Grounding human vocabulary in robot perception through interaction

This thesis addresses the problem of word learning in computational agents. The motivation behind this work lies in the need to support language-based communication between service robots and their human users, as well as grounded reasoning using symbols relevant for the assigned tasks. The research focuses on the problem of grounding human vocabulary in robotic agent’s sensori-motor perception. Words have to be grounded in bodily experiences, which emphasizes the role of appropriate embodiments. On the other hand, language is a cultural product created and acquired through social interactions. This emphasizes the role of society as a source of linguistic input. Taking these aspects into account, an experimental scenario is set up where a human instructor teaches a robotic agent the names of the objects present in a visually shared environment. The agent grounds the names of these objects in visual perception. Word learning is an open-ended problem. Therefore, the learning architecture of the agent will have to be able to acquire words and categories in an openended manner. In this work, four learning architectures were designed that can be used by robotic agents for long-term and open-ended word and category acquisition. The learning methods used in these architectures are designed for incrementally scaling-up to larger sets of words and categories. A novel experimental evaluation methodology, that takes into account the openended nature of word learning, is proposed and applied. This methodology is based on the realization that a robot’s vocabulary will be limited by its discriminatory capacity which, in turn, depends on its sensors and perceptual capabilities. An extensive set of systematic experiments, in multiple experimental settings, was carried out to thoroughly evaluate the described learning approaches. The results indicate that all approaches were able to incrementally acquire new words and categories. Although some of the approaches could not scale-up to larger vocabularies, one approach was shown to learn up to 293 categories, with potential for learning many more.

Mining biomedical information from scientific literature

The rapid evolution and proliferation of a world-wide computerized network, the Internet, resulted in an overwhelming and constantly growing amount of publicly available data and information, a fact that was also verified in biomedicine. However, the lack of structure of textual data inhibits its direct processing by computational solutions. Information extraction is the task of text mining that intends to automatically collect information from unstructured text data sources. The goal of the work described in this thesis was to build innovative solutions for biomedical information extraction from scientific literature, through the development of simple software artifacts for developers and biocurators, delivering more accurate, usable and faster results. We started by tackling named entity recognition - a crucial initial task - with the development of Gimli, a machine-learning-based solution that follows an incremental approach to optimize extracted linguistic characteristics for each concept type. Afterwards, Totum was built to harmonize concept names provided by heterogeneous systems, delivering a robust solution with improved performance results. Such approach takes advantage of heterogenous corpora to deliver cross-corpus harmonization that is not constrained to specific characteristics. Since previous solutions do not provide links to knowledge bases, Neji was built to streamline the development of complex and custom solutions for biomedical concept name recognition and normalization. This was achieved through a modular and flexible framework focused on speed and performance, integrating a large amount of processing modules optimized for the biomedical domain. To offer on-demand heterogenous biomedical concept identification, we developed BeCAS, a web application, service and widget. We also tackled relation mining by developing TrigNER, a machine-learning-based solution for biomedical event trigger recognition, which applies an automatic algorithm to obtain the best linguistic features and model parameters for each event type. Finally, in order to assist biocurators, Egas was developed to support rapid, interactive and real-time collaborative curation of biomedical documents, through manual and automatic in-line annotation of concepts and relations. Overall, the research work presented in this thesis contributed to a more accurate update of current biomedical knowledge bases, towards improved hypothesis generation and knowledge discovery.

Algoritmos inteligentes de baixa complexidade

A domótica é uma área com grande interesse e margem de exploração, que pretende alcançar a gestão automática e autónoma de recursos habitacionais, proporcionando um maior conforto aos utilizadores. Para além disso, cada vez mais se procuram incluir benefícios económicos e ambientais neste conceito, por forma a garantir um futuro sustentável. O aquecimento de água (por meios elétricos) é um dos fatores que mais contribui para o consumo de energia total de uma residência. Neste enquadramento surge o tema “algoritmos inteligentes de baixa complexidade”, com origem numa parceria entre o Departamento de Eletrónica, Telecomunicações e Informática (DETI) da Universidade de Aveiro e a Bosch Termotecnologia SA, que visa o desenvolvimento de algoritmos ditos “inteligentes”, isto é, com alguma capacidade de aprendizagem e funcionamento autónomo. Os algoritmos devem ser adaptados a unidades de processamento de 8 bits para equipar pequenos aparelhos domésticos, mais propriamente tanques de aquecimento elétrico de água. Uma porção do desafio está, por isso, relacionada com as restrições computacionais de microcontroladores de 8 bits. No caso específico deste trabalho, foi determinada a existência de sensores de temperatura da água no tanque como a única fonte de informação externa aos algoritmos, juntamente com parâmetros pré-definidos pelo utilizador que estabelecem os limiares de temperatura máxima e mínima da água. Partindo deste princípio, os algoritmos desenvolvidos baseiam-se no perfil de consumo de água quente, observado ao longo de cada semana, para tentar prever futuras tiragens de água e, consequentemente, agir de forma adequada, adiantando ou adiando o aquecimento da água do tanque. O objetivo é alcançar uma gestão vantajosa entre a economia de energia e o conforto do utilizador (água quente), isto sem que exista necessidade de intervenção direta por parte do utilizador final. A solução prevista inclui também o desenvolvimento de um simulador que permite observar, avaliar e comparar o desempenho dos algoritmos desenvolvidos.

Perception and software architecture for mobile robotics

When developing software for autonomous mobile robots, one has to inevitably tackle some kind of perception. Moreover, when dealing with agents that possess some level of reasoning for executing their actions, there is the need to model the environment and the robot internal state in a way that it represents the scenario in which the robot operates. Inserted in the ATRI group, part of the IEETA research unit at Aveiro University, this work uses two of the projects of the group as test bed, particularly in the scenario of robotic soccer with real robots. With the main objective of developing algorithms for sensor and information fusion that could be used e ectively on these teams, several state of the art approaches were studied, implemented and adapted to each of the robot types. Within the MSL RoboCup team CAMBADA, the main focus was the perception of ball and obstacles, with the creation of models capable of providing extended information so that the reasoning of the robot can be ever more e ective. To achieve it, several methodologies were analyzed, implemented, compared and improved. Concerning the ball, an analysis of ltering methodologies for stabilization of its position and estimation of its velocity was performed. Also, with the goal keeper in mind, work has been done to provide it with information of aerial balls. As for obstacles, a new de nition of the way they are perceived by the vision and the type of information provided was created, as well as a methodology for identifying which of the obstacles are team mates. Also, a tracking algorithm was developed, which ultimately assigned each of the obstacles a unique identi er. Associated with the improvement of the obstacles perception, a new algorithm of estimating reactive obstacle avoidance was created. In the context of the SPL RoboCup team Portuguese Team, besides the inevitable adaptation of many of the algorithms already developed for sensor and information fusion and considering that it was recently created, the objective was to create a sustainable software architecture that could be the base for future modular development. The software architecture created is based on a series of di erent processes and the means of communication among them. All processes were created or adapted for the new architecture and a base set of roles and behaviors was de ned during this work to achieve a base functional framework. In terms of perception, the main focus was to de ne a projection model and camera pose extraction that could provide information in metric coordinates. The second main objective was to adapt the CAMBADA localization algorithm to work on the NAO robots, considering all the limitations it presents when comparing to the MSL team, especially in terms of computational resources. A set of support tools were developed or improved in order to support the test and development in both teams. In general, the work developed during this thesis improved the performance of the teams during play and also the e ectiveness of the developers team when in development and test phases.

Métodos de soft computing para la estimación no invasiva de la temperatura en medios multicapa empleando ultrasonido retrodisperso

La seguridad y eficacia de las terapias térmicas están ligadas con la determinación exacta de la temperatura, es por ello que la retroalimentacón de la temperatura en los métodos computacionales es de vital importancia.

Diagnóstico de CVA isquémicos asistido por redes neuronales mediante la exploración por CT

La evolución tecnologica y computacional ha generado más oportunidades de mejorar la calidad de vida mediante nuevos logos médicos; en particular, con la calidad de las evaluaciones de diagnóstico. La tomografía computarizada (CT) es uno de los equipos de proyección de imagen para diagnóstico que más se han beneficiado de las mejoras tecnológicas.

A nova Torre de Babel – que futuro para a tradução automática?

Poderá, um dia, a tradução automática suprimir ou dissipar as diferenças que bloquearam e obstruíram a comunicação na mítica torre babeliana? Será a tradução automática capaz de diluir as diferenças linguísticas que separam as comunidades humanas? Estas perguntas são, provavelmente, as que ocorrem ao público em geral, quando ouve falar de uma nova descoberta em Inteligência Artificial ou de uma nova aplicação informática para tradução. A curiosidade e o entusiasmo do público não-especialista contrasta, não raras vezes, com algum cepticismo e desconfiança de tradutores e teóricos da tradução.

Sobrevivência: jogo interactivo para estudo de arquitecturas de agentes autónomos

Trabalho de projeto para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Biblioteca de navegação autónoma baseada em campos de potencial

Trabalho de Final de Mestrado para obtenção do grau de Mestre em Engenharia Informática e de Computadores

Adaptive learning in agents behaviour: a framework for electricity markets simulation

Electricity markets are complex environments with very particular characteristics. A critical issue regarding these specific characteristics concerns the constant changes they are subject to. This is a result of the electricity markets’ restructuring, which was performed so that the competitiveness could be increased, but it also had exponential implications in the increase of the complexity and unpredictability in those markets scope. The constant growth in markets unpredictability resulted in an amplified need for market intervenient entities in foreseeing market behaviour. The need for understanding the market mechanisms and how the involved players’ interaction affects the outcomes of the markets, contributed to the growth of usage of simulation tools. Multi-agent based software is particularly well fitted to analyze dynamic and adaptive systems with complex interactions among its constituents, such as electricity markets. This dissertation presents ALBidS – Adaptive Learning strategic Bidding System, a multiagent system created to provide decision support to market negotiating players. This system is integrated with the MASCEM electricity market simulator, so that its advantage in supporting a market player can be tested using cases based on real markets’ data. ALBidS considers several different methodologies based on very distinct approaches, to provide alternative suggestions of which are the best actions for the supported player to perform. The approach chosen as the players’ actual action is selected by the employment of reinforcement learning algorithms, which for each different situation, simulation circumstances and context, decides which proposed action is the one with higher possibility of achieving the most success. Some of the considered approaches are supported by a mechanism that creates profiles of competitor players. These profiles are built accordingly to their observed past actions and reactions when faced with specific situations, such as success and failure. The system’s context awareness and simulation circumstances analysis, both in terms of results performance and execution time adaptation, are complementary mechanisms, which endow ALBidS with further adaptation and learning capabilities.

Integração de reacção e deliberação em agentes inteligentes

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Redes de Comunicação e Multimédia

Relatório de estágio na Empresa Biodroid Entertainment

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia de Redes de Comunicação e Multimédia

Interação social entre agentes em ambientes de recursos limitados

Trabalho final de Mestrado para obtenção do grau de Mestre em Engenharia de Redes de Comunicação e Multimédia

TRFS: desenvolvimento de um protótipo para simulação microscópica de tráfego

Dissertação para obtenção do grau de Mestre em Engenharia Civil na Área de Especialização de Vias de Comunicação e Transportes

Implementação de um modelo de geometric semantic genetic programming para aplicação naval

Recaí sob a responsabilidade da Marinha Portuguesa a gestão da Zona Económica Exclusiva de Portugal, assegurando a sua segurança da mesma face a atividades criminosas. Para auxiliar a tarefa, é utilizado o sistema Oversee, utilizado para monitorizar a posição de todas as embarcações presentes na área afeta, permitindo a rápida intervenção da Marinha Portuguesa quando e onde necessário. No entanto, o sistema necessita de transmissões periódicas constantes originadas nas embarcações para operar corretamente – casos as transmissões sejam interrompidas, deliberada ou acidentalmente, o sistema deixa de conseguir localizar embarcações, dificultando a intervenção da Marinha. A fim de colmatar esta falha, é proposto adicionar ao sistema Oversee a capacidade de prever as posições futuras de uma embarcação com base no seu trajeto até à cessação das transmissões. Tendo em conta os grandes volumes de dados gerados pelo sistema (históricos de posições), a área de Inteligência Artificial apresenta uma possível solução para este problema. Atendendo às necessidades de resposta rápida do problema abordado, o algoritmo de Geometric Semantic Genetic Programming baseado em referências de Vanneschi et al. apresenta-se como uma possível solução, tendo já produzido bons resultados em problemas semelhantes. O presente trabalho de tese pretende integrar o algoritmo de Geometric Semantic Genetic Programming desenvolvido com o sistema Oversee, a fim de lhe conceder capacidades preditivas. Adicionalmente, será realizado um processo de análise de desempenho a fim de determinar qual a ideal parametrização do algoritmo. Pretende-se com esta tese fornecer à Marinha Portuguesa uma ferramenta capaz de auxiliar o controlo da Zona Económica Exclusiva Portuguesa, permitindo a correta intervenção da Marinha em casos onde o atual sistema não conseguiria determinar a correta posição da embarcação em questão.