Ecole Polytechnique Fédérale de (original) (raw)

Agent Communication Semantics for Open Environments: Issues and Challenges

2002

Explicit communication semantics are often considered essential for rich interaction between heterogeneous automated systems. While extensive work on semantic models has been carried out, much of this work remains to be tested in real open environments. This paper briefly describes some of the issues and challenges to be considered when combining existing semantic frameworks for effective agent communication. In particular, we describe issues related to the development of the Agentcities Network which is a large-scale open test bed for agent systems that aims to enable on-line experimentation with semantic frameworks for agent communication. The presentation is kept discursive in nature: characterizing different aspects of communication, outlining research challenges, commenting on possible strategies and describing the current status of activities in the Agentcities Network.

Agent Communication Semantics for Open Environments

2002

Explicit communication semantics are often considered essential for rich interaction between heterogeneous automated systems. While extensive work on semantic models has been carried out, much of this work remains to be tested in real open environments.

DASMAS: dialogue based automation of semantic interoperability in multi agent systems

2005

This paper presents our ongoing effort on developing a dialogue based framework for resolving semantic interoperability in multi agent systems. Our approach is characterized by: (1) multi agent systems that have real world heterogeneous ontologies; (2) the resolution of semantic differences at run-time through an adapted ontology negotiation protocol (ONP); and (3) the use of the Word Net lexicon in the resolution process.

Semantics in Multi-agent Systems

Agreement Technologies, 2013

In this chapter we discuss how semantic technologies in general and specific Semantic Web standards in particular can contribute to the goal of achieving interoperability between independent, loosely coupled, heterogeneous, autonomous software components (i.e. agents) and for the realization of open interaction systems. In particular we will discuss how those technologies have been used for the definition of the semantics of agent communication languages, for the definition of norms and policies used to regulate interactions in open frameworks, and for defining efficient mechanisms for matching demands (i.e., content they need) to supplies (i.e., available content) in telecommunication networks. In particular regarding this last type of application we describe a techno-economic approach for solving the matching problem, by means of a multi-agent system representing an electronic marketplace. Its functionality is realized by applying a semantic-aware content discovery model with two-level filtering in order to finally recommend a ranked set of eligible content to the users in response to their requests. The filtering processes not only consider the semantic information associated with the available content, but also ratings regarding the actual performance of businesses that act as content providers as well as the prices paid by businesses for advertising their content.

Agent Based Semantic Interoperability between Agents and Semantic Web Languages

… Information Networking and …, 2008

The flourishing idea of Semantic Web is realized as extension of the World Wide Web infrastructure. The WWW has rehabilitated interest in semantic interoperability between various semantic languages. Semantic languages like OWL, WSML and FIPA SL formalize WWW into machine process able and understandable, by their ability to represent machine interpretable contents on the Web. These semantic description languages differ in syntax and semantic representation, resulting in mismatches that hamper semantic information exchange and interoperability for cross service utilization among the resulting information systems. In this paper we propose agent based technique to facilitate translation among heterogeneous contents while preserving the semantics. We propose the architecture to realize the system in a middleware that enables agent based dynamic semantic interoperability between FIPA compliant software agents and semantic web languages including OWL and WSML. We have developed a prototype application through which a software agent communicate and use a web service published in OWL or WSML and vice versa.

Semantic Web Technology for Agent Communication Protocols

Lecture Notes in Computer Science, 2008

One relevant aspect in the development of the Semantic Web framework is the achievement of a real inter-agents communication capability at the semantic level. The agents should be able to communicate and understand each other using standard communication protocols freely, that is, without needing a laborious a priori preparation, before the communication takes place. For that setting we present in this paper a proposal that promotes to describe standard communication protocols using Semantic Web technology (specifically, OWL-DL and SWRL). Those protocols are constituted by communication acts. In our proposal those communication acts are described as terms that belong to a communication acts ontology, that we have developed, called CommOnt. The intended semantics associated to the communication acts in the ontology is expressed through social commitments that are formalized as fluents in the Event Calculus. In summary, OWL-DL reasoners and rule engines help in our proposal for reasoning about protocols. We define some comparison relationships (dealing with notions of equivalence and specialization) between protocols used by agents from different systems.

Towards a pragmatic use of ontologies in multi-agent platforms

2003

The knowledge representation field is gaining momentum with the advent of the Semantic Web activity within the W3C. This working group, thanks to previous researches, has proposed the Ontology Web Language to enhance the expressivity of web pages and to allow semantic inferences. This paper argues that knowledge representation technologies should be core components of multi-agent platforms. In the first part of this paper, we introduce our agent model that relies on the notion of skill. Then, we identify several criteria that let us to believe that the Owl language should be used as a content language within Agent Communication Languages and also in the design of multi-agent platforms. In the last part, we discuss the conceptual and technological challenges that platform designers coming from the multi-agent field have to deal with when trying to integrate knowledge representation technologies.

A Proposal for Interoperability to Agent Communication using Synonyms

2012

This paper describes the development of an model in area of communication between agents. This study involves the concepts of agents and communication issues in their interactions. Using the ontology as a technique of classification of knowledge, the model includes an approach to build an intermediate software component between agents and ontological knowledge base, using synonyms in treatment of inaccuracy information. The software component uses Jenaand SPARQL for manipulation of the ontology. To validation, the case study used is the model of the multi-agent system that represents the urban vegetable garden of Parque São JerÃ'nimo (Spain).