Dissertations / Theses: 'Artificial Social Agents'

1

Hogg, Lisa Marie Jean. "Control of social reasoning in resource bounded agents." Thesis, Queen Mary, University of London, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.251682.

Full text

APA, Harvard, Vancouver, ISO, and other styles

2

de, Greeff Joachim. "Interactive concept acquisition for embodied artificial agents." Thesis, University of Plymouth, 2013. http://hdl.handle.net/10026.1/1587.

Full text

Abstract:

An important capacity that is still lacking in intelligent systems such as robots, is the ability to use concepts in a human-like manner. Indeed, the use of concepts has been recognised as being fundamental to a wide range of cognitive skills, including classification, reasoning and memory. Intricately intertwined with language, concepts are at the core of human cognition; but despite a large body or research, their functioning is as of yet not well understood. Nevertheless it remains clear that if intelligent systems are to achieve a level of cognition comparable to humans, they will have to posses the ability to deal with the fundamental role that concepts play in cognition. A promising manner in which conceptual knowledge can be acquired by an intelligent system is through ongoing, incremental development. In this view, a system is situated in the world and gradually acquires skills and knowledge through interaction with its social and physical environment. Important in this regard is the notion that cognition is embodied. As such, both the physical body and the environment shape the manner in which cognition, including the learning and use of concepts, operates. Through active partaking in the interaction, an intelligent system might influence its learning experience as to be more effective. This work presents experiments which illustrate how these notions of interaction and embodiment can influence the learning process of artificial systems. It shows how an artificial agent can benefit from interactive learning. Rather than passively absorbing knowledge, the system actively partakes in its learning experience, yielding improved learning. Next, the influence of embodiment on perception is further explored in a case study concerning colour perception, which results in an alternative explanation for the question of why human colour experience is very similar amongst individuals despite physiological differences. Finally experiments, in which an artificial agent is embodied in a novel robot that is tailored for human-robot interaction, illustrate how active strategies are also beneficial in an HRI setting in which the robot learns from a human teacher.

APA, Harvard, Vancouver, ISO, and other styles

3

Casali, Ana. "On intentional and social agents with graded attitudes." Doctoral thesis, Universitat de Girona, 2008. http://hdl.handle.net/10803/7748.

Full text

Abstract:

La principal contribución de esta Tesis es la propuesta de un modelo de agente BDI graduado (g-BDI) que permita especificar una arquitetura de agente capaz de representar y razonar con actitudes mentales graduadas. Consideramos que una arquitectura BDI más exible permitirá desarrollar agentes que alcancen mejor performance en entornos inciertos y dinámicos, al servicio de otros agentes (humanos o no) que puedan tener un conjunto de motivaciones graduadas. En el modelo g-BDI, las actitudes graduadas del agente tienen una representación explícita y adecuada. Los grados en las creencias representan la medida en que el agente cree que una fórmula es verdadera, en los deseos positivos o negativos permiten al agente establecer respectivamente, diferentes niveles de preferencias o de rechazo. Las graduaciones en las intenciones también dan una medida de preferencia pero en este caso, modelan el costo/beneficio que le trae al agente alcanzar una meta. Luego, a partir de la representación e interacción de estas actitudes graduadas, pueden ser modelados agentes que muestren diferentes tipos de comportamiento. La formalización del modelo g-BDI está basada en los sistemas multi-contextos. Diferentes lógicas modales multivaluadas se han propuesto para representar y razonar
sobre las creencias, deseos e intenciones, presentando en cada caso una axiomática completa y consistente. Para tratar con la semántica operacional del modelo de agente, primero se definió un calculus para la ejecución de sistemas multi-contextos, denominado Multi-context calculus. Luego, mediante este calculus se le ha dado al modelo g-BDI semántica computacional. Por otra parte, se ha presentado una metodología para la ingeniería de agentes g-BDI en un escenario multiagente. El objeto de esta propuesta es guiar el diseño de sistemas multiagentes, a partir de un problema del mundo real. Por medio del desarrollo de un sistema recomendador en turismo como caso de estudio, donde el agente recomendador tiene una arquitectura g-BDI, se ha mostrado que este modelo es valioso para diseñar e implementar agentes concretos. Finalmente, usando este caso de estudio se ha realizado una experimentación sobre la flexibilidad y performance del modelo de agente g-BDI, demostrando que es útil para desarrollar agentes que manifiesten conductas diversas. También se ha mostrado que los resultados obtenidos con estos agentes recomendadores modelizados con actitudes graduadas, son mejores que aquellos alcanzados por los agentes con actitudes no-graduadas.
The central contribution of this dissertation is the proposal of a graded BDI agent model (g-BDI), specifying an architecture capable of representing and reasoning with graded mental attitudes. We consider that making the BDI architecture more exible will allow us to design and develop agents capable of improved performance in uncertain and dynamic environments, serving other agents (human or not) that may have a set of graded motivations.
In the g-BDI model, the agent graded attitudes have an explicit and suitable representation. Belief degrees represent the extent to which the agent believes a formula to be true. Degrees of positive or negative desires allow the agent to set di_erent levels of preference or rejection respectively. Intention degrees also give a preference measure but, in this case, modelling the cost/benefit trade off of achieving an agent's goal. Then, agents having different kinds of behaviour can be modelled on the basis of the representation and interaction of their graded attitudes. The formalization of the g-BDI agent model is based on Multi-context systems and in order to represent and reason about the beliefs, desires and intentions, we followed a many-valued modal approach. Also, a sound and complete axiomatics for representing each graded attitude is proposed. Besides, in order to cope with the operational semantics aspects of the g-BDI agent model, we first defined a Multi-context calculus for Multi-context systems execution and then, using this calculus we give this agent model computational meaning.
Furthermore, a software engineering process to develop graded BDI agents in a multiagent scenario is presented. The aim of the proposed methodology is to guide the design of a multiagent system starting from a real world problem. Through the development of a Tourism recommender system, where one of its principal agents is modelled as a g-BDI agent, we show that the model is useful to design and implement concrete agents.
Finally, using the case study we have made some experiments concerning the exibility and performance of the g-BDI agent model, demonstrating that this agent model is useful to develop agents showing varied and rich behaviours. We also show that the results obtained by these particular recommender agents using graded attitudes improve those achieved by agents using non-graded attitudes.

APA, Harvard, Vancouver, ISO, and other styles

4

Magalhaes, Martins Joao Pedro. "Emergent rhythmic structures as cultural phenomena driven by social pressure in a society of artificial agents." Thesis, University of Plymouth, 2012. http://hdl.handle.net/10026.1/1185.

Full text

Abstract:

This thesis studies rhythm from an evolutionary computation perspective. Rhythm is the most fundamental dimension of music and can be used as a ground to describe the evolution of music. More specifically, the main goal of the thesis is to investigate how complex rhythmic structures evolve, subject to the cultural transmission between individuals in a society. The study is developed by means of computer modelling and simulations informed by evolutionary computation and artificial life (A-Life). In this process, self-organisation plays a fundamental role. The evolutionary process is steered by the evaluation of rhythmic complexity and by the exposure to rhythmic material. In this thesis, composers and musicologists will find the description of a system named A-Rhythm, which explores the emerged behaviours in a community of artificial autonomous agents that interact in a virtual environment. The interaction between the agents takes the form of imitation games. A set of necessary criteria was established for the construction of a compositional system in which cultural transmission is observed. These criteria allowed the comparison with related work in the field of evolutionary computation and music. In the development of the system, rhythmic representation is discussed. The proposed representation enabled the development of complexity and similarity based measures, and the recombination of rhythms in a creative manner. A-Rhythm produced results in the form of simulation data which were evaluated in terms of the coherence of repertoires of the agents. The data shows how rhythmic sequences are changed and sustained in the population, displaying synchronic and diachronic diversity. Finally, this tool was used as a generative mechanism for composition and several examples are presented.

APA, Harvard, Vancouver, ISO, and other styles

5

Monteiro, Júlio de Lima do Rêgo. "Simulação de parcerias entre agentes: uma extensão do sistema PART-NET." Universidade de São Paulo, 2004. http://www.teses.usp.br/teses/disponiveis/3/3141/tde-28022005-002806/.

Full text

Abstract:

O objetivo deste trabalho é o desenvolvimento de uma ferramenta de simulação baseada em multiagentes para calcular a emergência de parcerias entre múltiplos agentes. A metodologia adotada foi tomar como base o sistema PART-NET [CONTE98], que efetua o cálculo da emergência de parcerias entre uma dupla de agentes, e alterá-lo de acordo com o objetivo proposto. Dessa maneira, dividiu-se o trabalho em duas etapas. Na primeira, o sistema original foi reescrito na linguagem Java, promovendo benefícios operacionais, como a melhora da interface e a apresentação dos resultados de forma gráfica. Esse sistema intermediário foi denominado PartNET+. A segunda etapa constituiu-se em expandir a funcionalidade do sistema intermediário, tornando sua arquitetura de agentes mais completa pela adição de planos, o que permite novos tipos de parcerias. Para processar essas parcerias, criou-se um novo algoritmo para cálculo de parcerias entre múltiplos agentes, com base em hipergrafos. O sistema resultante, que compreende estas extensões funcionais, foi denominado PartNET++.
The purpose of this work is the development of a multiagent based simulation tool to account partnership formation among multiple agents. In order to achieve that, the PART-NET [CONTE98] system was adopted as a base. This system calculates the partnership formation of pairs of agents, and was altered according to the proposed objective. In this manner, the work was divided in two stages. In the first, the original system was redesigned using the Java language, bringing operational improvements to the predecessor, such as user interface enhancement and graphical display of the results. This intermediary system was named PartNET+. The second stage promotes new functionality to this intermediary system, adding plans to its agent architecture to allow new kinds of partnerships. A new algorithm for multiple agents partnership formation was developed based on hipergraphs, and the final system that handles this enhanced partnership formation was called PartNET++

APA, Harvard, Vancouver, ISO, and other styles

6

Kumar, Rohit. "Socially Capable Conversational Agents for Multi-Party Interactive Situations." Research Showcase @ CMU, 2011. http://repository.cmu.edu/dissertations/162.

Full text

Abstract:

Since the inception of AI research, great strides have been made towards achieving the goal of extending natural language conversation as a medium of interaction with machines. Today, we find many Conversational Agents (CAs) situated in various aspects of our everyday life such as information access, education and entertainment. However, most of the existing work on CAs has focused on agents that support only one user in each interactive session. On the other hand, people organize themselves in groups such as teams of co-workers, family and networks of friends. With the mass-adoption of Internet based communication technologies for group interaction, there is an unprecedented opportunity for CAs to support interactive situations involving multiple human participants. Support provided by these CAs can make the functioning of some of these groups more efficient, enjoyable and rewarding to the participants. Through our work on supporting various Multi-Party Interactive Situations (MPIS), we have identified two problems that must be addressed in order to embed effective CAs in such situations. The first problem highlights the technical challenges involving the development of CAs in MPIS. Existing approaches for modeling agent behavior make assumptions that break down in multi-party interaction. As a step towards addressing this problem, this thesis contributes the Basilica software architecture that uses an event-driven approach to model conversation as an orchestration of triggering of conversational behaviors. This architecture alleviates the technical problems by providing a rich representational capability and the flexibility to address complex interaction dynamics. The second problem involves the choice of appropriate agent behaviors. In MPIS, agents must compete with human participants for attention in order to effectively deliver support and interventions. In this work, we follow a model of human group interaction developed by empirical research in small group communication. This model identifies two fundamental processes in human group interaction, i.e., Instrumental (Task-related) and Expressive (Social-Emotional). Behaviors that constitute this expressive process hold the key to managing and regulating user attention and serve other social functions in group interaction. This thesis describes two socially capable conversational agents that support users in collaborative learning and group decision making activities. Their social capabilities are composed of a set of behaviors based on the Social-Emotional interaction categories identified by work in small group communication. These agents demonstrate the generalizability of our methodology for designing and implementing social capabilities across two very different interactive situations. In addition to the implementation of these agents, the thesis presents a series of experiments and analysis conducted to investigate the effectiveness of these social capabilities. First and foremost, these experiments show significant benefits of the use of socially capable agents on task success and agent perception across the two different interactive situations listed above. Second, they investigate issues related to the appropriate use of these social capabilities specifically in terms of the amount and timing of the constituent social behaviors. Finally, these experiments provide an understanding of the underlying mechanism that explains the effects that social capabilities can achieve.

APA, Harvard, Vancouver, ISO, and other styles

7

Santos, Fernão Reges dos. "Comunidades virtuais baseadas em vídeo digital: uma proposta de conteúdo adaptativo pautada em redes de aprendizagem e agentes inteligentes." Universidade Presbiteriana Mackenzie, 2010. http://tede.mackenzie.br/jspui/handle/tede/1514.

Full text

Abstract:

Made available in DSpace on 2016-03-15T19:38:15Z (GMT). No. of bitstreams: 1 Fernao Reges dos Santos.pdf: 3479474 bytes, checksum: 654fb96f7fdab2d5f475a37081149c9c (MD5) Previous issue date: 2010-06-07
With the increasing number of participants to internet social network based systems, which uses several computer mediated communication resources like chat, instant messaging, hypertext links to videos and several objects available to facilitate the interaction between users, new frontiers emerges to apply this concepts on educational environment with collaborative forms. This work researches the applicability of Artificial Intelligence models combined with Social Network systems through use of Intelligent Agents. Initially the combination of Intelligent Agents and Social Networks proposal uses Multiagent based kernel acting to analyze and mediate the interaction process over social network.. Considering this perspective and to try stimulate the interactive user process on social network, this work brings the possibility of integrating the main kernel with a social network based on platforms using digital video, like Internet and Digital TV. Using educational content operating with a external module working as Intelligent Tutoring System which provides instructional units to be used with interactive and collaborative forms by participants, resulting a distance and collaborative learning tool. The main target for this tool combining Intelligent Agents and Social Networks, intends to provide a context where educators can research new educational strategies, interactive and collaborative perspectives.
Com o crescente número de usuários de sistemas redes sociais baseadas em Internet, cresce também a integração desses sistemas com diversos recursos de comunicação mediada por computador como serviços de comunicação instantânea e sistemas de bate-papo, vínculos hipertextuais para vídeos, arquivos de áudio e outros objetos que podem ser utilizados como facilitadores do processo interativo e de distribuição de conteúdo nas redes sociais. Nesse cenário, surgem novas possibilidades de aplicação desse tipo de ambiente de forma educacional e colaborativa. A partir desse cenário, esta dissertação aborda a aplicação de modelos de Inteligência Artificial em Sistemas de Redes Sociais por meio da utilização de Agentes Inteligentes. O objetivo da composição de Redes Sociais e Agentes Inteligentes para essa ferramenta é disponibilizar um ambiente em que possam ser investigadas as diferentes possibilidades de estratégias pedagógicas que podem aplicadas nesse novo ambiente de interação e colaboração social. De forma experimental, essa combinação entre Agentes Inteligentes e Sistemas de Redes Sociais foi proposta por meio de um modelo de sistema Multiagente, que atua como núcleo intermediador e analítico do processo interativo que ocorre na rede. Considerando essa perspectiva, e para estímulo do processo interativo entre os usuários da rede, foi estabelecida a integração desse núcleo a uma rede social que opera em plataformas de distribuição de vídeos digitais, como Internet e TV Digital Interativa, utilizando conteúdo educativo que, operando em conjunto com um módulo tutor inteligente, disponibiliza atividades para serem realizadas de forma interativa entre os participantes, resultando em uma ferramenta de Educação a Distância e aprendizado colaborativo.

APA, Harvard, Vancouver, ISO, and other styles

8

Novaro, Arianna. "Collective decision-making with goals." Thesis, Toulouse 3, 2019. http://www.theses.fr/2019TOU30179.

Full text

Abstract:

Des agents devant prendre une décision collective sont souvent motivés par des buts individuels. Dans ces situations, deux aspects clés doivent être abordés : sélectionner une alternative gagnante à partir des voix des agents et s'assurer que les agents ne manipulent pas le résultat. Cette thèse étudie l'agrégation et la dimension stratégique des décisions collectives lorsque les agents utilisent un langage représenté de manière compacte. Nous étudions des langages de type logique : de la logique propositionnelle aux CP-nets généralisés, en passant par la logique temporelle linéaire (LTL). Notre principale contribution est l'introduction d'un cadre de vote sur les buts, dans lequel les agents soumettent des buts individuels exprimés comme des formules de la logique propositionnelle. Les fonctions d'agrégation classiques issues du vote, de l'agrégation de jugements et de la fusion de croyances sont adaptées et étudiées de manière axiomatique et computationnelle. Les propriétés axiomatiques connues dans la littérature sur la théorie du choix social sont généralisées à ce nouveau type d'entrée, ainsi que les problèmes de complexité visant à déterminer le résultat du vote. Une autre contribution importante est l'étude de l'agrégation des CP-nets généralisés, c'est-à-dire des CP-nets où la précondition de l'énoncé de préférence est une formule propositionnelle. Nous utilisons différents agrégateurs pour obtenir un classement collectif des résultats possibles. Grâce à cette thèse, deux axes de recherche sont ainsi reliés : l'agrégation des CP-nets classiques et la généralisation des CP-nets à des préconditions incomplètes. Nous contribuons également à l'étude du comportement stratégique dans des contextes de prise de décision collective et de théorie des jeux. Le cadre du vote basé sur les buts est de nouveau étudié sous l'hypothèse que les agents peuvent décider de mentir sur leur but s'ils obtiennent ainsi un meilleur résultat. L'accent est mis sur trois règles de vote majoritaires qui se révèlent manipulables. Par conséquent, nous étudions des restrictions à la fois sur le langage des buts et sur les stratégies des agents en vue d'obtenir des résultats de votes non manipulables. Nous présentons par ailleurs une extension stratégique d'un modèle récent de diffusion d'opinion sur des réseaux d'influence. Dans les jeux d'influence définis ici, les agents ont comme but des formules en LTL et ils peuvent choisir d'utiliser leur pouvoir d'influence pour s'assurer que leur but est atteint. Des solutions classiques telles que la stratégie gagnante sont étudiées pour les jeux d'influence, en relation avec la structure du réseau et les buts des agents. Enfin, nous introduisons une nouvelle classe de concurrent game structures (CGS) dans laquelle les agents peuvent avoir un contrôle partagé sur un ensemble de variables propositionnelles. De telles structures sont utilisées pour interpréter des formules de logique temporelle en temps alternés (ATL), grâce auxquelles on peut exprimer l'existence d'une stratégie gagnante pour un agent dans un jeu itéré (comme les jeux d'influence mentionnés ci-dessus). Le résultat principal montre qu'un CGS avec contrôle partagé peut être représenté comme un CGS avec contrôle exclusif. En conclusion, cette thèse contribue au domaine de la prise de décision collective en introduisant un nouveau cadre de vote basé sur des buts propositionnels. Elle présente une étude de l'agrégation des CP-nets généralisés et une extension d'un cadre de diffusion d'opinion avec des agents rationnels qui utilisent leur pouvoir d'influence. Une réduction du contrôle partagé à un contrôle exclusif dans les CGS pour l'interprétation des logiques du raisonnement stratégique est également proposée. Par le biais de langages logiques divers, les agents peuvent ainsi exprimer buts et préférences sur la décision à prendre, et les propriétés souhaitées pour le processus de décision peuvent en être garanties
Agents having to take a collective decision are often motivated by individual goals. In such scenarios, two key aspects need to be addressed. The first is defining how to select a winning alternative from the expressions of the agents. The second is making sure that agents will not manipulate the outcome. Agents should also be able to state their goals in a way that is expressive, yet not too burdensome. This dissertation studies the aggregation and the strategic component of multi-agent collective decisions where the agents use a compactly represented language. The languages we study are all related to logic: from propositional logic, to generalized CP-nets and linear temporal logic (LTL). Our main contribution is the introduction of the framework of goal-based voting, where agents submit individual goals expressed as formulas of propositional logic. Classical aggregation functions from voting, judgment aggregation, and belief merging are adapted to this setting and studied axiomatically and computationally. Desirable axiomatic properties known in the literature of social choice theory are generalized to this new type of propositional input, as well as the standard complexity problems aimed at determining the result. Another important contribution is the study of the aggregation of generalized CP-nets coming from multiple agents, i.e., CP-nets where the precondition of the preference statement is a propositional formula. We use different aggregators to obtain a collective ordering of the possible outcomes. Thanks to this thesis, two lines of research are thus bridged: the one on the aggregation of complete CP-nets, and the one on the generalization of CP-nets to incomplete preconditions. We also contribute to the study of strategic behavior in both collective decision-making and game-theoretic settings. The framework of goal-based voting is studied again under the assumption that agents can now decide to submit an untruthful goal if by doing so they can get a better outcome. The focus is on three majoritarian voting rules which are found to be manipulable. Therefore, we study restrictions on both the language of the goals and on the strategies allowed to the agents to discover islands of strategy-proofness. We also present a game-theoretic extension of a recent model of opinion diffusion over networks of influence. In the influence games defined here, agents hold goals expressed as formulas of LTL and they can choose whether to use their influence power to make sure that their goal is satisfied. Classical solution concepts such as weak dominance and winning strategy are studied for influence games, in relation to the structure of the network and the goals of the agents. Finally, we introduce a novel class of concurrent game structures (CGS) in which agents can have shared control over a set of propositional variables. Such structures are used for the interpretation of formulas of alternating-time temporal logic, thanks to which we can express the existence of a winning strategy for an agent in a repeated game (as, for instance, the influence games mentioned above). The main result shows by means of a clever construction that a CGS with shared control can be represented as a CGS with exclusive control. In conclusion, this thesis provides a valuable contribution to the field of collective decision-making by introducing a novel framework of voting based on individual propositional goals, it studies for the first time the aggregation of generalized CP-nets, it extends a framework of opinion diffusion by modelling rational agents who use their influence power as they see fit, and it provides a reduction of shared to exclusive control in CGS for the interpretation of logics of strategic reasoning. By using different logical languages, agents can thus express their goals and preferences over the decision to be taken, and desirable properties of the decision process can be ensured

APA, Harvard, Vancouver, ISO, and other styles

9

Boucaud, Fabien. "Un agent touchant : modélisation du toucher social dans les interactions humain-agent en environnement immersif." Thesis, Compiègne, 2021. http://www.theses.fr/2021COMP2666.

Full text

Abstract:

Malgré la puissance de nos technologies de communication actuelles pour maintenir du contact social dans des situations extrêmes, elles restent insuffisantes pour totalement combler les sentiments de solitude et d'isolement. Le toucher social, est essentiel au bien-être humain, nous permet de développer et raffermir nos liens relationnels et est un puissant canal de communication des émotions. Le présent travail de thèse s'intéresse à la façon dont on peut munir des agents artificiels de capacités de toucher social. Qu'il s'agisse de robots ou de personnages virtuels, ces nouvelles entités sociales sont déjà équipées de nombreuses modalités d'interaction (paroles, gestes, expressions faciales, etc.), et munir ces nouveaux types d’entités sociales de capacités de toucher pourrait améliorer encore leurs capacités émotionnelles et relationnelles. Plus particulièrement, notre principale question de recherche est de déterminer quand et comment toucher u and allowsn humain de manière utile, autonome et respectueuse. A cet effet, nous proposons une structure théorique et une implémentation fonctionnelle d'un agent touchant capable d'interagir dynamiquement avec un humain en temps réel, au sein d'un environnement immersif. En particulier, nous décrivons un module de perception des comportements de l'humain, un modèle de décision qui prenne en compte la cohérence et l'acceptabilité du toucher en contexte, et une interface haptique SOFTLY qui puisse être utilisée en immersion dans un environnement virtuel. Les évaluations de ces développements mettent en lumière les capacités prometteuses de ce framework, ainsi que ses limites actuelles et perspectives d'amélioration pour des travaux futurs
Despite the current abilities of our communication technologies, they remain unable to completely counterbalance feelings of isolation and loneliness. Social touch is essential to human well-being and allows us to develop and strenghten our relationships. It is also powerful channel of emotional communication. This thesis work is aimed at endowing artificial agents with social touch abilities. Whether they are robotic or virtual artificial agents represent new kinds of social entities and are already equipped with many interactional modalities (speech, gestures, facial expressions, etc.). Endowing them with touching abilities could further enhance their abilities to communicate emotions and to bond with humans. More specifically, our main research question is to determine when and how to touch a human is meaningful, autonomous and respectful way. To answer this question, we propose a theoretical structure and a functional implementation of a touching agent, able to dynamically interact with a human in real-time in an immersive environment. We describe a perception module to detect the human’s behaviour, a decision model able to take coherence and acceptability of touch into account, and a haptic interface (SOFTLY) that can be used in the immersive setup to generate haptic feedback. Evaluations of this framework are discussed and hightlight that its abilities are promising, althought there are still clear avenues of improvement for the model

APA, Harvard, Vancouver, ISO, and other styles

10

Nakamiti, Eduardo Kiochi. "Agentes inteligentes artificiais." Pontifícia Universidade Católica de São Paulo, 2009. https://tede2.pucsp.br/handle/handle/5240.

Full text

Abstract:

Made available in DSpace on 2016-04-26T18:18:07Z (GMT). No. of bitstreams: 1 Eduardo Kiochi Nakamiti.pdf: 508081 bytes, checksum: 823ace52fadc0ffa1e477b48ec078c0f (MD5) Previous issue date: 2009-09-01
The diffusion of Artificial Intelligent Agents, superficially considered as elements that have independent thinking and whose decisions influence processes in the everyday human reality increasingly known, especially in electronic media, the users of banking services, on access to telephone service in our home appliances and entertainment. Its presence is sometimes felt by the ease of access to resources often so powerful and sometimes so unnoticed. It can be perceived in a negative way, when access to electronic banking services is denied without explanation. Much of learning today, relies on Internet and getting information online without the help of search engines is disappointing. Today, these mechanisms offer more than simply the result of a search. They seem to have the intelligence to offer suggestions in relation to our interest. This form of communication that are incorporating to their customs, is strongly influenced by known agents, in computer systems. In this work, we will make a history of its appearance, and technological innovations and cultural, primarily focusing on the first Artificial Intelligence in order to built a clear, detailed view of the Artificial Intelligent Agents, at present, and to establish a hypothetical path for future developments. The methodological basis of work is based on the complexity of the issue addressed. Such complexity refers to tools and distinct views, dynamic and interactive, pointing to the computer and its various aspects, the artificial intelligence and its tools, the cyber arena of interdisciplinarity as the first and, to the environment and the semiotic analysis tool of the production and mediation of knowledge and theories of complexity. The corpus of the analysis and interpretation are circumscribed to the phenomenon of Artificial Intelligent Agents of nowadays and of the future, but for both, and according to the methodology adopted, the fields of knowledge are inspected more in the expectation of higher fidelity description. The main conclusion is the remarkable trend of spraying and increasing invisibility of Artificial Intelligent Agents, as elements of support in decision making and control of the environment and the information we received
A explosão dos Agentes Inteligentes Artificiais, considerados superficialmente como elementos que apresentam raciocínio autônomo e cujas decisões influem processos, é uma realidade cada vez mais sentida no cotidiano dos seres humanos , principalmente nos meios de comunicação eletrônicos, entre usuários de serviços bancários, em acessos a serviços telefônicos, nos eletrodomésticos e em nossos entretenimentos. Sua presença é sentida às vezes pela facilidade de acesso a recursos muitas vezes de forma poderosa ou outras vezes de forma discreta. Também pode ser sentida de forma negativa, quando ocorre o bloqueio de uma operação bancária eletrônica sem explicação. Muito do aprendizado, hoje em dia, passa pela internet, e buscar informação na rede sem a ajuda de mecanismos de busca é desconcertante. Hoje em dia esses mecanismos nos oferecem mais do que simplesmente o resultado de uma procura. Eles parecem ter inteligência própria ao nos oferecer sugestões relacionadas ao nosso interesse. Esta forma de comunicação está se incorporando aos costumes e é fortemente influenciada pelos denominados agentes, contidos nos sistemas. Nesse trabalho, é feito um histórico do seu aparecimento e das inovações tecnológicas e culturais introduzidas, focalizando, primariamente, os primórdios da Inteligência Artificial para que seja construída uma visão clara e detalhada dos agentes inteligentes artificiais até o momento presente, a fim de que seja possível estabelecer uma trajetória hipotética de evolução futura. O referencial teórico do trabalho apóia-se na complexidade do tema abordado. Complexidade que evoca ferramentas e olhares distintos, dinâmicos e interatuantes, apontando para a computação e seus vários aspectos, a inteligência artificial e suas ferramentas; a cibernética como primeira arena de interdisciplinaridade e, atingindo a semiótica como ambiente e ferramenta de análise do processo de produção e mediação do conhecimento e as teorias da complexidade. O corpus da análise e interpretação restringe-se ao fenômeno dos Agentes Inteligentes Artificiais desde sua origem, a partir da inspeção de vários campos de conhecimento, necessários à compreensão do tema abordado. O trabalho levanta a hipótese da tendência marcante de pulverização e invisibilidade crescentes dos Agentes Inteligentes Artificiais, como elementos de apoio na tomada de decisão e controle da informação recebida

APA, Harvard, Vancouver, ISO, and other styles

11

Nongaillard, Antoine. "An agent-based approach for distributed resource allocations." Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2009. http://tel.archives-ouvertes.fr/tel-00831365.

Full text

Abstract:

Resource allocation problems have been widely studied according to various scenarios in literature. In such problems, a set of resources must be allocated to a set of agents, according to their own preferences. Self-organization issues in telecommunication, scheduling problems or supply chain management problems can be modeled using resource allocation problems. Such problems are usually solved by means of centralized techniques, where an omniscient entity determines how to optimally allocate resources. However, these solving methods are not well-adapted for applications where privacy is required. Moreover, several assumptions made are not always plausible, which may prevent their use in practice, especially in the context of agent societies. For instance, dynamic applications require adaptive solving processes, which can handle the evolution of initial data. Such techniques never consider restricted communication possibilities whereas many applications are based on them. For instance, in peer-to-peer networks, a peer can only communicate with a small subset of the systems. In this thesis, we focus on distributed methods to solve resource allocation problems. Initial allocation evolves step by step thanks to local agent negotiations. We seek to provide agent behaviors leading negotiation processes to socially optimal allocations. In this work, resulting resource allocations can be viewed as emergent phenomena. We also identify parameters favoring the negotiation efficiency. We provide the negotiation settings to use when four different social welfare notions are considered. The original method proposed in this thesis is adaptive, anytime and can handle any restriction on agent communication possibilities.

APA, Harvard, Vancouver, ISO, and other styles

12

Marby, Christofer, and Andreas Öberg. "Intelligenta System." Thesis, Högskolan i Borås, Institutionen Handels- och IT-högskolan, 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:hb:diva-20231.

Full text

Abstract:

Intresset för agenter som forskningsområde är någonting relativt nytt. Agenter i sig är en naturlig del av Artificiell intelligens men det är först på senare tid som de hamnat i fokus. Begreppet agent har spridit sig som en löpeld utanför AI-forskningen och kan hittas i många andra områden. Vad detta intresse för agenter kommer ifrån kan debatteras men det är troligtvis dels en följd av att internet visat hur kraftfullt ett distribuerat system kan vara, och att agenter och botar bokar våra biljetter samt söker igenom webbsidor åt oss.Arbetets huvudfråga är att undersöka hur ett intelligent system (för värmedistributionen i ett hus) kan uppnås genom att koppla ihop ett antal agenter med begränsade funktionalitet och distinkta uppgifter. Intelligensen i systemet ska uppnås genom samverkan mellan de olika agenterna. Denna studies förslag för att lösa problemet är en teoristudie av existerande litteratur för designprinciper samt design och implementering av ett exempelsystem, som sedan kommer att simuleras i för att samla in data gällande validitet.Experimentet visade att ett agentsystem kan ge en klar ekonomisk besparing men kommer också med ett relativt högt pris för att implementeras. Om agenterna kan dela infrastruktur genom att installeras samtidigt som ett nytt hus byggs och kan använda tänkt infrastruktur. Dessutom kan besparingen utökas genom att agentsystemet appliceras på en större nybyggnation.

APA, Harvard, Vancouver, ISO, and other styles

13

Franco, Márcia Häfele Islabão. "Mecanismo de interação entre agentes : construção e avaliação de trocas sociais." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2008. http://hdl.handle.net/10183/70700.

Full text

Abstract:

Esta tese apresenta a formalização, construção e validação experimental de um mecanismo de interação entre agentes baseado em valores de troca. Através do mecanismo de interação, os agentes são capazes de estabelecer, avaliar e regular os balanços de troca de suas interações, com o objetivo de alcançar resultados que eles valorizem, i.e., considerem adequados. Na formalização do mecanismo de interação são considerados diversos aspectos abordados nas Ciências Sociais, na Psicologia e em Teorias Utilitaristas. No mecanismo são observados, igualmente, os aspectos sociais e psicológicos que podem influenciar os resultados das interações entre os agentes. Desse modo, o mecanismo leva em consideração que os agentes podem construir suas estratégias levando em consideração as informações relacionadas com o “poder social” e as “atitudes” de interação. No mecanismo de interação recorre-se aos diálogos de argumentação com a finalidade de permitir que os agentes possam influenciar os seus parceiros em relação ao estabelecimento de acordos sobre os serviços e aos valores de troca envolvidos nas interações. Na validação experimental, o cenário utilizado foi o dos “Robôs Coletores de Lixo em Marte”. Através dos resultados obtidos, pode-se observar que o mecanismo de interação considera os valores de troca no processo de formação da cooperação, auxiliando os agentes na escolha de futuros parceiros.
This thesis presents the formalization, construction and validation of an interaction mechanism based on exchange values. Through the interaction mechanism, the agents are capable to establish, to evaluate and to regulate the balances of exchange of their interactions, with the objective of reaching the results that they consider adequate. In the formalization of the mechanism several aspects of Social Sciences, Psychology and Utilitarian Theories are considered. In the mechanism are observed the social and psychological aspects that can influence the results of the interactions between the agents. In this manner, the mechanism considers that the agents can build their strategies considering the information related to the social power and to interaction attitudes. In the mechanism the argument dialogs are used with the purpose to allow the agents to influence their partners in relation to the establishment of agreements about the services and about the exchange values involved in the interactions. In the validation, the scenario used was the “Garbage Collector Robots in Mars”. Through the obtained results, it was possible to observe that the interaction mechanism considers the values of exchange in the process of formation of the cooperation, helping the agents to choose their future partners.

APA, Harvard, Vancouver, ISO, and other styles

14

Veillon, Lise-Marie. "Apprentissage artificiel collectif ; aspects dynamiques et structurels." Thesis, Sorbonne Paris Cité, 2018. http://www.theses.fr/2018USPCD004/document.

Full text

Abstract:

L’apprentissage collectif dans un système multi-agents considère comment une communauté constituée d’agents autonomes partageant un même objectif d’apprentissage peut bénéficier, au niveau individuel et collectif, d’échanges structurés d’informations. Les agents, reliés par un réseau de communication, ont tous la faculté de percevoir des observations, appelées exemples d’apprentissage. Cette thèse s’appuie sur un protocole pré-existant, SMILE (Sound-Multi-agent-Incremental-LEarning), qui organise un échange parcimonieux d’exemples et d’hypothèses. Ce protocole garantit, dans le cas d’agents tous connectés, que les agents obtiennent une hypothèse qui tient compte de tous les exemples perçus par l’ensemble des agents. Il existe des variantes séquentielles de ce protocole qui mettent en place une propagation de l’information pour offrir les mêmes garanties dans un réseau, non pas complet mais, connexe.Cette thèse apporte deux nouveaux éclairages sur l’apprentissage artificiel collectif. Une première étude montre l’influence de la structure du réseau sur l’apprentissage avec un protocole dont les communications sont limitées au voisinage, sans propagation. Une seconde contribution présente et analyse un nouveau protocole, Waves, qui préserve les garanties de SMILE et dont les interactions en parallèle rendent l’apprentissage en réseau plus dynamique. Ce protocole est évalué en détail,dans un contexte simplifié de tour par tour, ce qui permet de le raffiner par la suite avec diverses améliorations. Il est cependant conçu pour s’adapter à un apprentissage en ligne et une acquisition non limitée, ni en temps ni en nombre, de nouveaux exemples par la communauté
Collective learning in multi-agent systems considers how a community of autonomous agents sharing a learning purpose may benefit from exchanging information to learn efficiently as a community as well as individuals. The community forms a communication network where each agent may accesses observations, called learning examples. This thesis is based on a former protocol, SMILE (Sound-Multi-agent-Incremental-LEarning), which sets up parsimonious examples and hypotheses exchanges between agents. In a fully connected community, this protocol guarantees an agent’s hypothesis takes into account all the examples obtained by the community. Some sequential protocols add propagation to SMILE in order to extend this consistency guarantee to other connected networks. This thesis contribution to the artificial collective learning field is two fold.First, we investigate the influence of network structures on learning in networks when communication is limited to neighbourhood without further information propagation. Second, we present and analyze a new protocol, Waves, with SMILE’s guarantees and a more dynamic learning process thanks to its execution in parallel. The evaluation of this protocol in a simple turn-based setting gives the opportunity to improve it here in multiple ways. It is however meant to be used with online learning without any restriction on the acquisition rate of new examples, neither on speed nor number

APA, Harvard, Vancouver, ISO, and other styles

15

Noble, Diego Vrague. "The impact of social context in social problem solving." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2013. http://hdl.handle.net/10183/115613.

Full text

Abstract:

Nossa incapacidade em compreender todos os fatores responsáveis por fenômenos naturais faz com que tenhamos que recorrer a simplificações na representação e na explicação destes. Por sua vez, a forma com que representamos e pensamos a respeito destes fenômenos é influenciada por fatores de natureza interna, como o nosso estado psicológico, ou então de natureza externa, como o ambiente social. Dentre os fatores externos, o ambiente social, ou contexto social, é um dos que tem maior influência na forma que pensamos e agimos. Quando estamos em grupo, mudamos a todo instante a forma com que resolvemos problemas em resposta ao contexto que nos cerca. Entretanto, esta característica até então foi pouco explorada em modelos computacionais de resolução coletiva de problemas. Este trabalho investiga o impacto do contexto social na resolução coletiva de problemas. Nós apresentaremos evidências de que o contexto social tem um papel importante na forma com que o grupo e o indivíduos se comportam. Mais precisamente, nós mostraremos que a centralidade de um indivíduo na rede social nem sempre é um bom preditor de sua contribuição quando o mesmo pode adaptar sua estratégia de busca em resposta ao contexto. Além disso, mostraremos que a adaptação ao contexto social por parte dos indivíduos pode melhorar o desempenho coletivo, facilitando a convergência para soluções boas; e que a diversidade de estratégias de resolução do problema não leva necessariamente a uma diversidade de soluções na população; e que, mesmo que o contexto social seja percebido da mesma forma pelos indivíduos, a forma com que eles reagem pode levar a diferentes resultados. Todos estes resultados suportam a ideia de que o contexto social deve ser considerado em experimentos com resolução social de problemas. Por fim, concluímos o trabalho discutindo o impactso do mesmo e apontando novos problemas a serem investigados.
Our inability to perceive and understand all the factors that account for real-world phenomena forces us to rely on clues when reasoning and making decisions about the world. Clues can be internal such as our psychological state and our motivations; or external, such as the resources available, the physical environment, the social environment, etc. The social environment, or social context, encompasses the set of relationships and cultural settings by which we interact and function in a society. Much of our thinking is influenced by the social environment and we constantly change the way we solve problems in response to our social environment. Nevertheless, this human trait has not been thoughtfully investigated by current computational models of human social problem-solving, for these models have lacked the heterogeneity and self-adaptive behavior observed in humans. In this work, we address this issue by investigating the impact of social context in social problem solving by means of extensive numerical simulations using a modified social model. We show evidences that social context plays a key role in how the system behaves and performs. More precisely, we show that the centrality of an agent in the network is an unreliable predictor the agent’s contribution when this agent can change its problem-solving strategy according to social context. Another finding is that social context information can be used to improve the convergence speed of the group to good solutions and that diversity in search strategies does not necessarily translates into diversity in solutions. We also determine that even if nodes perceive social context in same way, the way they react to it may lead to different outcomes along the search process. Together, these results contribute to the understanding that social context does indeed impact in social problem-solving. We conclude discussing the overall impact of this work and pointing future directions.

APA, Harvard, Vancouver, ISO, and other styles

16

Gomes, Renata Correia Lima Ferreira. "Agentes verossímeis: uma investigação sobre a construção dos personagens autônomos nos videogames." Pontifícia Universidade Católica de São Paulo, 2008. https://tede2.pucsp.br/handle/handle/5142.

Full text

Abstract:

Made available in DSpace on 2016-04-26T18:17:33Z (GMT). No. of bitstreams: 1 Renata Correia Lima Ferreira Gomes.pdf: 13310244 bytes, checksum: 461b70952a77f132a4d560c29c6c5e16 (MD5) Previous issue date: 2008-11-03
Conselho Nacional de Desenvolvimento Científico e Tecnológico
From the conceptual of character-oriented games and of simulation games the present research draws the idea of narrative games as an immersive simulation , to be experienced by the interactor through his or her traversing the virtual space of the game as an implicated character and through his or her interaction with the autonomous characters of the game. We carry through the hypothesis that the key for the implentation of a dramatic strutucture in the game albeit fundamentally different from that of film or theater is in the design of autonomous characters. These we take to be object inhabiting the space-time of the game, carrying a high degree of autonomy, complexity and intentionality, who, through the possibility of empathy, constitute in themselves a pathway towards a dramatic entity with or against whom the interactor has to act. To demonstrate that, we describe narrative as a evolutionary strategy towards a causal mindframe, which evolves side-be-side with the media that materialize it, from oral narratives to 3D interactive digital pieces. A second step toward demonstrating our hypothesis is to describe autonomous characters through Artificial Intelligence applied to narrative: the believable characters . We take as a reference the work of the research groups Oz and Synthetic Characters, and of Brazilian game designer Marcos Cuzziol. Finally, a third step is to approach the nature of the fiction character, through the work of Aristotle and Fernando Segolin, and the concept of empathy, under the approach of Evan Thompson. Empathy here is understood as pre-condition for the comprehension of the Other and of ourselves as affective, emotional and intentional entities. To illustrate this final view, we analyze a few aspects of the Creatures from the games Black & White I e II, in an attempt to point out how some qualities proposed are instantiated
A partir do universo dos games de personagem e games de simulação , a pesquisa em curso pretende descrever a narrativa nos games como uma simulação imersiva , a ser experimentada pelo interator através de seu percurso pelo espaço virtual do game no papel de um personagem e de sua interação com personagens autônomos, operados pelo software. Levamos adiante a hipótese de que a peça-chave para a implementação de uma estrutura dramática no game ainda que fundamentalmente diferente daquela conhecida no cinema e teatro - jaz no design dos personagens autônomos. Estes entendemos como objetos do espaço-tempo virtual, dotados de alto grau de autonomia, complexidade e intencionalidade, que, através da possibilidade de empatia, constituiriam em si o caminho para a emergência de uma vontade dramática com/contra a qual o interator teria que lidar. Para isto, descrevemos a narrativa como uma estratégia evolutiva de pensamento comunicacional e causal, que se desenvolve de acordo com os meios nos quais se materializa, da oralidade primária ao audiovisual digital interativo 3D. Um segundo passo trata de descrever os personagens autônomos, em sua faceta de Inteligência Artificial voltada para games e narrativas interativas: os agentes verossímeis . Para isso, tomamos como referência o trabalho dos grupo de pesquisa Oz e Sythetic Characters, assim como do game designer brasileiro Marcos Cuzziol. Um terceiro passo consiste em abordar a natureza da personagem de ficção a partir de Aristóteles, Fernando Segolin e do conceito de empatia, sobretudo na visão de Evan Thompson, esta entendida como pré-condição para a compreensão do outro e de nós mesmos como entidades afetivas, emocionais e intencionais. Para finalizar, procedemos a uma análise de alguns aspectos das Criaturas dos jogos Black & White I e II, na tentativa de descrever como se instanciam algumas qualidades das propostas anteriores

APA, Harvard, Vancouver, ISO, and other styles

17

Santos, Elder Rizzon. "Uma abordagem baseada em ontologias para a interoperabilidade entre agentes heterogêneos." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2006. http://hdl.handle.net/10183/7839.

Full text

Abstract:

Esta dissertação apresenta a utilização de ontologias como um primeiro passo em direção à interoperabilidade, no nível semântico, entre agentes de diferentes domínios. O contexto de aplicação é um portal educacional chamado PortEdu. Este portal fornece a infra-estrutura e suporte para ambientes de aprendizagem baseados em agentes. O foco deste trabalho é em um agente específico, o agente social, no qual são acrescentadas todas as funcionalidades necessárias para que ele possa interagir com agentes fora de seu contexto. O agente social pertence a um ambiente de aprendizagem multi-agente projetado para apoiar o treinamento do raciocínio, diagnóstico e modelagem de domínios de conhecimento incerto e complexo, como a área médica. Esse ambiente de aprendizagem chama-se AMPLIA. O conhecimento do agente social é modelado através de redes bayesianas, as quais possibilitam ao agente representar seu conhecimento probabilístico e tomar decisões através dele. A representação através de redes bayesianas não foi desenvolvida para ser utilizada no processo de comunicação com outros agentes, o que dificulta a interoperabilidade do agente social com os demais agentes do portal educacional, no qual os ambientes de ensino aprendizagem encontram-se ancorados. A abordagem proposta para fornecer interoperabilidade amplia a arquitetura do agente social possibilitando-o representar seu conhecimento probabilístico através de OWL (Web Ontology Language) e também sua comunicação com agentes externos através de FIPA-ACL (Foundation for Intelligent Physical Agents – Agent Communication Language), linguagem para comunicação utilizada no PortEdu. A OWL não foi projetada para representar incerteza, sendo assim, também foi desenvolvida uma estrutura para possibilitar tal representação em OWL.
This dissertation presents the utilization of ontologies as a first step towards interoperability at the semantic level among agents of different domains. Our test bed is an Educational Portal (PortEdu). This portal provides the infra-structure and support for agent-based learning environments. We focus on a specific agent, the social agent, adding all the necessary functionality for him to interact with agents that aren’t fully aware of its context. The social agent belongs to a Multi-agent Learning Environment designed to support training of diagnostic reasoning and modeling of domains with complex and uncertain knowledge, such as the medical area. This learning environment is called AMPLIA. The knowledge of social agent is implemented with Bayesian networks, which allows the agent to represent its probabilistic knowledge and make its decisions. The representation through Bayesian networks was not designed to be used for communication with other agents, which makes it more difficult for the social agent to interoperate with the agents present in the portal. The approach proposed to supply interoperability extends the social agent’s architecture allowing the representation of his probabilistic knowledge through OWL (Web Ontology Language) and also allows this communication with external agents through FIPA-ACL (Foundation for Intelligent Physical Agents – Agent Communication Language), which is the communication language adopted in PortEdu. OWL was not designed to represent uncertain knowledge, thus, it was also developed a structure to allow such representation in OWL.

APA, Harvard, Vancouver, ISO, and other styles

18

Swift, Adam Glen. "Mapping posthuman discourse and the evolution of living information." Thesis, Queensland University of Technology, 2006. https://eprints.qut.edu.au/16439/1/Adam_Swift_Thesis.pdf.

Full text

Abstract:

The discourse that surrounds and constitutes the post-human emerged as a response to earlier claims of an essential or universal human or human nature. These discussions claim that the human is a discursive construct that emerges from various configurations of nature, embodiment, technology, and culture, configurations that have also been variously shaped by the forces of social history. And in the absence of an essential human figure, post-human discourses suggest that there are no restrictions or limitations on how the human can be reconfigured. This axiom has been extended in light of a plethora of technological reconfigurations and augmentations now potentially available to the human, and claims emerge from within this literature that these new technologies constitute a range of possibilities for future human biological evolution. This thesis questions the assumption contained within these discourses that technological incursions or reconfigurations of the biological human necessarily constitute human biological or human social evolution by discussing the role the evolution theories plays in our understanding of the human, the social, and technology. In this thesis I show that, in a reciprocal process, evolution theory draws metaphors from social institutions and ideologies, while social institutions and ideologies simultaneously draw on metaphors from evolution theory. Through this discussion, I propose a form of evolution literacy; a tool, I argue, is warranted in developing a sophisticated response to changes in both human shape and form. I argue that, as a whole, our understanding of evolution constitutes a metanarrative, a metaphor through which we understand the place of the human within the world; it follows that historical shifts in social paradigms will result in new definitions of evolution. I show that contemporary evolution theory reflects parts of the world as codified informatic systems of associated computational network logic through which the behaviour of participants is predefined according to an evolved or programmed structure. Working from within the discourse of contemporary evolution theory I develop a space through which a version of the post-human figure emerges. I promote this version of the post-human as an Artificial Intelligence computational programme or autonomous agent that, rather than seeking to replace, reduce or deny the human subject, is configured as an exosomatic supplement to and an extension of the biological human.

APA, Harvard, Vancouver, ISO, and other styles

19

Swift, Adam Glen. "Mapping posthuman discourse and the evolution of living information." Queensland University of Technology, 2006. http://eprints.qut.edu.au/16439/.

Full text

Abstract:

The discourse that surrounds and constitutes the post-human emerged as a response to earlier claims of an essential or universal human or human nature. These discussions claim that the human is a discursive construct that emerges from various configurations of nature, embodiment, technology, and culture, configurations that have also been variously shaped by the forces of social history. And in the absence of an essential human figure, post-human discourses suggest that there are no restrictions or limitations on how the human can be reconfigured. This axiom has been extended in light of a plethora of technological reconfigurations and augmentations now potentially available to the human, and claims emerge from within this literature that these new technologies constitute a range of possibilities for future human biological evolution. This thesis questions the assumption contained within these discourses that technological incursions or reconfigurations of the biological human necessarily constitute human biological or human social evolution by discussing the role the evolution theories plays in our understanding of the human, the social, and technology. In this thesis I show that, in a reciprocal process, evolution theory draws metaphors from social institutions and ideologies, while social institutions and ideologies simultaneously draw on metaphors from evolution theory. Through this discussion, I propose a form of evolution literacy; a tool, I argue, is warranted in developing a sophisticated response to changes in both human shape and form. I argue that, as a whole, our understanding of evolution constitutes a metanarrative, a metaphor through which we understand the place of the human within the world; it follows that historical shifts in social paradigms will result in new definitions of evolution. I show that contemporary evolution theory reflects parts of the world as codified informatic systems of associated computational network logic through which the behaviour of participants is predefined according to an evolved or programmed structure. Working from within the discourse of contemporary evolution theory I develop a space through which a version of the post-human figure emerges. I promote this version of the post-human as an Artificial Intelligence computational programme or autonomous agent that, rather than seeking to replace, reduce or deny the human subject, is configured as an exosomatic supplement to and an extension of the biological human.

APA, Harvard, Vancouver, ISO, and other styles

20

Chao, Crystal. "Timing multimodal turn-taking in human-robot cooperative activity." Diss., Georgia Institute of Technology, 2015. http://hdl.handle.net/1853/54904.

Full text

Abstract:

Turn-taking is a fundamental process that governs social interaction. When humans interact, they naturally take initiative and relinquish control to each other using verbal and nonverbal behavior in a coordinated manner. In contrast, existing approaches for controlling a robot's social behavior do not explicitly model turn-taking, resulting in interaction breakdowns that confuse or frustrate the human and detract from the dyad's cooperative goals. They also lack generality, relying on scripted behavior control that must be designed for each new domain. This thesis seeks to enable robots to cooperate fluently with humans by automatically controlling the timing of multimodal turn-taking. Based on our empirical studies of interaction phenomena, we develop a computational turn-taking model that accounts for multimodal information flow and resource usage in interaction. This model is implemented within a novel behavior generation architecture called CADENCE, the Control Architecture for the Dynamics of Embodied Natural Coordination and Engagement, that controls a robot's speech, gesture, gaze, and manipulation. CADENCE controls turn-taking using a timed Petri net (TPN) representation that integrates resource exchange, interruptible modality execution, and modeling of the human user. We demonstrate progressive developments of CADENCE through multiple domains of autonomous interaction encompassing situated dialogue and collaborative manipulation. We also iteratively evaluate improvements in the system using quantitative metrics of task success, fluency, and balance of control.

APA, Harvard, Vancouver, ISO, and other styles

21

Patrix, Jérémy. "Détection de comportements à travers des modèles multi-agents collaboratifs, appliquée à l'évaluation de la situation, notamment en environnement asymétrique avec des données imprécises et incertaines." Phd thesis, Université de Caen, 2013. http://tel.archives-ouvertes.fr/tel-00991091.

Full text

Abstract:

Ce manuscrit de thèse présente une méthode innovante brevetée pour la détection de comportements collectifs. En utilisant des procédés de fusion sur les données issues d'un réseau multi-capteurs, les récents systèmes de surveillance obtiennent les séquences d'observations des personnes surveillées. Ce bas niveau d'évaluation de la situation a été mesuré insuffisant pour aider les forces de sécurité lors des événements de foule. Afin d'avoir une plus haute évaluation de la situation dans ces environnements asymétriques, nous proposons une approche multi-agents qui réduit la complexité du problème par des agents sur trois niveaux - macro, méso et micro - d'observations. Nous utilisons un nouvel état relatif dans les approches de l'état de l'art pour nous permettre la détection, en temps réel, des groupes, de leurs comportements, objectifs et intentions. Dans le cadre de projets européens, nous avons utilisé un serious game simulant une foule dans des scénarios asymétriques. Les résultats montrent un meilleur accord avec les prédictions théoriques et une amélioration significative des travaux précédents. Le travail présenté ici pourrait être utilisé dans de futures études de détection de comportements multi-agents et pourrait un jour aider à résoudre les problèmes liés aux événements catastrophiques de foules incontrôlables.

APA, Harvard, Vancouver, ISO, and other styles

22

Lindkvist, Emilie. "Learning-by-modeling : Novel Computational Approaches for Exploring the Dynamics of Learning and Self-governance in Social-ecological Systems." Doctoral thesis, Stockholms universitet, Stockholm Resilience Centre, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:su:diva-122395.

Full text

Abstract:

As a consequence of global environmental change, sustainable management and governance of natural resources face critical challenges, such as dealing with non-linear dynamics, increased resource variability, and uncertainty. This thesis seeks to address some of these challenges by using simulation models. The first line of research focuses on the use of learning-by-doing (LBD) for managing a renewable resource, exemplified by a fish stock, and explores LBD in a theoretical model using artificial intelligence (Paper I and II). The second line of research focuses on the emergence of different forms of self-governance and their interrelation with the dynamics of trust among fishers when harvesting a shared resource, using an agent-based model. This model is informed by qualitative data based on small-scale fisheries in Mexico (Paper III and IV). Paper I and II find that the most sustainable harvesting strategy requires that the actor values current and future yields equally, cautiously experiments around what is perceived as the best harvest action, and rapidly updates its ‘mental model’ to any perceived change in catch. More specifically, Paper II reveals that understanding these aspects in relation to the type of change can yield not only increased performance, but also, and more importantly, increased robustness to both fast and slow changes in resource dynamics. However, when resource dynamics include the possibility of a more fundamental shift in system characteristics (a regime shift), LBD is problematic due to the potential for crossing a threshold, resulting in possible persistent reductions in harvests (Paper I). In Paper III, results indicate that cooperative forms of self-governance are more likely to establish and persist in communities where fishers’ have prior cooperative experience, fishers’ trustworthiness is more or less equal, and that this likelihood increases when resource availability fluctuates seasonally. Finally, to achieve a transformation toward more cooperative forms of self-governance, interventions are required that can strengthen both financial capital and trust among the members of the cooperatives (Paper IV). The unique contribution of this thesis lies in the method for ‘quantitatively’ studying LBD, the stylized model of a small-scale fishery, and the analysis of the two models to advance our understanding of processes of learning and self-governance in uncertain and variable social-ecological environments. Together, the results shed light on how social and ecological factors and processes co-evolve to shape social-ecological outcomes, as well as contributing to the development of novel methods within the emerging field of sustainability science.
I vårt antropocena tidevarv är ett långsiktigt förvaltarskap av naturresurser inom social-ekologiska system av yttersta vikt. Detta kräver en djup förståelse av människan, ekologin, interaktionerna sinsemellan och deras utveckling över tid. Syftet med denna avhandling är att nå en djupare och mer nyanserad förståelse kring två av grundpelarna inom forskningen av hållbar förvaltning av naturresurser–kontinuerligt lärande genom learning-by-doing (LBD) för att förstå naturresursens dynamik, samt vad som kan kallas socialt kapital, i detta sammanhang i betydelsen tillit mellan individer, som naturligtvis ligger till grund för framgångsrik gemensam förvaltning. Denna föresats operationaliseras genom att använda två olika simuleringsmodeller. Den ena modellen undersöker hur en hållbar förvaltning av en förnyelsebar resurs, i denna avhandling exemplifierad av en fiskepopulation, kan uppnås genom LBD. Den andra modellen söker blottlägga det komplexa sociala samspel som krävs för att praktisera gemensam förvaltning genom att använda ett fiskesamhälle som fallstudie. Tidigare forskning på båda dessa två områden är relativt omfattade. Emellertid har den forskning som specialiserat sig på LBD i huvudsak inskränkt sig till empiriska fallstudier. Vad som bryter ny mark i denna avhandling är att vi konstruerar en simuleringsmodell av LBD där vi kan studera lärandeprocessen i detalj för att uppnå en mer hållbar förvaltning över tid. Beträffande modellen som behandlar socialt kapital så har tidigare forskning fokuserat på hur en organisation, eller grupp, kan uppnå hållbar förvaltning. Dock saknas ett helhetsgrepp där som tar hänsyn till alla nivåer; från individnivå (mikro), via gruppnivå (meso), till samhällsnivå (makro). Detta är något som denna avhandling försöker avhjälpa genom att undersöka betydelsen av individers egenskaper, uppbyggnaden av socialt kapital, samt hur detta påverkar emergens av ett samhälle dominerat av mer kooperativa förvaltningsformer respektive mer hierarkiska diton. I papper I and II studeras kärnan av LBD som återkoppling mellan en aktör och en resurs, där aktören lär sig genom upprepade interaktioner med en resurs. Resultaten visar att LBD är av avgörande betydelse för en hållbar förvaltning, speciellt då naturresursens dynamik är stadd i förändring. I den mest hållbara strategin bör aktören värdera nuvarande och framtida fångster lika högt, försiktigt experimentera kring vad aktören upplever som bästa strategi, för att sedan anpassa sin mentala modell till upplevda förändringar i fångst relativt dess insats någorlunda kraftigt. I papper III och IV behandlas uppbyggnaden av förtroende mellan individer och grupp, samt själv-organiserat styre. Genom att använda småskaligt fiske i Mexiko som en illustrativ fallstudie, utvecklades en agent-baserad modell av ett arketypiskt småskaligt fiskesamhälle. Resultaten indikerar att kooperativa förvaltningsformer är mer dominanta i samhällen där de som utför fisket har liknande pålitlighet, starkt gemensamt socialt kapital vid kooperativets start, och då resursen fluktuerar säsongsmässigt (papper III). Papper IV visar att för att uppnå en transformation från hierarkiska förvaltningsformer till kooperativa diton krävs interventioner som inriktar sig på både socialt och finansiellt kapital. Denna avhandling bidrar således till en djupare förståelse kring hur socialt kapital växer fram, samt hur mer strategiska LBD processer bör utformas när abrupta och osäkra förändringar i ekosystemen blir allt vanligare på grund av människans ökade tryck på planeten.

At the time of the doctoral defense, the following papers were unpublished and had a status as follows: Paper 2: Submitted. Paper 3: Submitted. Paper 4: Manuscript.

APA, Harvard, Vancouver, ISO, and other styles

23

Morales-Rodríguez, Maria Lucila. "Modèle d'interaction sociale pour des agents conversationnels animés : Application à la rééducation de patients cérébro-lésés." Phd thesis, Université Paul Sabatier - Toulouse III, 2007. http://tel.archives-ouvertes.fr/tel-00660114.

Full text

Abstract:

L'interaction sociale en univers virtuel ouvre de nouveaux horizons dans le domaine des technologies de l'information et en particulier de l'usage des jeux vidéo à des fins professionnelles (" serious game "). En introduisant la possibilité de gérer avec un certain niveau de réalisme des interactions sociales et émotionnelles entre les agents conversationnels animés (ACA) représentant des acteurs humains, cette approche permet d'envisager de nombreuses applications professionnelles qui jusqu'alors ne pouvaient être envisagées que dans le cadre domaine de l'interaction homme-homme. La difficulté principale de cette approche est de produire une dynamique des interactions humaines qui ait un sens dans le cadre des taches et des actions qui doivent être accomplies par les acteurs. Afin d'ancrer théoriquement cette question, nous avons fait référence aux approches de la cognition située (afin de prendre en compte le rôle médiateur des objets de l'environnement) et aux approches représentationnelles pour la production des actes de langage. Le contexte applicatif de ce travail de recherche concerne la rééducation de patients cérébro-lésés. Dans un premier temps, nous nous sommes intéressés à la description de la dynamique des interactions visuelles, gestuelles, verbales entre un patient et un véritable thérapeute. Cette étude nous a permis de catégoriser les différentes phases de dialogue et d'élaborer un modèle de la dynamique de l'interaction prenant en compte la personnalité des acteurs, leurs intentions, leurs comportements gestuels et verbal. A partir de ce modèle, nous avons élaboré une architecture informatique générique qui s'articule autour d'un modèle comportemental et d'un modèle kinésique. Le modèle comportemental sélectionne les actes de langage et l'attitude du personnage (empathique, neutre, etc.). Le modèle kinésique gère les expressions faciales, corporelles et gestuelles résultant du modèle comportemental. D'un point de vue théorique, nous nous sommes intéressés à la notion de présence afin d'identifier quelle était la nature des couplages pertinents permettant de produire un sentiment de présence sociale (sentiment pour les acteurs humains qui animent leurs avatars de vivre une interaction sociale non médiatisée par les éléments du dispositif technique). Enfin, le dispositif a été utilisé dans le cadre d'un programme de recherche sur le concept de neurone miroir. L'hypothèse étant que la présentation au patient d'une image virtuelle de son membre handicapé lui permettrait de mieux récupérer. Des tests IRMf associés à chaque expérience devrait permettait de confirmer ou d'infirmer le rôle de ces neurones miroir dans le processus de récupération.

APA, Harvard, Vancouver, ISO, and other styles

24

Johansson, Nelly, and Lin Haspel. "Kan en självkörande bil vara en etisk agent?" Thesis, Umeå universitet, Institutionen för informatik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-171030.

Full text

Abstract:

The purpose of this study is to investigate important prerequisites for how self-driving cars should/can be programmed from an ethical point of view and to examine how individuals reason about how self-driving cars should act in situations where accidents are inevitable. Artificial intelligence is generally a major area where ethics and morals are important factors to relate to. As the area is so wide, a demarcation has been made for self-driving cars, with the aim of being able to generate increased understanding of the wider context. To answer the question "Can a self-driving car be an ethical agent?" a qualitative method approach has been used. Based on moral-philosophical theories, ethically difficult scenarios have been constructed that respondents have had to take a position on and motivate their positions in the form of semi-structured interviews. The result of the study shows that as different individuals reason differently about what is actually an ethical right act in different situations, it is difficult to determine how a car should act to be classified as an ethical agent. It also turns out that one and the same individual in different situations has different moral-philosophical theories as a starting point because of different influencing factors. This in turn shows that ethical positions are extremely situated, which contributes to an enormous complexity of the phenomenon.

APA, Harvard, Vancouver, ISO, and other styles

25

Lugo, Gustavo Alberto Giménez. "Um modelo de sistemas multiagentes para partilha de conhecimento utilizando redes sociais comunitárias." Universidade de São Paulo, 2004. http://www.teses.usp.br/teses/disponiveis/3/3141/tde-15112004-190053/.

Full text

Abstract:

Este trabalho apresenta um modelo para sistemas multiagentes constituídos por agentes de informação destinados a auxiliar comunidades humanas que partilham conhecimento. Tais agentes são cientes do entorno social dos usuários, pois possuem representações do conhecimento dos mesmos e também das redes sociais que os circundam, organizadas subjetivamente. Conceitos pertencentes às suas ontologias são estendidos com informação organizacional para representar de forma explícita as situações nas quais foram aprendidos e utilizados. Discute-se como tais agentes autônomos podem raciocinar sobre o uso e a privacidade de conceitos em termos de construções organizacionais, possibilitando raciocinar sobre papéis sociais em comunidades abertas na Internet.
This work presents a model for multi-agent systems for information agents supporting information-sharing communities. Such agents are socially aware in the sense that they have representations of the users' knowledge and also of their social networks, which are subjectively organized. Concepts in their ontologies are extended with organizational information to record explicitly the situations in which they were learned and used. It is discussed how such autonomous agents are allowed to reason about concept usage and privacy in terms of organizational constructs, paving the way to reason about social roles in open Internet communities.

APA, Harvard, Vancouver, ISO, and other styles

26

Thellman, Sam. "Social Dimensions of Robotic versus Virtual Embodiment, Presence and Influence." Thesis, Linköpings universitet, Interaktiva och kognitiva system, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-130645.

Full text

Abstract:

Robots and virtual agents grow rapidly in behavioural sophistication and complexity. They become better learners and teachers, cooperators and communicators, workers and companions. These artefacts – whose behaviours are not always readily understood by human intuition nor comprehensibly explained in terms of mechanism – will have to interact socially. Moving beyond artificial rational systems to artificial social systems means having to engage with fundamental questions about agenthood, sociality, intelligence, and the relationship between mind and body. It also means having to revise our theories about these things in the course of continuously assessing the social sufficiency of existing artificial social agents. The present thesis presents an empirical study investigating the social influence of physical versus virtual embodiment on people's decisions in the context of a bargaining task. The results indicate that agent embodiment did not affect the social influence of the agent or the extent to which it was perceived as a social actor. However, participants' perception of the agent as a social actor did influence their decisions. This suggests that experimental results from studies comparing different robot embodiments should not be over-generalised beyond the particular task domain in which the studied interactions took place.

APA, Harvard, Vancouver, ISO, and other styles

27

Bjärehall, Johannes, and Johan Hallberg. "Återskapa mänskligt beteende med artificiell intelligens i 2D top-down wave shooter spel." Thesis, Högskolan i Skövde, Institutionen för informationsteknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:his:diva-18708.

Full text

Abstract:

Arbetet undersöker mänskligt beteende hos beteendeträd och LSTM nätverk. Ett spel skapades som testades av personer i en undersökning där deltagarna fick spela tillsammans med vardera agent i slumpmässig ordning för att bedöma agenternas beteende. Resultatet från undersökningen visade att beteendeträdet var den mänskliga varianten enligt deltagarna oavsett ordning som testpersonerna spelade med vardera agent. Problemet med resultatet beror antagligen till störst del på att det inte fanns tillräckligt med tid och bristande CPU kraft för att utveckla LSTM agenten ytterligare. För att förbättra och arbeta vidare med arbetet kan mer tid läggas på att träna LSTM nätverket och finjustera beteendeträdet. För att förbättra testet borde riktig multiplayer funktionalitet implementeras som gör att det går att testa agenterna jämfört med riktiga mänskliga spelare.

APA, Harvard, Vancouver, ISO, and other styles

28

Invartsen, Mette. "EXPANDED CHOREOGRAPHY : Shifting the agency of movement in The Artificial Nature Project and 69 positions." Doctoral thesis, Stockholms konstnärliga högskola, Institutionen för dans, 2016. http://urn.kb.se/resolve?urn=urn:nbn:se:uniarts:diva-177.

Full text

Abstract:

Through two books and a series of video documentations of live performances Mette Ingvartsen makes choreography into a territory of physical, artistic and social experimentation. The Artificial Nature Series focusses on how relations between human and non-human agency can be explored and reconfigured through choreography. By investigating and creating a ‘nonhuman theater’ questions regarding material agency, ecology, natural disasters, the Anthropocene and non-subjective performativity are posed. The resulting reflections are closely related to the poetic principles utilized to create the performances, while also drawing connections to territories outside theater. By contrast, 69 positions inscribes itself into a history of human performance with afocus on nudity, sexuality and how the body historically has been a site for political struggles. By creating a guided tour through sexual performances – from the naked protest actions of the 1960’s, through an archive ofpersonal performances into a reflection on contemporary sexual practice – this solo work rethinks audience participation and proposes a notion of soft and social choreography. The contrasting performative strategiesarticulate a twofold notion of expanded choreography: on the one hand movement is extended beyond the human body by including the agency of nonhuman performers, and on the other hand, movement is expanded into animaginary and virtual space thanks to ‘language choreography’.

LINKS

https://vimeo.com/164552586

https://vimeo.com/164558381

APA, Harvard, Vancouver, ISO, and other styles

29

Ribeiro, Richardson. "Análise do impacto da teoria das redes sociais em técnicas de otimmização e aprendezagem multiagente baseada em recompensas / Richardson Ribeiro, orientador, Fabrício Enembreck." reponame:Biblioteca Digital de Teses e Dissertações da PUC_PR, 2010. http://www.biblioteca.pucpr.br/tede/tde_busca/arquivo.php?codArquivo=2377.

Full text

Abstract:

Tese (doutorado) - Pontifícia Universidade Católica do Paraná, Curitiba, 2010
Bibliografia: f. 181-201
Este trabalho é dedicado ao estudo da aplicação das teorias sociais para a construção de estruturas de relacionamento capazes de influenciar comportamentos locais gerados a partir de recompensas em indivíduos de um sistema multiagente. A interação entre m
This work is dedicated to study the application of the social theories to the construction of relationships structures able to influence local behaviors generated from individuals? rewards of a multiagent system. The interaction between coordination model

APA, Harvard, Vancouver, ISO, and other styles

30

Ferreira, Júnior Paulo Roberto. "Coordenação de sistemas multiagente atuando em cenários complexos : uma abordagem baseada na divisão de trabalho dos insetos sociais." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2008. http://hdl.handle.net/10183/13653.

Full text

Abstract:

Agentes atuando em sociedade devem agir de maneira coerente para atingir um objetivo comum. A coordenação nos sistemas multiagente previne o comportamento caótico dos agentes, permite que o sistema lide com restrições globais e a interdependência entre os agentes, e faz com que o sistema possa ser composto por agentes com diferentes competências. A coordenação pode ser baseada na estrutura organizacional, onde a comunidade de agentes atua a favor de um objetivo comum através da forma como estão organizados. Em ambientes dinâmicos a organização dos agentes deve se adaptar a mudanças nos objetivos do sistema, na disponibilidade de recursos, nos relacionamentos entre os agentes, e assim por diante. Esta flexibilidade é um problema chave nos sistemas multiagente e está relacionada a modelos de adaptação como os observados nos insetos sociais. O presente trabalho propõe uma abordagem para a geração e adaptação da organização de um sistema multiagente, em tempo de execução, utilizando como base os modelos teóricos de organização das colônias de insetos sociais. Esta abordagem enfoca a alocação e o escalonamento dinâmicos de tarefas distribuídos entre agentes com diferentes competências e em ambientes de larga escala. Dois cenários principais são utilizados para experimentar e validar a abordagem proposta. Estes cenários estão baseados em problemas de pesquisa operacional denominados Resource-Constrained Project Scheduling Problem (RCPSP) e o Generalized Assignment Problem (GAP). Este trabalho contribui para o avanço do estado-da-arte no estudo e desenvolvimento de sistemas multiagente e na modelagem e aplicação de técnicas de inteligência de enxames em problemas computacionais. A abordagem proposta para coordenação de agentes em cenários complexos é nova, eficaz e robusta. De maneira geral, esta abordagem contribui para busca da solução de problemas de coordenação de sistemas multiagente aplicados a problemas reais.
A community of individual agents must work in a coherent manner to reach some common goal. The coordination process in multiagent systems prevents chaotic behavior of agents, makes the system able to deal with global constraints and inter-agents dependencies, and allows the system to be composed of agents with different capabilities. This process is normally based on the organizational structure, where the community of agents works towards the system goal through the manner they are organized. However, in dynamic environments, agents must be able to adapt to the changing goals of the system, to the resources available, to their relationships with another agents, to changes on the environment and so on. This problem is a key one in multiagent systems and relates to models of adaptation, such as those observed among social insects. This work proposes a new approach to generate and adapt the multiagent organization on the fly based on the theoretical models of social insects colonies organization. This approach focuses on distributed dynamic scheduling and task allocation using agents with different capabilities in large scale environments. Two main scenarios have been used to experiment and validate the proposed approach: the Resource-Constrained Project Scheduling Problem (RCPSP) and the Generalized Assignment Problem (GAP). This work contributes to advancing the state-of-the-art in the study and development of multiagent systems and in the modeling and application of swarm intelligence techniques. The proposed approach to coordinate agents in complex scenarios is novel, effective and robust. This approach contributes to the search of coordination solutions to multiagent systems real applications.

APA, Harvard, Vancouver, ISO, and other styles

31

Öhlund, Linnea. "Sociala agenter på arbetsplatsen - Vem gör jobbet ? : En kvalitativ studie om AI-roboten som den nya arbetaren." Thesis, Umeå universitet, Institutionen för informatik, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-159325.

Full text

Abstract:

The future workplace may not be a place just for human workers but will likely be filled with artificial intelligence, robots and agents being colleagues instead of tools. In some industries where a shortage of personal is a central issue, digitalization in various fields can be explored as a mean to help. This study aims to discover different aspects regarding a social agent that has been implemented at a dental clinic with a purpose to preform different tasks that is normally regarded as human tasks. By conducting interviews and observations it was possible to shine light at a variation of underlying factors to take in to consideration when implementing such an agent at a workplace. The study showed that even if an agent is capable to help people with their questions and tasks many users chose other alternatives that did not include getting help from the agent but instead meant that they used other alternatives.

APA, Harvard, Vancouver, ISO, and other styles

32

Moussa, Richard. "SEGMENTATION MULTI-AGENTS EN IMAGERIE BIOLOGIQUE ET MÉDICALE : APPLICATION AUX IRM 3D." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2011. http://tel.archives-ouvertes.fr/tel-00652445.

Full text

Abstract:

La segmentation d'images est une opération cruciale pour le traitement d'images. Elle est toujours le point de départ des processus d'analyse de formes, de détection de mouvement, de visualisation, des estimations quantitatives de distances linéaires, de surfaces et de volumes. À ces fins, la segmentation consiste à catégoriser les voxels en des classes basées sur leurs intensités locales, leur localisation spatiale et leurs caractéristiques de forme ou de voisinage. La difficulté de la stabilité des résultats des méthodes de segmentation pour les images médicales provient des différents types de bruit présents. Dans ces images, le bruit prend deux formes : un bruit physique dû au système d'acquisition, dans notre cas l'IRM (Imagerie par Résonance Magnétique), et le bruit physiologique dû au patient. Ces bruits doivent être pris en compte pour toutes les méthodes de segmentation d'images. Durant cette thèse, nous nous sommes focalisés sur des modèles Multi-Agents basés sur les comportements biologiques des araignées et des fourmis pour effectuer la tâche de segmentation. Pour les araignées, nous avons proposé une approche semi-automatique utilisant l'histogramme de l'image pour déterminer le nombre d'objets à détecter. Tandis que pour les fourmis, nous avons proposé deux approches : la première dite classique qui utilise le gradient de l'image et la deuxième, plus originale, qui utilise une partition intervoxel de l'image. Nous avons également proposé un moyen pour accélérer le processus de segmentation grâce à l'utilisation des GPU (Graphics Processing Unit). Finalement, ces deux méthodes ont été évaluées sur des images d'IRM de cerveau et elles ont été comparées aux méthodes classiques de segmentation : croissance de régions et Otsu pour le modèle des araignées et le gradient de Sobel pour les fourmis.

APA, Harvard, Vancouver, ISO, and other styles

33

Okuyama, Fabio Yoshimitsu. "Modelo MAS-SOC : integrando ambientes e organizações para simulações baseadas em sistemas multiagentes situados." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2008. http://hdl.handle.net/10183/18646.

Full text

Abstract:

Este trabalho encontra-se situado na área de Inteligência Artificial, mais especificamente na modelagem de Sistemas Multiagentes destinados à simulação social. A área de pesquisa de simulação social baseada em agentes é uma área recente e bastante promissora. Por tratar de problemas extremamente complexos, existe a necessidade de criar modelos e abstrações para possibilitar sua realização. Dando continuidade a trabalhos anteriores, esta tese pretende consolidar uma nova versão do modelo MAS-SOC, destinado à definição de simulações sociais baseada em Sistemas Multiagentes Situados, com organizações que funcionam em ambientes determinados (organizações situadas). É proposta uma abordagem integrada, que conecta de maneira forte as entidades agentes, organizações e ambiente, sendo os agentes, o ambiente e as estruturas da organização tratadas como entidades de primeira ordem. A definição do ambiente é feita através da linguagem ELMS, estendida com uma infraestrutura normativa. Esta infraestrutura normativa é composta basicamente por objetos normativos e espaços normativos que permitem a distribuição espacial da informação normativa no ambiente, possibilitando a contextualização das normas que os agentes devem seguir em um escopo espacial determinado. A contextualização das normas facilita a sua operacionalização e a verificação de conformidade, reduzindo também a possibilidade de interpretações errôneas das normas. Com isso, a infraestrutura normativa conecta ambiente físico à estrutura da organização do sistema multiagente. Além disso, o modelo proposto usa um esquema mínimo de definição das organizações para armazenar informações e restrições que o projetista da simulação prefira representar desta forma. Esta maneira integrada de modelar os sistemas multiagentes, associando a organização ao espaço em que a organização deve funcionar, pode facilitar a modelagem de grandes sistemas, pois o conceito de espaço normativo permite que a modelagem seja feita através da partição do ambiente físico em módulos onde as atividades da organização situada são realizadas. Assim, o modelo trata de forma bastante prática o uso das normas organizacionais que podem ser representadas através de objetos normativos. Esta forma de representação possibilita aos agentes decidirem sobre a aderência as normas, já que estas não estão embutidas no mecanismo de raciocínio dos agentes. Além disso, a forma contextualizada das normas facilita raciocínio sobre elas e possibilita a aderência a normas previamente desconhecidas pelos agentes.
This work is situated in the research area of Artificial Intelligence, specifically the modelling of Multi-agent systems for social simulation. The research area of agent based social simulation is a recent and interesting area. In order to handle with its very complex problems, it requires the development of models and abstractions to make possible its realisation. Continuing previous works, this thesis aims to consolidate extensions to the MAS-SOC model, in order to turn it into a suitable model for the social simulation based on situated multi-agent systems with organizations that operate in determined environments (situated organisations). It is proposed an integrated approach in which multiagent entities such as agents, organisations and environments are strongly connected to each other, and the environment and the organisational structures being treated as first order entities. The definition of the environment is made with the use of the ELMS language, which have been extended with a normative infrastructure. The normative infrastructure is composed essentially by normative objects and normative places, which are means for the spatial distribution of the normative information over the environment, allowing the contextualisation of the norms in a bounded spatial scope. The norms being bounded in a specific spatial scope facilitates its operationalisation and conformity checks, also reducing the possibilities of norms misinterpretations. Thus, the normative infrastructure connects the physical environment to the organisational structures of the multiagent system. The thesis proposes that this integrated approach to model multi-agent systems may ease the modelling of large scale systems, since it allows the partition of the environment in a modular way, facilitating the operationalisation and verification of the adequacy of the structure of an organisation to the physical space where it is located, and also reducing the possibility of the misinterpretations of norms by the agents, through the contextualisation of norms. Also, the proposed scheme uses a minimal structure for the definition of the organisations in order to store information that the simulation designer prefers to represent in such way. Further, the proposed approach allows a very practical way to use of norms in a physical environment, by allowing the agents to reason about following a norm abiding behaviour or not, since the norms are not hard-wired in their reasoning mechanisms, and its contextualized form facilitates that agents reason about adhering to norms that were previously unknown to them.

APA, Harvard, Vancouver, ISO, and other styles

34

Buche, Cédric. "Adaptive behaviors for virtual entities in participatory virtual environments." Habilitation à diriger des recherches, Université de Bretagne occidentale - Brest, 2012. http://tel.archives-ouvertes.fr/tel-00672518.

Full text

Abstract:

Le CERV constitue à Brest un pôle d'excellence en réalité virtuelle à vocation européenne. Les systèmes que l'on cherche à modéliser sont de plus en plus complexes, du fait essentiellement de la diversité des composants, de la diversité des structures et de la diversité des interactions mises en jeu. Un système est alors a priori un milieu ouvert (apparition/disparition dynamique de composants) et hétérogène (morphologies et comportements variés). La réalité virtuelle implique pleinement l'utilisateur humain dans la simulation, rejoignant ainsi l'approche de la conception. La majorité des travaux en réalité virtuelle concerne l'immersion sensorimotrice de l'utilisateur humain au sein d'univers. Ces univers virtuels offrent à l'utilisateur la sensation d'être dans l'environnement et lui donne la possibilité d'y agir. Pour être complet, il faut également "qu'il s'y passe quelque chose", et pas seulement en terme de résultat des actions de l'utilisateur. Les entités qui peuplent les univers virtuels doivent donc avoir un comportement autonome. Ceci soulève la question suivante : comment doter une entité d'un comportement autonome dans un environnement virtuel complexe auquel l'homme participe ? Des techniques d'intelligence artificielle symbolique ont déjà été appliquées pour définir ces comportements. Mais ces techniques montrent très vite leurs limites car elles sont principalement basées sur des règles de comportements mises a priori par le concepteur. Or, dans des mondes virtuels complexes (simulation ouverte, hétérogène et participative), plusieurs entités vont avoir des comportements imprédictibles (variabilité comportementale des entités autonomes, libre arbitre de l'utilisateur), créant ainsi des situations toujours nouvelles. Et face à une situation non prévue par le programmeur, les entités auront le plus souvent des comportements inadaptés. C'est pourquoi les méthodologies tirées des systèmes artificiels adaptatifs peuvent contribuer à pallier ces limitations. Le travail que je poursuis porte sur la thématique de l'adaptation de comportements d'entités autonomes en environnement virtuel participatif. Adapter son comportement, c'est effectuer des transformations conduisant à s'adapter à son environnement. Cette adaptation aura pour objectif de rendre le comportement de l'entité virtuelle le plus crédible possible (ressemblant à un comportement humain). Pour cela, nous prenons le parti de considérer que l'entité doit apprendre au fur et à mesure des expériences, elle doit anticiper le comportement des autres entités et les conséquences sur l'environnement, elle doit également exploiter la présence de l'utilisateur humain dans l'univers virtuel pour adapter son comportement. Imaginons un monde virtuel où chaque entité, au même titre qu'un humain, aurait son propre comportement qui évolue automatiquement pendant la simulation. C'est tout l'enjeu des travaux de recherche présentés ici.

APA, Harvard, Vancouver, ISO, and other styles

35

Meany, Michael M. "The performance of comedy by artificial intelligence agents." Thesis, 2014. https://vuir.vu.edu.au/25825/.

Full text

Abstract:

The PhD project is composed of two parts: a creative project (thirty-five per cent of the total research project); and an exegesis (sixty-five per cent). The creative project employs a pair of chat-bots, natural language processing artificial intelligence agents, to act as comedian and straight-man in a comedy performance based on a topic supplied by the user in a web-based interface. This is an interdisciplinary project that draws on the domains of humour theory, creativity theory, creative writing, and human-computer interaction theory to illuminate the practice of comedy scriptwriting process in a new-media environment.

APA, Harvard, Vancouver, ISO, and other styles

36

Couto, Daniela Gaspar. "Artificial intelligence and human values." Master's thesis, 2018. http://hdl.handle.net/10071/18291.

Full text

Abstract:

Artificial Intelligence (AI) is increasingly used in daily life. Where once decisions and choices were left to human management, technology now plays a much more incisive role. This topic has spawned several diverging and alarming opinions (e.g. Elon Musk and Stephen Hawkings), due to the various ethical susceptibilities that AI development spans. The present study attempts to perceive whether human values influence individuals’ attitudes towards AI evolution. This technology is exposed in several different contexts: in the chance that AI threatens each one of the values; the opposite case, where AI is beneficial; in the need (or lack thereof) for the presence of regulatory agents, and whether that changed people's initial decision. With a sample of 205 participants, and through quantitative methodology (questionnaire), as well as qualitative (semi-structured interviews), the conclusion is that equality, freedom, health and national security constitute a predictive power when it comes to the attitudes that individuals nurture towards AI evolution. More specifically, in the event that AI threatens equality, people develop unfavourable attitudes towards its evolution. The same happens for freedom, where people are also against AI evolution, whether it benefits or threatens human values. People tend to be in favour of AI evolution if it benefits health, but require the presence of regulatory agents. Lastly, the attitudes towards AI evolution are positive if it benefits national security. People still demonstrate generally positive attitudes in the event that this value is threatened by AI, but require the presence of regulatory agents.
A inteligência artificial (IA) é cada vez mais utilizada na vida quotidiana, em que onde as decisões e escolhas eram deixadas à gestão humana, a tecnologia assume agora um papel mais incisivo nessa questão. Esta temática tem sido motivo para várias opiniões divergentes e alarmísticas (e.g. Elon Musk e Stephen Hawkings), devido às várias suscetibilidades éticas que o desenvolvimento da IA abarca. O presente estudo procura percecionar se os valores humanos influenciam as atitudes que os indivíduos têm para com a evolução da IA. Esta tecnologia é exposta em vários contextos: no caso da IA ameaçar cada um dos valores; no caso oposto, de a mesma os beneficiar; na necessidade ou não da presença de agentes reguladores, e se os mesmos de alguma forma alteravam a sua decisão inicial. Com uma amostra de 205 participantes, através de uma metodologia quantitativa (questionário) e qualitativa (entrevistas semiestruturadas), concluiu-se que a igualdade, a liberdade, a saúde e a segurança nacional constituem um poder preditivo relativamente às atitudes que os indivíduos têm face à evolução da IA. Mais especificamente, se a IA ameaçar a igualdade surgem atitudes desfavoráveis à sua evolução, igualmente, no caso da liberdade as pessoas também são contra à evolução da IA, mesmo que ela beneficie ou ameace os valores humanos. A saúde se for beneficiada pela IA, a pessoas tendem a ser a favor da sua evolução, mas sempre com a presença de agentes reguladores. Por fim, se a IA beneficiar a segurança nacional, surgem atitudes positivas face à sua evolução, bem como, se a IA ameaçar o mesmo valor as pessoas continuam a demonstrar atitudes positivas, mas exigem a presença de agentes reguladores.

APA, Harvard, Vancouver, ISO, and other styles

37

"Data Driven Inference in Populations of Agents." Doctoral diss., 2019. http://hdl.handle.net/2286/R.I.53476.

Full text

Abstract:

abstract: In the artificial intelligence literature, three forms of reasoning are commonly employed to understand agent behavior: inductive, deductive, and abductive. More recently, data-driven approaches leveraging ideas such as machine learning, data mining, and social network analysis have gained popularity. While data-driven variants of the aforementioned forms of reasoning have been applied separately, there is little work on how data-driven approaches across all three forms relate and lend themselves to practical applications. Given an agent behavior and the percept sequence, how one can identify a specific outcome such as the likeliest explanation? To address real-world problems, it is vital to understand the different types of reasonings which can lead to better data-driven inference. This dissertation has laid the groundwork for studying these relationships and applying them to three real-world problems. In criminal modeling, inductive and deductive reasonings are applied to early prediction of violent criminal gang members. To address this problem the features derived from the co-arrestee social network as well as geographical and temporal features are leveraged. Then, a data-driven variant of geospatial abductive inference is studied in missing person problem to locate the missing person. Finally, induction and abduction reasonings are studied for identifying pathogenic accounts of a cascade in social networks.
Dissertation/Thesis
Doctoral Dissertation Computer Science 2019

APA, Harvard, Vancouver, ISO, and other styles

38

Sousa, Francisco Pedroso de. "The impact of social virtual presence agents and content-based product recommendation system on on-line customer purchase intention." Master's thesis, 2020. http://hdl.handle.net/10071/21615.

Full text

Abstract:

The appearance of the digital market came as turning point factor, obligating companies to maintain the relationship with consumers by improving and keeping a high technological innovativeness on-line overall experience. The lack of studies on antropomorphization of virtual voice assistances chatbot and the possibilities, yet to be found, on customized product recommendation system variation integration, brought the author to this study. The aim of this research is to investigate the effects of using two different chatbot social virtual presences interactions: with a fully pre-recorded computed personification agent versus with a pre-recorded human social virtual agent; and also understand how having a customized content-based product recommendation system can influence the consumers purchase intention at on-line shopping framework. An on-line platform was developed, recreating a possible virtual store interaction, and the core data was treated using a PLS-SEM model. The results indicate that Human Social Virtual Presence Agent, while assisting the shoppers, have a larger model positive effect on Intellectual stimulus and Hedonic Benefits than a computed personification Agent. This might be explained by the fact that computed imagery and sound Agent was perceived with some amount of emotional creepiness by the participants. Also, recommendation system presence is impacting customers purchase intention on a positive way when compared with not using recommendation system. Thus, this study shows how relevant social interactions are for the customers, especially when done by a human, and how recommendation system has an impact on customers purchase intention.
Com o aparecimento do mercado "on-line", as empresas que quiseram manter uma relação de qualidade com os seus clientes, tiveram de investir no desenvolvimento de uma experiência de utilizador de qualidade e manter um olhar atento na inovação. A falta de estudos relativos à antropomorfização em "chatbots" virtuais e as possibilidades, ainda por descobrir, do sistema de recomendação de produtos à medida de cada utilizador, trouxeram o autor ao tema deste estudo. O seu objetivo é investigar os efeitos de dois tipos de presença social em "chatbots": uma presença virtual computada versus uma presença virtual humana; e como o sistema de recomendação de produtos à medida de cada utilizador influencia a intenção de compra dos consumidores nas lojas "on-line". Para tal, foi desenvolvida uma plataforma "on-line", recriando uma possível interação em loja virtual. Os dados foram tratados utilizando o modelo PLS-SEM. Os resultados indicam que a presença social virtual feita por um agente humano melhora substancialmente o estímulo intelectual feito pela marca e os seus benefícios hedónicos, quando comparado com um agente virtual computado. Tal resultado pode ser explicado pelo facto dos participantes que interagiram com um agente computado sentirem um maior valor de "creepiness". Considerando que a utilização do sistema de recomendação de produtos tem forte impacto na intenção de comprar do consumidor, este estudo mostra-se relevante ao salientar a importância da presença social nas lojas "on-line", especialmente quando o agente é humano.

APA, Harvard, Vancouver, ISO, and other styles

39

Monteiro, Nuno Filipe Rodrigues. "Towards an Agent-Based Artificial Transportation System Test-Bed for Policy Making and Incentive Design." Master's thesis, 2014. https://repositorio-aberto.up.pt/handle/10216/78165.

Full text

APA, Harvard, Vancouver, ISO, and other styles

40

Monteiro, Nuno Filipe Rodrigues. "Towards an Agent-Based Artificial Transportation System Test-Bed for Policy Making and Incentive Design." Dissertação, 2014. https://repositorio-aberto.up.pt/handle/10216/78165.

Full text

APA, Harvard, Vancouver, ISO, and other styles

41

Capelo, André Manuel Bailão Martins Cunha. "O impacto da inteligência artificial na gestão comercial." Master's thesis, 2019. http://hdl.handle.net/10071/18966.

Full text

Abstract:

Os avanços tecnológicos levam a que as empresas atualmente se encontrem numa era de trans-formação digital e tecnológica, através da incorporação de sistemas de Inteligência Artificial (IA) no seu quotidiano. Hoje em dia, uma empresa que não utilize um sistema de IA ou não o forneça ao seu colaborador, perde vantagem competitiva perante outras empresas da mesma área de negócio, que utilizem sistemas de IA. O objetivo deste trabalho foi tentar perceber qual o impacto que as ferramentas de IA têm no desenvolvimento de funções comerciais e se estas se podem afirmar como um meio de auxílio ou um substituto, ao nível desta função. Por outro lado, tentou-se perceber que tipo de ferramentas de IA os comerciais utilizam e que tipo de ferramentas poderiam ser desenvolvidas para melhorar a sua tomada de decisão. Para tal, foram realizadas 15 entrevistas a comerciais de diversas empresas, e posteriormente foi feita uma análise qualitativa das mesmas. Foi possível concluir que todos os comerciais utilizam sistemas de IA no seu dia a dia, que estas ferramentas são um meio de auxílio no desenvolvimento das suas funções, o que lhes permite ter mais tempo e prepará-los melhor para os problemas levan-tados pelos seus clientes e ao nível da negociação. Por outro lado, o tipo de ferramentas que são utilizadas por comerciais, são ainda um pouco limitadas, devendo as empresas apostar tanto na sua formação e desenvolvimento na área da IA, bem como na formação dos seus comerciais.
Technological advances lead companies today to find themselves in an age of digital and tech-nological transformation through the incorporation of Artificial Intelligence (AI) systems into their daily lives. Nowadays a company that does not use an AI system or does not provide it to its employee loses competitive advantage over other companies in the same business area. The aim of this paper was to try to understand the impact that AI tools have on the development of business functions (related to commercial area) and if they can be affirmed as a means of help or as a substitute for this function. On the other hand, we tried to understand what kind of AI tools commercials use and what kind of tools could be developed to improve their decision making. Considering our aim, we did 15 interviews were conducted with commercials from various companies, and subsequently a qualitative analysis was made of them. It can be con-cluded that all commercials use AI systems in their daily lives, that these tools are a means of assisting in the development of their functions, allowing them to have more time and better prepare them for the problems raised by their customers. On the other hand, the type of tools that are used by commercials are still somewhat limited, and companies should focus on both their training and development in AI as well as the training of their commercials.

APA, Harvard, Vancouver, ISO, and other styles

42

Rufino, Margarida Maria Lima. "Adesão, relação, e aprendizagem em psicoterapia autoguiada mhealth por um agente virtual com inteligência artificial." Master's thesis, 2020. http://hdl.handle.net/10451/45859.

Full text

Abstract:

Tese de mestrado, Psicologia (Área de Especialização em Psicologia Clínica e da Saúde - Psicoterapia Cognitiva-Comportamental e Integrativa), Universidade de Lisboa, Faculdade de Psicologia, 2020
Portugal é dos países com maior prevalência de perturbação psiquiátrica na Europa. Um dos principais motivos é à dificuldade de acesso aos cuidados inerentes, associado à sobrelotação dos serviços públicos de apoio à saúde mental, a desinformação sobres os serviços disponíveis, os custos elevados no privado, e o estigma relativo ao conceito de acompanhamento psicológico. Deste modo, algumas das alternativas a esta fratura que é o acesso ao apoio à saúde mental passam pelo uso de tecnologia, nomeadamente, o uso de aplicações gratuitas para telemóvel de apoio à saúde mental. Sendo assim, o objetivo do presente estudo é estudar a viabilidade de uso e explorar a interação dos participantes com um agente virtual com inteligência artificial (AI) - chatbot de apoio à saúde mental numa aplicação para telemóvel. Principalmente, explorar e avaliar a adesão, relação, e aprendizagem dos participantes com o chatbot bem como compreender qual a opinião destes participantes relativamente à utilidade deste tipo de aplicações de apoio à saúde mental. Após a instalação da aplicação e o uso da mesma durante uma semana, os 36 participantes foram submetidos a uma entrevista telefónica de forma a explorar as variáveis mencionadas. Os resultados evidenciam uma adesão acentuada à aplicação e uma afirmação geral relativamente à sua importância e utilidade a nível de acessibilidade e apoio psicológico. Adicionalmente, alguns participantes sentiram uma ligação com o chatbot e é de acordo geral que a conversa com uma agente virtual potencia a autorrevelação, pelo que se prevê que em futuros estudos poderá ser possível o estabelecimento de uma relação terapêutica entre um humano e um agente virtual, através da melhoria de determinados aspetos como a repetição e personalização da aplicação ao utilizador, e o idioma. Além disso, foi evidenciado que o caráter psicoeducativo possibilitou introspeção e consciencialização de si próprio. O presente estudo demonstrou resultados promissores para um futuro mais informado e com maior acesso a cuidados de saúde mental.
Portugal is one of the countries who has the highest prevalence of mental disorder in Europe. One of the main reasons is the difficulty of accessing mental health care, associated with the overcrowding of public mental health support services, lack of information about available services, high costs in the private sector and the stigma related to the concept of psychological support. Therefore, some of the alternatives to this fracture, which is access to mental health support, include the use of technology, namely, the use of free mobile phone applications to support mental health. Thus, the objective of the present study is to study the feasibility of mhealth applications and to explore the interaction of the participants with a virtual artificial intelligence (AI) agent -chatbot to support mental health in a mobile application. Mainly, to explore and evaluate the participants' adherence, relationship, and learning with the chatbot, as well as to understand the opinion of these participants regarding the usefulness of this type of mental health support applications. After installing the application and using it for a week, the 36 participants underwent a telephone interview in order to explore the variables mentioned. The results show a strong adherence to the application and a general agreement regarding its importance and usefulness in terms of accessibility and psychological support. In addition, some participants felt a connection with the chatbot and it is generally agreed that the conversation with a virtual agent enhances self-disclosure, which is why in future studies it may be possible to establish a therapeutic relationship between a human and a virtual agent, through improving certain aspects such as repetition and customization of the application to the user, and the language. In addition, it was evidenced that the psychoeducational character enabled introspection and self-awareness. The present study demonstrated promising results for a more informed future and with greater access to mental health care.

APA, Harvard, Vancouver, ISO, and other styles

43

Henriques, Nuno Andrade da Cruz. "SensAI+Expanse : Prediction of Emotional Valence Changes on Humans in Context by an Artificial Agent Towards Empathy." Doctoral thesis, 2020. http://hdl.handle.net/10451/44892.

Full text

Abstract:

The field of Cognitive Science is broader enough on the interdisciplinary study of the brain, mind, and intelligence with a scientific research community gaining momentum over the last few decades. Specifically, joining the two fields of psychology and artificial intelligence (AI) one may envision agents, embodied or not, human-like or wearable, with the ability to significantly change the way humans live. This research conceive the artificial agent as a non-anthropomorphic with adaptive empathy for human-agent interaction (HAI) synergy towards better companionship. Therefore, the main objectives of this research are (a) to build a predictive model for each human user on context-based emotional valence changes; and (b) to study the age, gender, and human behaviour neutrality and robustness of the artificial agent regarding the prediction ability. The context include geographically located data from sensors, text sentiment analysis, and human emotional valence self-report, all timestamped events, using a common mobile device such as a smartphone. Also, to analyse and discuss the results on how to leverage such a model to adapt interaction strategies in order to foster higher levels of empathy between a non-anthropomorphic agent and its interacting human. For these goals SensAI+Expanse is developed where SensAI acts as an embodied nearby agent and Expanse encompass the machine learning resources in efficient manner, i.e., a distributed, fault-tolerant, mobile and Cloud-based platform from scratch as a research tool to continuously, online, gather and process data towards automated machine learning (AutoML) and prediction. The study is designed with a methodology in place to avoid the Western, Educated, Industrialized, Rich, and Democratic (WEIRD) societies bias. This goal is accomplished by collecting data in the wild and worldwide by making use of the publicly accessible Google Play repository for the Android™ SensAI smartphone application. Eligible participants are diverse in age, gender, and behaviour on self-reporting emotional valence. In order to balance the gender distribution by age a dichotomy approach using age median (M = 34) is used. Regarding participation duration, two thirds (33/49) of the eligible individuals for analysis remain interacting for the required minimum of four weeks. The analysis of the results show evidence of significant behaviour differences between some age and gender combinations regarding self-reported emotional valence. Furthermore, the results from a comparison study between state-of-the-art algorithms revealed Extreme Gradient Boosting on average the best model for prediction (F1 = 0:91) with efficient energy use, and explainable using feature importance inspection. Moreover, the artificial agent remained neutral regarding human demographics and, simultaneously, able to reveal individual idiosyncrasies. Therefore, this research contributions include results with evidence, restricted to population and data samples available, of differences in behaviour amongst some combinations of age ranges versus gender. The main contribution is a novel platform for studies regarding human emotional valence changes in context. This system may complement and supersede (eventually) traditional long-list self-appraisal questionnaires. The SensAI+Expanse platform contributes with several parts such as a mobile device application (SensAI) able to adapt and learn in order to predict emotional valence states with high performance, a cloud computing (Cloud) service (SensAI Expanse) with ready-to-action analysis and processing modules towards AutoML. Additionally, smartphone sensing add a contribution for continuous, non-invasive and personalised health check. In the future, developments about human-agent relationships regarding affective interactions are foreseen. Further, the measurement of empathetic reactions and evaluating outcomes may be used to verify and validate health status thus improving care and significantly change the way humans live.
O campo da ciência cognitiva é suficientemente amplo no estudo interdisciplinar do cérebro, mente, e inteligência com uma comunidade de pesquisa científica em crescimento nas últimas décadas. Especificamente, juntando os dois campos da psicologia e inteligência artificial, é possível antever agentes, incorporados ou não, como humanos ou abstratos numa pulseira, com a capacidade de mudar significativamente a maneira como vivemos. A investigação descrita neste documento concebe o agente não antropomórfico com empatia adaptativa por sinergia da interação humano-artificial no sentido de uma melhor companhia entre agentes. Assim, os principais objetivos desta pesquisa são (a) construir um modelo de previsão adaptada a cada utilizador humano sobre mudanças de valência emocional em contexto; e (b) estudar comparativamente à idade, género, e comportamento humano a neutralidade e robustez do agente artificial na sua capacidade de previsão. O contexto inclui dados geograficamente localizados de sensores, análise de sentimento em texto, e de relatórios de valência emocional pelos humanos, estes eventos incluem informação temporal, usando um dispositivo móvel comum, tal como um telemóvel. Adicionalmente, para analisar e discutir os resultados de como alavancar esse modelo para se adaptarem estratégias de interação, de modo a promover aumento da empatia entre um agente não antropomórfico e o seu utilizador humano em contacto. Para cumprir estes objetivos é desenvolvido o SensAI+Expanse onde SensAI atua como um agente corporizado e de proximidade, e o Expanse abrange os recursos de aprendizagem por computador (machine learning) de forma eficiente. Isto é, uma plataforma distribuída, tolerante ao erro, móvel e baseada na nuvem (Cloud) informática, criada de raiz como ferramenta de pesquisa para reunir dados continuamente, ligada, e os processar para a aprendizagem automatizada por computador (automated machine learning) e a previsão. O estudo é desenvolvido com uma metodologia específica para evitar o viés das sociedades educadas, industrializadas, ricas e democráticas (conhecido como WEIRD). Este objetivo é alcançado através da recolha de dados em campo e alargado ao mundo inteiro (potencialmente) fazendo uso do repositório Google Play acessível ao público como local de publicação da aplicação SensAI. Os participantes elegíveis são diversos em idade, género, e no comportamento ao informarem a valência emocional. No sentido de equilibrar adequadamente a distribuição de género por idade, uma abordagem dicotómica utiliza a mediana das idades (M = 34). Em relação à duração da participação, dois terços (33/49) dos indivíduos elegíveis para análise permaneceram em interação pelo mínimo necessário de quatro semanas. A análise dos resultados mostra evidência de diferenças significativas de comportamento entre algumas combinações de idade e género em relação à valência emocional informada pelos utilizadores. Adicionalmente, os resultados de um estudo comparativo entre os melhores algoritmos atuais revelaram o Extreme Gradient Boosting, em média, o melhor modelo para previsão (F1 = 0; 91) com uso eficiente de energia e explicável usando inspeção de importância de cada caraterística (e.g., localização específica). Além disso, o agente artificial permaneceu neutro em relação à demografia humana e, simultaneamente, capaz de revelar idiossincrasias individuais. Portanto, as contribuições desta pesquisa incluem resultados com evidência, restritos à população e amostras de dados disponíveis, de diferenças de comportamento entre algumas combinações de intervalos etários e género. A principal contribuição é uma nova plataforma para estudos sobre as mudanças de valência emocional nos humanos e em contexto. Este sistema pode complementar e substituir (eventualmente) os tradicionais questionários com listas longas de questões para autoavaliação. A plataforma SensAI+Expanse contribui com várias partes, tais como (a) uma aplicação de dispositivo móvel (SensAI) com a capacidade de se adaptar e aprender de modo a prever estados de valência emocional com elevado desempenho; e (b) um serviço de computação em nuvem (Cloud), o SensAI Expanse, capaz de análise no momento e com módulos de processamento para a aprendizagem automatizada por computador (automated machine learning). Além disso, a abordagem de recolha de dados usando os sensores do telemóvel (smartphone sensing) adiciona uma contribuição no para análise da saúde ou do bem-estar em contínuo, não invasivo, e personalizado. Num futuro próximo, prevê-se um desenvolvimento interessante sobre as relações humano-agente em relação às interações afetivas. Adicionalmente, a medição das reações empáticas e a avaliação dos resultados das mesmas podem ser usados para verificar e validar o estado de saúde, e assim melhorar os cuidados e mudar significativamente a forma de viver dos seres humanos.

APA, Harvard, Vancouver, ISO, and other styles

44

Cavalheiro, Inês Barata Feio Paixão. "The influence of artificial intelligence on the online behaviour of Portuguese consumers and brands." Master's thesis, 2021. http://hdl.handle.net/10071/23804.

Full text

Abstract:

Artificial Intelligence (AI) is intensifying its importance, being increasingly present in people's everyday interactions and activities, while shaping a variety of industries, among which is the field of online shopping, that is currently experiencing significant growth in terms of volume and acceptance among customers. A range of factors have contributed to the change in how shoppers behave, including the ease of access and a greater variety of products and services available online. Nonetheless, retail sectors still face some difficulties in adopting e-commerce, particularly related to the issue of converting the in-store experience to the online environment. To answer these constraints, several AI-based tools, namely Chatbots, Recommendation Agents, and Virtual Try On Systems (VTOs) have been introduced in the e-commerce field in order to enhance the online experience. Ultimately these technologies promise to provide new possibilities for the field of online shopping, to increase the digital interaction between customers and brands, and to influence customers purchase behaviour. As so, this dissertation aims to assess why AI should become increasingly relevant for companies in order to better understand and meet consumers' needs through personalised experiences, offering a possibility to gain competitive advantages. Hence, the impact of these AI-based tools on the online experience of the customer and subsequent purchase intention was examined using a mixed approach of quantitative methods, considering both a corporate and a consumer perspective. The results highlight that AI is seen as a promising tool among both Portuguese brands and customers using online retail platforms. In particular, it was possible to conclude that the use of AI tools enables a better customer experience when shopping online, ultimately leading customers to complete their purchases.
A Inteligência Artificial tem cada vez maior importância na sociedade atual, não só estando progressivamente mais presente nas interações e atividades diárias das pessoas, como também contribuindo crescentemente para a transformação de diversas indústrias, entre as quais o e-commerce. Simultaneamente, o campo do comércio online está a experienciar um crescimento significativo em termos de volume e aceitação entre os clientes. A facilidade de acesso e maior variedade de produtos e serviços disponíveis online são fatores que têm contribuído para a mudança no comportamento dos compradores. No entanto, os sectores retalhistas ainda enfrentam algumas dificuldades na adoção do comércio eletrónico, particularmente relacionadas com a questão da conversão da experiência na loja para o ambiente online. Para responder a estas questões, várias ferramentas baseadas na IA, nomeadamente Chatbots, Agentes de Recomendação e Sistemas de Virtual Try-On (VTOs), foram introduzidas no âmbito do comércio eletrónico a fim de melhorar a experiência online, proporcionar novas possibilidades de interação entre consumidores e marcas, e, em última análise, influenciar a intenção de compra dos clientes. Esta dissertação visa avaliar por que razão a IA deve tornar-se cada vez mais relevante para que as empresas compreendam e satisfaçam melhor as necessidades dos consumidores, através de experiências personalizadas, oferecendo uma possibilidade de obter vantagens competitivas. Assim, o impacto destes Sistemas Inteligentes sobre a experiência online do cliente e subsequente intenção de compra foi examinado, utilizando uma abordagem mista de métodos quantitativos, considerando tanto uma perspetiva empresarial como uma perspetiva do consumidor. Os resultados salientam que a IA é vista como uma ferramenta promissora tanto entre as marcas portuguesas como entre os clientes que utilizam plataformas de retalho online. Em particular, foi possível concluir que o uso de ferramentas de IA permite uma melhor experiência do cliente quando faz compras online, levando em última análise os clientes a completar as suas compras.

APA, Harvard, Vancouver, ISO, and other styles

45

Gomes, Eduardo. "An agent-based approach to model farmers' land use cover change intentions." Doctoral thesis, 2019. http://hdl.handle.net/10451/48481.

Full text

Abstract:

Land Use and Cover Change (LUCC) occurs as a consequence of both natural and human activities, causing impacts on biophysical and agricultural resources. In enlarged urban regions, the major changes are those that occur from agriculture to urban uses. Urban uses compete with rural ones due among others, to population growth and housing demand. This competition and the rapid nature of change can lead to fragmented and scattered land use development generating new challenges, for example, concerning food security, soil and biodiversity preservation, among others. Landowners play a key role in LUCC. In peri-urban contexts, three interrelated key actors are pre-eminent in LUCC complex process: 1) investors or developers, who are waiting to take advantage of urban development to obtain the highest profit margin. They rely on population growth, housing demand and spatial planning strategies; 2) farmers, who are affected by urban development and intend to capitalise on their investment, or farmers who own property for amenity and lifestyle values; 3) and at a broader scale, land use planners/ decision-makers. Farmers’ participation in the real estate market as buyers, sellers or developers and in the land renting market has major implications for LUCC because they have the capacity for financial investment and to control future agricultural land use. Several studies have analysed farmer decision-making processes in peri-urban regions. These studies identified agricultural areas as the most vulnerable to changes, and where farmers are presented with the choice of maintaining their agricultural activities and maximising the production potential of their crops or selling their farmland to land investors. Also, some evaluate the behavioural response of peri-urban farmers to urban development, and income from agricultural production, agritourism, and off-farm employment. Uncertainty about future land profits is a major motivator for decisions to transform farmland into urban development. Thus, LUCC occurs when the value of expected urban development rents exceeds the value of agricultural ones. Some studies have considered two main approaches in analysing farmer decisions: how drivers influence farmer’s decisions; and how their decisions influence LUCC. To analyse farmers’ decisions is to acknowledge the present and future trends and their potential spatial impacts. Simulation models, using cellular automata (CA), artificial neural networks (ANN) or agent-based systems (ABM) are commonly used. This PhD research aims to propose a model to understand the agricultural land-use change in a peri-urban context. We seek to understand how human drivers (e.g., demographic, economic, planning) and biophysical drivers can affect farmer’s intentions regarding the future agricultural land and model those intentions. This study presents an exploratory analysis aimed at understanding the complex dynamics of LUCC based on farmers’ intentions when they are faced with four scenarios with the time horizon of 2025: the A0 scenario – based on current demographic, social and economic trends and investigating what happens if conditions are maintained (BAU); the A1 scenario – based on a regional food security; the A2 scenario – based on climate change; and the B0 scenario – based on farming under urban pressure, and investigating what happens if people start to move to rural areas. These scenarios were selected because of the early urbanisation of the study area, as a consequence of economic, social and demographic development; and because of the interest in preserving and maintaining agriculture as an essential resource. Also, Torres Vedras represents one of the leading suppliers of agricultural goods (mainly fresh fruits, vegetables, and wine) in Portugal. To model LUCC a CA-Markov, an ANN-multilayer perceptron, and an ABM approach were applied. Our results suggest that significant LUCC will occur depending on farmers’ intentions in different scenarios. The highlights are: (1) the highest growth in permanently irrigated land in the A1 scenario; (2) the most significant drop in non-irrigated arable land, and the highest growth in the forest and semi-natural areas in the A2 scenario; and (3) the greatest urban growth was recognised in the B0 scenario. To verify if the fitting simulations performed well, statistical analysis to measure agreement and quantity-allocation disagreements and a participatory workshop with local stakeholders to validate the achieved results were applied. These outcomes could provide decision-makers with the capacity to observe different possible futures in ‘what if’ scenarios, allowing them to anticipate future uncertainties, and consequently allowing them the possibility to choose the more desirable future.

APA, Harvard, Vancouver, ISO, and other styles

46

Raposo, Beatriz de Almeida Pereira Nunes. "AI minds morals 00111111." Master's thesis, 2021. http://hdl.handle.net/10071/23992.

Full text

Abstract:

The growing frontiers of technology are also pushing the frontiers of social science as regards the challenges AI poses to assumptions about human being and human society. The increasing surrogate status of AI agents, namely those endowed with autonomous action, is of special interest in the intersection of psychology and ethics. Ascribing morality and mind may read as fictional, but a deeper understanding of these constructs may explain the already emerging literature on AI agency and morality. This literature is still scarce and has not treated both topics conjointly, which we believe would be expectable as morality and mind seem to go hand-in-hand. With this objective, we designed a 2x2 experiment to test the effects that ascribed mind dimensions (agentic-experiential & metacognitive) crossed with ascribed morality to agents (authority & harm motivations) have on explaining the degree of blame depending on the nature of the agent (Human vs. AI). With a sample of 137 individuals, controlling for age, gender, wrongfulness, and displacement of responsibilities, we tested this three-way interaction to find fundamental differences between Human and AI agents. Humans were more blamable when they were seen as being less authority motivated (uncompliant) while having low metacognitive mind (less reflexive). Conversely, AI agents were more blamable when they were seen as being authority motivated while having low metacognitive mind. Findings are discussed at the light of the theory highlighting implications for theory, practice and the human-AI interaction.
A extensão das fronteiras da tecnologia tem estimulado o crescimento das ciências sociais no que concerne os desafios que a IA coloca aos pressupostos sobre o Ser Humano e a sociedade. O crescente estatuto dos agentes de IA, nomeadamente daqueles dotados de ação autónoma, é de especial interesse na interseção da Psicologia e da Ética. Atribuir moralidade e mente pode parecer ficcional, contudo a compreensão aprofundada destes construtos pode explicar a emergência de literatura sobre IA e moralidade. Esta literatura é ainda escassa e não conjugou ainda os tópicos, o que acreditamos ser expectável dado a moralidade e a mente serem indissociáveis. Com este objetivo, foi desenhada uma experiência 2x2 para testar os efeitos que a atribuição de mente (agêntica-experiencial & metacognitiva) cruzada com a atribuição de moralidade a agentes (motivações para autoridade & prejuízo) têm na explicação do nível de culpa dependendo na natureza do agente (Humano vs. IA). Com uma amostra de 137 indivíduos, controlando a idade, sexo, iniquidade/injustiça, e deslocação de responsabilidade, foi testada esta interação tripla, a fim de testar diferenças significativas entre agentes Humanos e de IA. Os agentes humanos foram mais culpados quando percecionados como sendo menos motivados para a autoridade (desobediente) e possuem menor mente metacognitiva (menos reflexivos). Contrariamente, agentes IA foram mais culpados quando percecionados como sendo motivados para a autoridade e menos mente metacognitiva. Os resultados são discutidos à luz das teorias centrando as implicações para a teoria, a prática e as interações humano-IA.

APA, Harvard, Vancouver, ISO, and other styles

47

Ribeiro, Beatriz Assunção. "A responsabilidade legal de veículos autónomos : uma perspectiva da ciência cognitiva." Master's thesis, 2019. http://hdl.handle.net/10451/39556.

Full text

Abstract:

A Tecnologia dos Veículos Autónomos avança rapidamente e urge um debate entre todas as áreas que possam oferecer um contributo. O funcionamento complexo de um Veículo Autónomo, as querelas éticas associadas ao mesmo, e os problemas de segurança que se têm vindo a colocar, tornam-no num produto em tudo exceci-onal, o que acarreta limitações ao nível do Direito. Este é o contributo da Ciência Cognitiva, com recurso às disciplinas de Filosofia da Mente e Ciências da Computação, fazendo a ponte com o Direito, com o objetivo de responder a algumas dessas limitações. O propósito geral desta dissertação é perceber o que é um Agente, que impacto tem no ambiente e o que é que torna um Agente uma entidade legalmente responsável. Como entidades num mundo em que muito é definido pelos atos voluntários, os Veículos Autónomos são Agentes complexos enquadrados num ambiente com infinitos estímulos. A esta tecnologia ainda lhe falta, como iremos argumentar, um pressuposto mínimo da imputação da responsabilidade: a Metacognição. O que esta dissertação pretende é mostrar, numa primeira fase e através de considerações sobre Agentividade1 e ação voluntária, que a Metacognição é um elemento essencial, no Direito, para a atribuição de Responsabilidade. Numa segunda, alega-se que o tipo de Metacog-nição na qual o Direito se baseia está em falta no VA. E, finalmente, debate-se qual deverá ser o regime jurídico do VA, tendo tudo isto em conta. Para esta discussão, além de tecermos ideias sobre um regime mais disperso e solidário de responsabilidades, bem como sobre a necessidade de um sistema legal de responsabilidade civil paralelo a um seguro de respon-sabilidade civil obrigatório, comparamos os VA com os regimes dos menores, animais e interditos, dada a sua semelhança no que diz respeito aos processos metacognitivos.
As the technology of Autonomous Vehicles advances swiftly, it’s urgent to look into all the areas that can some-how contribute to a useful debate. The highly complex functioning of the Autonomous Vehicle, the ethics ques-tions associated, and the safety problems that appeared with it, make it an exceptional product, with serious implications in Law. In this dissertation we pretend to build a bridge between Philosophy of Mind and Compu-tation Science and the Law, in order to respond to the limitations of this technology. The purpose of this thesis is to analyse what it means to be an Agent, with an impact in the environment and what makes an Agent an entity to whom we can ascribe legal responsibility. As entities in a world where a lot of what happens it’s defined by the idea of Voluntary Acts, Autonomous Vehicles are complex agents, framed in an environment that presents an infinite number of stimuli. This Technology, as we shall argue, lacks a mini-mum requirement of responsibility: Metacognition. What this dissertation wants to show is, using the concepts of Agency and Voluntary Action, that Metacognition is an essential element, in Law, in order to ascribe respon-sibility. In a second phase of this thesis, we argue that this type of Metacognition, that Law requires to consider someone responsible, is missing in the Autonomous Vehicle. Finally, in the last chapters, there’s some debate over the Legal system that should be applied to this technology. In this debate, while suggesting a scattered regime that also considers joint liabilities, as well as the existence of a mandatory insurance parallel to the civil Responsibility regime, we briefly compare Autonomous Vehicles to minors, animals and disabled people, given their similarity when it comes to the degree of Metacognitive processes.

APA, Harvard, Vancouver, ISO, and other styles

Dissertations / Theses on the topic 'Artificial Social Agents'

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles