realizing adaptivity in the
of intelligent agents technology in order to create and Mobile Tourist Domain, AI Communications, vol.22 n.2, April
deploy various ubiquitous services for a mobile audience 2009, pp.109-116
in pervasive environments. We introduced two agents who
interact according to a learning by teaching model. A student [9] S. Venticinque, B. Di Martino, S. Quilici Gigli,P. Carfora,
agent is running on a mobile device and a teacher agent and G. Renda. Aided exploitation and context awareness of
complex archaeological sites by mobile devices, Euromed
on remote. The common goal is to maximize the expected 2010, Museum Futures workshop, November 2010
satisfaction of the user adapting applications and contents to
be delivered and augmenting and improving his perception
of the reality. Personal devices have been exploited to
interact with the environment, to run interactive applications
and to present contents to the user. We described a frame-
work that implements the proposed approach. It represents
preliminary research results about the aided exploitation and
context awareness of complex archaeological sites by mobile
devices. The framework supports the experts in the domain
of the Cultural Heritage to augment the archaeological site
with a set of multimedia contents which are delivered by
4 http://www.fipa.org