Os conceitos de reputação e confiança, tão difundidos em outras áreas de pesquisa, mostraram-se úteis também em sistemas multiagentes (SMA), particularmente no processo de formação de parcerias, em que agentes selecionam parceiros com os quais irão cooperar. Apesar dos inúmeros trabalhos desenvolvidos na área de SMA que propõem modelos para o cálculo de reputação e confiança, um aspecto essencial do uso de tais modelos ainda não foi suficientemente estudado: como estes conceitos podem efetivamente ajudar agentes autônomos a agir em um sistema aberto. Do ponto de vista do agente, existem algumas questões importantes relacionadas a este cenário: (1) como escolher um parceiro, levando em conta a reputação do candidato e o custo associado à parceria? (2) o quão vantajoso é manipular informação? (3) como agir em uma sociedade norteada pelo conceito de reputação a fim de atingir melhores resultados? Este trabalho tem por objetivo promover uma análise de tais questões por meio da discussão de resultados obtidos com uma ferramenta de simulação denominada RePart, criada especificamente para este fim. As simulações apresentam como cenário um modelo simplificado de um mercado constituído por consumidores e empresas. / The concepts of reputation and trust, largely researched in other fields, have proved to be also very useful in multi-agent systems (MAS), specially in the process of partnership formation, in which agents select partners to cooperate with. Despite all research that has been carried out in the past few years concerning different reputation and trust models for autonomous agents, an essential aspect related to the use of these models was not sufficiently stressed: how these concepts may effectively help an autonomous agent in order to better evolve in an open MAS scenario. From an agent perspective, there are some important questions regarding this issue: (1) how to choose a partner, taking into account its reputation and the costs associated with the partnership? (2) is it worth to manipulate information? (3) how to act in a society guided by the concept of reputation in order to achieve better results? This work promotes the analysis of these questions through the discussion of the results obtained from a reputation-based partnership formation simulator called RePart, which was specifically designed for this goal. The simulations present a simplified consumer/enterprise market scenario as a target domain.

Os conceitos de reputação e confiança, tão difundidos em outras áreas de pesquisa, mostraram-se úteis também em sistemas multiagentes (SMA), particularmente no processo de formação de parcerias, em que agentes selecionam parceiros com os quais irão cooperar. Apesar dos inúmeros trabalhos desenvolvidos na área de SMA que propõem modelos para o cálculo de reputação e confiança, um aspecto essencial do uso de tais modelos ainda não foi suficientemente estudado: como estes conceitos podem efetivamente ajudar agentes autônomos a agir em um sistema aberto. Do ponto de vista do agente, existem algumas questões importantes relacionadas a este cenário: (1) como escolher um parceiro, levando em conta a reputação do candidato e o custo associado à parceria? (2) o quão vantajoso é manipular informação? (3) como agir em uma sociedade norteada pelo conceito de reputação a fim de atingir melhores resultados? Este trabalho tem por objetivo promover uma análise de tais questões por meio da discussão de resultados obtidos com uma ferramenta de simulação denominada RePart, criada especificamente para este fim. As simulações apresentam como cenário um modelo simplificado de um mercado constituído por consumidores e empresas. / The concepts of reputation and trust, largely researched in other fields, have proved to be also very useful in multi-agent systems (MAS), specially in the process of partnership formation, in which agents select partners to cooperate with. Despite all research that has been carried out in the past few years concerning different reputation and trust models for autonomous agents, an essential aspect related to the use of these models was not sufficiently stressed: how these concepts may effectively help an autonomous agent in order to better evolve in an open MAS scenario. From an agent perspective, there are some important questions regarding this issue: (1) how to choose a partner, taking into account its reputation and the costs associated with the partnership? (2) is it worth to manipulate information? (3) how to act in a society guided by the concept of reputation in order to achieve better results? This work promotes the analysis of these questions through the discussion of the results obtained from a reputation-based partnership formation simulator called RePart, which was specifically designed for this goal. The simulations present a simplified consumer/enterprise market scenario as a target domain.

Les applications sous-marines actuelles exigent la réalisation de travaux de différentes natures dans des zones de plus en plus vastes et toujours plus profondes. La conception et l'utilisation de flottilles d'AUV dans ce contexte est un véritable challenge. Les bénéfices attendus sontmultiples. Premièrement, cela doit permettre de minimiser les coûts grâce à une répartition de ceux-ci sur l'ensemble de la flottille : la perte d'un AUV ou son mauvais fonctionnement ne remettront pas en cause l'intégralité de la mission. Deuxièmement, l'utilisation d'une flottilledoit de fait permettre de réduire le temps d'exécution d'une mission grâce à la parallélisation de certaines tâches. Enfin, la réalisation d'une mission par une flottille permet de conserver le caractère spécialisé des AUV et donc d'envisager plus facilement leur réutilisation dansd'autres contextes. Cependant, les approches de coopération multi-AUV existantes sont limitées par deux principaux verrous : (1) le nombre de communications induit et (2) la gestion de l'hétérogénéité potentielle d'une flottille.L'approche que nous proposons vise à répondre à ces problématiques.L'idée principale est de combiner une approche de coopération réactive avec une approche organisationnelle. L'approche de coopération réactive permet l'échange des signaux de communication très simples. Cependant, elle ne permet de résoudre que des problèmes de coopération de nature assez restreinte qui concernent essentiellement la coordination spatiale de véhicules homogènes. La première contribution de cette thèse est l'extension de l'approche satisfaction-altruisme. Un nouveau mécanisme décisionnel réactif, capable de considérer des actions coopératives de diverses natures, est proposé. La deuxième contribution consiste à spécifier les contextes d'interactions réactives à l'aide d'une approche organisationnelle. Le modèle organisationnel Agent/Groupe/Rôle est utilisé pour avoir une représentation explicite de l'organisation de la flottille. Les concepts de groupe, mais surtout de rôle, sont employés dans l'adressage des signaux de communication et permettent la mise en oeuvre d'interactions hétérogènes avec une grande modularité. L'ensemble est intégré dans une nouvelle architecture logicielle, appelée REMORAS, destinée à équiper des véhicules sous-marins autonomes. Une validation de la faisabilité de notre approche est proposée à l'aide d'une simulation de plusieurs scénarios mettant en jeu des AUV hétérogènes. / Underwater marine applications are nowadays branching into various fields covering larger and deeper zones. Performing the required tasks with the aid of AUV flotillas is a real challenge. However, the advantages of using such a new technology are numerous. Firstly, this would highly reduce the cost of the mission thanks to the distribution of this former among the various AUV: the loss of one AUV or its bad functioning will not degrade the performance of the flotilla in general. Secondly, the use of a flotilla reduces the execution time of a mission given the parallelization of certain tasks. Finally, any mission can be accomplished by the flotilla by taking into consideration the specificity of each AUV. In fact, each of these vehicles holds different characteristics rendering the global architecture heterogeneous and therefore applicable in different contexts. However, the methods concerned with multi-AUV cooperation are hindered by two main limitations: (1) the number of communications induced and (2) the management of the heterogeneity in the flotilla.The proposed approach aims at responding to these challenges. The principal idea is to combine this reactive cooperational approach with an organizational one. The reactive cooperational approach allows the exchange of simple communication signals. However, it does not help in solving the problems of cooperation that are very constrained and that mainly concern the spatial coordination of homogeneous vehicles. The first contribution in this thesis is the extension of the satisfaction-altruism approach. A new reactive decisional mechanism capable of considering the cooperative actions of various natures is proposed. The second contribution consists in specifying the context of reactive interactions based on an organizational approach. The organizational model Agent/Group/Role is used in order to have an explicit representation of the flotilla. The concepts of "group" and especially "role" are used in the attribution of the communication signals allowing the accomplishment of heterogeneous interactions with a big modularity. A new concept is therefore born and is integrated in a new software architecture called REMORA intended to equip autonomous underwater vehicles. This proposed new method has been validated through various numerical simulations in different scenarios putting at stake heterogeneous AUV.

Cette thèse a pour cadre le contrôle auto-adaptatif de procédés biologiques et son objectif est de permettre l'application de ce contrôle à une grande variété de problèmes distincts en évitant la phase usuelle de leur modélisation. Les bioprocédés sont des systèmes complexes, hautement dynamiques et parvenir à les contrôler en vue d'obtenir une production définie se révèle une tâche difficile. De plus, les incertitudes liées aux mesures et le manque de connaissances des réactions biologiques précises se déroulant à l'intérieur même du bioprocédé, font que les méthodes usuelles mises en œuvre pour contrôler un bioprocédé particulier doivent être largement re-calibrées dès qu'il s'agit d'adapter ce contrôle à un bioprocédé différent. L'apport de cette thèse est de proposer une approche informatique de cette problématique, centrée sur l'utilisation de Systèmes Multi-Agents Adaptatifs (AMAS). Les propriétés auto-organisatrices de tels systèmes, ainsi que leur conception centrée sur les comportements locaux, permettent d'appréhender la complexité des procédés biologiques et de fournir un système apte à leur contrôle sans nécessiter d'informations détaillées sur ceux-ci, tout en étant capable de s'adapter à leurs dynamiques. Deux systèmes multi-agents adaptatifs distincts, répondant chacun à un ensemble de contraintes différentes, ont permis d'étudier la faisabilité et l'apport de cette approche au domaine du contrôle de procédés. L'aboutissement est un modèle AMAS générique qui est associé à chaque variable contrôlable du procédé afin d'apprendre et de déterminer les actions de contrôle pour atteindre les objectifs définis par l'utilisateur. Les agents observent en temps réel l'évolution des variables du procédé pour en extraire les informations nécessaires à son contrôle. Le système de contrôle établit alors une contextualisation des contrôles à appliquer qui devient indépendante de la connaissance du bioprocédé. Ce contrôle auto-adaptatif a été évalué sur un ensemble de problèmes de contrôle de systèmes dynamiques, notamment celui d'un bioprocédé simulé, et les résultats obtenus sont analysés dans ce mémoire / This work aims at creating a self-adaptive approach to control bioprocesses while still being generic enough to be applied on a wide range of problems without relying on their modeling. Bioprocesses are complex and highly dynamic systems, and controlling them to reach a user-defined objective is a difficult task. Furthermore, the limited amount of available measures and the lack of a precise biological knowledge of what is happening inside the bioprocess lead usual control approaches to be recalibrated before being applied on a different bioprocess. The benefit of this work is a computer-based approach relying on the Adaptive Multi-Agent Systems (AMAS) theory. The objectives of adaptability and genericity are reached thanks to the self-organization of such systems and their design focusing on the local behavior of the agents, dealing with the complexity of such a problem without needing an extensive amount of information on the system to control.Two distinct multi-agent systems, defined by a specific set of constraints, were created to study the feasibility and benefits of such an approach. The outcome is a generic AMAS model, associated with each controllable variable, which learns the actions to apply in order to fulfill user-defined objectives. Agents observe in real-time the evolution of the variables and extract the information needed to control the target system. The AMAS is then able to contextualize the control without modeling the behavior of the system to control itself.This self-adaptive control was evaluated on a set of problems involving the control of dynamic systems, such as bioprocesses, and the associated results are analyzed

Este trabalho aborda os sistemas de montagem auto-organizados baseados em agentes para o ambiente industrial. Para isso, traz uma visão ampla dos paradigmas atuais para a manufatura que usam o conceito de agente e que promovem auto-organização, mas é focado no paradigma de sistemas de montagem e de produção evolutivos. Além da autoorganização, aspectos de auto-otimização nestes sistemas também são considerados. Portanto, este trabalho aborda os aspectos teóricos e práticos de sistemas evolutivos e, em particular, propõe uma plataforma multiagente que usa o conceito de agente mecatrônico para permitir o desenvolvimento de sistemas auto-organizados e que também possuam a capacidade de otimizar autonomamente algum recurso interno ao sistema. Um agente mecatrônico é uma entidade capaz de ação autônoma num sistema de manufatura, devido a uma decisão própria ou à solicitação de ação por outros agentes, e tal é conseguido através da definição e execução de funcionalidades pelos agentes mecatrônicos. A plataforma multiagente proposta foi implementada e validada no âmbito de um projeto da União Europeia o qual possui parceiros acadêmicos e industriais e visa a criação de sistemas evolutivos auto-organizados em um cenário industrial real. / This work deals with agent-based self-organized assembly systems for manufac– turing. Although the text aims to provide a comprehensive overview on current paradigms to manufactiuring systems development and execution that use the concept of agent and promote self-organization, the thesis main focus lies in evolvable production and assembly systems paradigms. Beyond self-organization, self-optimization aspects of evolvable systems are also considered. Therefore, this thesis discusses theoretical and practical aspects of evolvable systems and, in particular, develops a multi-agent platform that uses the mechatronic agent concept to enable the development of self-organized systems and has the capacity of autonomously to optimize some internal resource of the system. A mechatronic agent is an entity that is capable of autonomous action on a manufacturing system due to this own reasoning or by reacting to a requested action from other agents. The proposed platform was implemented and validated within the scope of a research project funded by the European Union that has both academic and industrial partners and it goals the building of self-organized evolvable assembly systems for a real industrial scenario.

Cette thèse concerne le contrôle coopératif de systèmes multi-agents. Ce sujet a été largement étudié dans la littérature récente en raison de son grand nombre d'applications. Cette thèse propose de nouvelles conceptions de stratégies de contrôle collaboratif afin de réaliser une mission d'exploration sous-marine. En particulier, l'objectif final est de diriger une flotte de véhicules autonomes sous-marins, équipés de capteurs appropriés, jusqu'à l'emplacement d'une source de température, de polluants ou d'eau douce. Dans cette situation, il est pertinent de considérer les contraintes de communication entre véhicules qui sont décrites au moyen de graphe de communication. Les premières contributions traitent du développement de commandes de formation qui stabilisent la flotte vers des formations variant dans le temps, et qui, de plus, distribuent uniformément les véhicules le long de la formation. Enfin, le problème de recherche est abordée par l'interprétation de la flotte de véhicules comme un réseau mobile de capteurs. En particulier, il est démontré que les mesures recueillies par la flotte de véhicules permet d'estimer le gradient de concentration de la quantité d'intérêt. Suivant cette idée, un algorithme distribué basé sur des algorithmes de consensus est proposé d'estimer la direction du gradient d'une distribution du signal. / This dissertation focuses on cooperative control of multi-agent systems. This topic has been extensively studied in recent literature due to its large number of applications. This thesis is concerned by the design of collaborative control strategies in order to achieve an underwater exploration mission. In particular, the final aim is to steer a fleet of autonomous underwater vehicles, which are equipped by appropriate sensors, to the location of a source of temperature, pollutant or fresh water. In this situation it is relevant to consider constraints in the communication between vehicles which are described by means of a communication graph. The first contributions deal with the development of cooperative formation control laws which stabilize the fleet to time-varying formations and, in addition, which also distribute the vehicles uniformly along the formation. Finally, the source-seeking problem is tackled by interpreting the fleet of vehicles as a mobile sensors network. In particular, it is shown that the measurements collected by the fleet of vehicles allows us to approximate the gradient of a scalar field. Following this idea, a distributed algorithm based on consensus algorithms is proposed to estimate the gradient direction of a signal distribution.

Este trabalho aborda os sistemas de montagem auto-organizados baseados em agentes para o ambiente industrial. Para isso, traz uma visão ampla dos paradigmas atuais para a manufatura que usam o conceito de agente e que promovem auto-organização, mas é focado no paradigma de sistemas de montagem e de produção evolutivos. Além da autoorganização, aspectos de auto-otimização nestes sistemas também são considerados. Portanto, este trabalho aborda os aspectos teóricos e práticos de sistemas evolutivos e, em particular, propõe uma plataforma multiagente que usa o conceito de agente mecatrônico para permitir o desenvolvimento de sistemas auto-organizados e que também possuam a capacidade de otimizar autonomamente algum recurso interno ao sistema. Um agente mecatrônico é uma entidade capaz de ação autônoma num sistema de manufatura, devido a uma decisão própria ou à solicitação de ação por outros agentes, e tal é conseguido através da definição e execução de funcionalidades pelos agentes mecatrônicos. A plataforma multiagente proposta foi implementada e validada no âmbito de um projeto da União Europeia o qual possui parceiros acadêmicos e industriais e visa a criação de sistemas evolutivos auto-organizados em um cenário industrial real. / This work deals with agent-based self-organized assembly systems for manufac– turing. Although the text aims to provide a comprehensive overview on current paradigms to manufactiuring systems development and execution that use the concept of agent and promote self-organization, the thesis main focus lies in evolvable production and assembly systems paradigms. Beyond self-organization, self-optimization aspects of evolvable systems are also considered. Therefore, this thesis discusses theoretical and practical aspects of evolvable systems and, in particular, develops a multi-agent platform that uses the mechatronic agent concept to enable the development of self-organized systems and has the capacity of autonomously to optimize some internal resource of the system. A mechatronic agent is an entity that is capable of autonomous action on a manufacturing system due to this own reasoning or by reacting to a requested action from other agents. The proposed platform was implemented and validated within the scope of a research project funded by the European Union that has both academic and industrial partners and it goals the building of self-organized evolvable assembly systems for a real industrial scenario.

Este trabalho aborda os sistemas de montagem auto-organizados baseados em agentes para o ambiente industrial. Para isso, traz uma visão ampla dos paradigmas atuais para a manufatura que usam o conceito de agente e que promovem auto-organização, mas é focado no paradigma de sistemas de montagem e de produção evolutivos. Além da autoorganização, aspectos de auto-otimização nestes sistemas também são considerados. Portanto, este trabalho aborda os aspectos teóricos e práticos de sistemas evolutivos e, em particular, propõe uma plataforma multiagente que usa o conceito de agente mecatrônico para permitir o desenvolvimento de sistemas auto-organizados e que também possuam a capacidade de otimizar autonomamente algum recurso interno ao sistema. Um agente mecatrônico é uma entidade capaz de ação autônoma num sistema de manufatura, devido a uma decisão própria ou à solicitação de ação por outros agentes, e tal é conseguido através da definição e execução de funcionalidades pelos agentes mecatrônicos. A plataforma multiagente proposta foi implementada e validada no âmbito de um projeto da União Europeia o qual possui parceiros acadêmicos e industriais e visa a criação de sistemas evolutivos auto-organizados em um cenário industrial real. / This work deals with agent-based self-organized assembly systems for manufac– turing. Although the text aims to provide a comprehensive overview on current paradigms to manufactiuring systems development and execution that use the concept of agent and promote self-organization, the thesis main focus lies in evolvable production and assembly systems paradigms. Beyond self-organization, self-optimization aspects of evolvable systems are also considered. Therefore, this thesis discusses theoretical and practical aspects of evolvable systems and, in particular, develops a multi-agent platform that uses the mechatronic agent concept to enable the development of self-organized systems and has the capacity of autonomously to optimize some internal resource of the system. A mechatronic agent is an entity that is capable of autonomous action on a manufacturing system due to this own reasoning or by reacting to a requested action from other agents. The proposed platform was implemented and validated within the scope of a research project funded by the European Union that has both academic and industrial partners and it goals the building of self-organized evolvable assembly systems for a real industrial scenario.

Cette thèse traite de l'automatisation de la généralisation cartographique qui est le procédé de simplification d'une base de données géographique vectorielle pour sa représentation sur une carte lisible. La recherche dans le domaine a abouti aujourd'hui au développement de nombreux processus automatiques de généralisation cartographique, chacun étant spécialisé pour un problème particulier comme un type de paysage, un thème de donnée, un type de conflit ou un mélange des trois (proximité entre bâtiments en zone urbaine). L'objectif de cette thèse est de tirer parti de cette diversité pour mettre en place la généralisation complète d'une carte en faisant collaborer des processus de généralisation complémentaires. Pour répondre à cet objectif, nous proposons le modèle CollaGen (Collaborative Generalisation) qui permet, par un système multi-agent, la collaboration des processus : les données sont découpées de manière pertinente par rapport aux processus à disposition en espaces géographiques (une zone urbaine ou le réseau routier par exemple) ; la généralisation d'un espace par un processus est ensuite orchestrée par CollaGen. CollaGen associe de manière itérative un espace à généraliser et un processus adapté, notamment par un mécanisme de registre type pages jaunes. L'interopérabilité entre les processus est assurée par une ontologie du domaine sur laquelle s'appuie un format de spécifications formelles d'une carte généralisée. Chaque généralisation est évaluée globalement en temps réel pour permettre un retour en arrière en cas de problème. Enfin, du fait du principe de découpage en espaces, CollaGen doit vérifier après chaque généralisation si des effets de bord sont apparus avec les objets géographiques situés juste à l'extérieur de l'espace, auquel cas il les corrige au mieux. Dans, cette thèse, le modèle CollaGen est mis en œuvre pour la généralisation de cartes topographiques (notamment au 1 : 50000) et les résultats sont comparés à d'autres approches et discutés / This phd thesis deals with cartographic generalisation, the process that simplifies a geographic database to allow its representation on legible map. Past research lead to the development of many automatic generalisation processes, each one being specialised for a specific problem like a particular landscape, a given data theme, a particular graphic conflict or a mix of the three (like ‘proximity between buildings in urban areas). The aim of the thesis is to benefit from this diversity to carry out a complete map generalisation by collaboration between complementary processes. To meet this objective, the CollaGen model is proposed (Collaborative Generalisation) as it allows, based on multi-agent techniques, generalisation processes collaboration : data is relevantly partitioned into geographic spaces (e.g. an urban area or the road network) ; then CollaGen orchestrate the generalisation of a space by an adapted process. CollaGen iterately maps a space to be generalised and an adapted process thanks to a yellow pages registry mecanism. The interoperability between processes is managed by a domain ontology on which formal map specifications are based. Each generalization is globally assessed online to allow backtracks if necessary. Finally, because of the space partitioning, CollaGen has to check after each generalisation if side effects appeared with spaces just outside the one that has been generalised. If some side effects occurred, they are corrected. In this thesis, CollaGen is implemented for topographic map generalisation (to 1 : 50000) and results obtained are compared to other approaches and discussed

A Inteligência Artificial Distribuída traz uma série de novas perspectivas para a computação quando considera sistemas heterogêneos, adaptativos, evolutivos, continuamente em funcionamento e abertos. Estes sistemas, chamados de sociedades, apresentam tais características por permitirem que seus componentes, chamados de agentes, migrem entre sociedades, isto é, agentes podem sair e entrar em sociedades. Sociedades abertas permitem a migração dos agentes e coloca dois tipos de problemas para o agente que está migrando: problemas de linguagem e interação, que concernem ao uso de expressões usadas e à maneira como as interações são organizadas na nova sociedade; e, problemas de conhecimento e atuação, que se referem à como um agente irá se comportar a fim de realizar justamente aquilo que a sociedade espera dele. Este trabalho se atem aos problemas de conhecimento e atuação. Para que os agentes da sociedade possam cooperar e coordenar suas ações, é necessário que tenham conhecimento das capacidades, habilidades, desejos e planos dos outros agentes. Grande parte do conhecimento a respeito dos outros pode ser extraído dos papéis que estes podem assumir na sociedade. Assim sendo, o problema colocado para este trabalho é como os agentes da sociedade que receberam o agente imigrante e o próprio agente imigrante conhecerão/aprenderão os papéis uns dos outros. São desenvolvidos três mecanismos de identificação de papéis, bem como a comparação entre eles e sua adequação a tipos de migração. Os três mecanismos são os seguintes: i) Identificação de papéis por protocolo de apresentação: é proposta uma linguagem de descrição de protocolos (LDP) e uma especificação de protocolo de apresentação nesta LDP. Os agentes que utilizam este mecanismo conseguem se identificar com rapidez, porém necessitam conhecer várias informações “locais” da sociedade, o que pode ser muito restritivo para um agente migrante. ii) Identificação de papéis por observação e classificação: esta solução procura classificar o agente observado em um papel de um conjunto prédefinido de papéis. Neste conjunto, os papéis são descritos por meio de processos de interação (PI). Para isto, desenvolveu-se a noção de PI. Para isto, desenvolveu-se a noção de PI. Foram desenvolvidas duas formas de proceder a classificação: construir uma especificação do agente a partir da observação das suas ações e verificar se esta pertence ao conjunto pré-definido de papéis; e, verificar se o comportamento do agente confere com as execuções possíveis para algum dos papéis pré-definidos. Este mecanismo é mais adequado para sociedades abertas e tem boa precisão no resultado apresentado, porém, a identificação do papel de um agente pode ser demorada. iii) Identificação de papéis por reconhecimento de intenções em planos: este mecanismo baseia-se na existência de uma relação entre intenções e papéis. A partir das ações observadas para o agente, procura-se saber qual seu plano, sua intenção e, conseqüentemente, seu papel. Para isto foi implementado um procedimento de indução de planos. Este mecanismo também é adequado para sociedades abertas, no entanto, a identificação, embora satisfatória, nem sempre é completamente correta. Estes três mecanismos foram testados em simulações numa implementação da sociedade Produtor - Consumidor, onde puderam ser comprovadas as características de cada um. / Distributed Artificial Intelligence brings a number of new perspectives to Computing Science when heterogeneous, adaptative and evolutive systems, those under functioning and open, are taken into consideration. These systems, named societies, present these characteristics because they allow their components, named agents, to migrate within societies, that is, agents are allowed to enter and to leave societies. Agents' migration brings two kinds of problems to the migrating agent: language and interaction problems both related to the use of used expressions and to the way the interactions are organized in the new society; and, knowledge and performance problems refering to the way the agent will behave in order to accomplish exactly what society expects him to do. This work is limited to knowledge and performance problems. In order to cooperate and coordinate their actions, the society's agents need to learn about the capabilities, abilities wishes and plans of other agents. A great part of knowledge of others can be extracted from the social roles these agents can play. Therefore, the problem posed in this work is how social agents who has received an immigrating agent and the immigrating agent himself will know and learn one another's roles. Three role identification mechanisms, and the comparison between them and their adaptation to migration types as well are developed. The three mechanisms are the following: i) Role Identification by means of presentation protocol:a language of protocol description (LPD) and a specification of presentation protocol in this LPD are proposed. The agents who use this mechanism can rapidly identify each other, however they need know a number of 'local' social information, which can be very restrictive to the migrating agent. ii) Role identification by means of observation and classification: this solution tries to classify the observed agent as a role out of set of definite roles. In this set, the roles are described by means of interactional processes (IP). Therefore, the notion of IP was developed. Two ways to proceed the role classification were developed: to build the agent's especification departing from the observation of their actions and to check whether this especification belongs to a set of pre-defined roles; and to check whether the agent's behavior fits the possible executions to some predefined roles. This mechanism is more adequate to open societies and has good precision in the result presented, but, the agent's role identification can last longer. iii) Role Identification by means of intention and plans recognition: this mechanism is based on the existence of a relationship between intentions and roles. By departing from the agent's observed actions, his plan, intention, consequently, his role is recognized. Therefore an induced plan procedure was implemented. This mechanism is also adequate to open societies, however, the identification, though satisfactory, is not always totally correct. These three mechanisms were tested in simulated situations in a kind of Producer- Consumer Society implementation in which each one's characteristics could be verified.