No description available.

This dissertation explores the modular learning in artificial neural networks that mainly driven by the inspiration from the neurobiological basis of the human learning. The presented modularization approaches to the neural network design and learning are inspired by the engineering, complexity, psychological and neurobiological aspects. The main theme of this dissertation is to explore the organization and functioning of the brain to discover new structural and learning inspirations that can be subsequently utilized to design artificial neural network. The artificial neural networks are touted to be a neurobiologicaly inspired paradigm that emulate the functioning of the vertebrate brain. The brain is a highly structured entity with localized regions of neurons specialized in performing specific tasks. On the other hand, the mainstream monolithic feed-forward neural networks are generally unstructured black boxes which is their major performance limiting characteristic. The non explicit structure and monolithic nature of the current mainstream artificial neural networks results in lack of the capability of systematic incorporation of functional or task-specific a priori knowledge in the artificial neural network design process. The problem caused by these limitations are discussed in detail in this dissertation and remedial solutions are presented that are driven by the functioning of the brain and its structural organization. Also, this dissertation presents an in depth study of the currently available modular neural network architectures along with highlighting their shortcomings and investigates new modular artificial neural network models in order to overcome pointed out shortcomings. The resulting proposed modular neural network models have greater accuracy, generalization, comprehensible simplified neural structure, ease of training and more user confidence. These benefits are readily obvious for certain problems, depending upon availability and usage of available a priori knowledge about the problems. The modular neural network models presented in this dissertation exploit the capabilities of the principle of divide and conquer in the design and learning of the modular artificial neural networks. The strategy of divide and conquer solves a complex computational problem by dividing it into simpler sub-problems and then combining the individual solutions to the sub-problems into a solution to the original problem. The divisions of a task considered in this dissertation are the automatic decomposition of the mappings to be learned, decompositions of the artificial neural networks to minimize harmful interaction during the learning process, and explicit decomposition of the application task into sub-tasks that are learned separately. The versatility and capabilities of the new proposed modular neural networks are demonstrated by the experimental results. A comparison of the current modular neural network design techniques with the ones introduced in this dissertation, is also presented for reference. The results presented in this dissertation lay a solid foundation for design and learning of the artificial neural networks that have sound neurobiological basis that leads to superior design techniques. Areas of the future research are also presented. / Ph. D.

Biological organisms, phenomena and strategies, herein referred to as biological systems, provide a rich set of analogies that can be used to inspire engineering innovation. Biologically-inspired, or biomimetic, designs are publicly viewed as creative and novel solutions to human problems. Moreover, some biomimetic designs have become so commonplace that it is hard to image life without them (e.g. velcro, airplanes). Although the biologically- inspired solutions are innovative and useful, the majority of inspiration taken from nature has happened by chance observation, dedicated study of a specific biological entity (e.g., gecko), or asking a biologist to explain the biology in simple terms. This reveals a fundamental problem of working across the engineering and biological domains. The effort and time required to become a competent engineering designer creates significant obstacles to becoming sufficiently knowledgeable about biological systems (the converse can also be said). This research aims to remove the element of chance, reduce the amount of time and effort required to developing biologically-inspired solutions, and bridge the seemingly immense disconnect between the engineering and biological domains. To facilitate systematic biologically-inspired design, a design methodology that relies on a framework of tools and techniques that bridge the two domains is established. The design tools and techniques that comprise the framework achieve: Identification of relevant biological solutions based on function; translation of identified biological systems of interest; functional representation of biological information such that it can be used for engineering design activities; and conceptualization of biomimetic engineering designs. Using functional representation and abstraction to describe biological systems presents the natural designs in an engineering context and allows designers to make connections between biological and engineered systems. Thus, the biological information is accessible to engineering designers with varying biological knowledge, but a common understanding of engineering design methodologies. This work has demonstrated the feasibility of using systematic design for the discovery of innovative engineering designs without requiring expert-level knowledge, but rather broad knowledge of many fields. / Graduation date: 2011

Sistemas de vigilância são geralmente empregados no monitoramento de áreas de grandes dimensões nas quais seus usuários visam detectar ou observar fenômenos de seu interesse. O uso de redes de sensores sem fio nesses sistemas apresenta especial interesse, uma vez que essas redes podem apresentar soluções de baixo custo e robustas para cobrir áreas extensas. Neste contexto, novas aplicações têm surgido propondo o uso de redes de sensores sem fio compostas por nós sensores estáticos e móveis. Uma das motivações para esta tendência é a redução do custo de implantação e operação do sistema, além da possibilidade de proporcionar incremento em suas funcionalidades. O foco desta tese se concentra na proposta de soluções para redes de sensores sem fio com uso cooperativo de sensores estáticos e móveis, com particular atenção a sensibilidade ao contexto na configuração e execução de missões de sensoriamento. O objetivo é manter um baixo custo de comunicação associado às soluções propostas. Esta preocupação se dá pelo fato da comunicação aumentar o consumo de energia em redes de sensores, o que é um problema importante para nós sensores com limitada fonte de energia, i.e. baterias. No caso de nós sensores móveis, esta limitação pode não ser relevante, uma vez que seu movimento deve consumir uma quantidade muito mais expressiva de energia do que a comunicação. Neste caso, o problema se relaciona à estabilidade dos enlaces, bem como ao curto intervalo de tempo disponível para transmitir e receber dados. Logo, o melhor é comunicar o menos possível. Com relação à interação entre nós sensores estáticos, os problemas de disseminação e alocação de missões de sensoriamento são estudados e uma solução que explora o uso de informações locais é proposta e avaliada. Esta solução emprega agentes de software móveis que têm a capacidade de tomar decisões autônomas através do uso de informações de contexto local. Para redes de sensores móveis, o problema estudado se refere a como transferir missões entre os nós sensores de acordo com seu movimento e localização em relação aos locais onde as missões devem ser executadas. Para tratar este problema, uma abordagem baseada em agentes móveis é proposta, na qual os agentes implementam a migração das missões de sensoriamento usando informações de contexto geográfico para decidir a respeito de suas migrações. Para redes de sensores com sensores estáticos e móveis, a cooperação entre eles é abordada através de um mecanismo com inspiração biológica para realizar a realizar a entrega de dados emitidos pelos sensores estáticos aos sensores móveis. Para isto, explora-se uma analogia baseada no comportamento de formigas na construção e seguimento de trilhas. As soluções propostas são flexíveis, sendo aplicáveis a diferentes domínios de aplicação. Resultados experimentais evidenciam sua escalabilidade, avaliando, por exemplo, seu custo em termos de comunicação, além de outras métricas de interesse para cada uma das soluções. Estes resultados são comparados aos atingidos por soluções de referência (solução ótima teórica e baseada em inundação), indicando sua eficiência. Estes resultados são próximos do ótimo teórico e significativamente melhores que aqueles atingidos por soluções baseadas em técnicas de inundação. / Surveillance systems are usually employed to monitor wide areas in which their users are interested in detecting and/or observing events or phenomena of their interest. The use of wireless sensor networks in such systems is of particular interest as these networks can provide a relative low cost and robust solution to cover large areas. Emerging applications in this context are proposing the use of wireless sensor networks composed of both static and mobile sensor nodes. Motivation for this trend is to reduce deployment and operating costs, besides providing enhanced functionalities. This work focuses on the proposal of solutions for wireless sensor networks including static and mobile sensor nodes specifically regarding cooperative and context aware mission setup and performance. The goal is to keep the communication costs as low as possible in the execution of the proposed solutions. This concern comes from the fact that communication increases energy consumption, which is a particular issue for energy constrained sensor nodes often used in wireless sensor networks, especially if battery supplied. In the case of the mobile nodes, this energy constraint may not be valid, since their motion might need much more energy, but links instabilities and short time windows available to receive and transmit data. Therefore, it is better to communicate as little as possible. For the interaction among static sensor nodes, the problems of dissemination and allocation of sensing missions are studied and a solution that explores local information is proposed and evaluated. This solution uses mobile software agents that have capabilities to take autonomous decisions about the mission dissemination and allocation using local context information. For mobile wireless sensor networks, the problem studied is how to perform handover of missions among the nodes according to their movements and locations in relation to the place where the missions have to be performed. To handle this problem, a mobile agent approach is proposed in which the agents implement the sensing missions’ migration from node to node using geographical context information to decide about their migrations. For the networks combining static and mobile sensor nodes, the cooperation among them is approached by a biologically-inspired mechanism to deliver data from the static to the mobile nodes. The data delivery mechanism explores an analogy based on the behaviour of ants building and following trails, inspired by the ant colony algorithm. The proposed solutions are flexible, being able to be applied to different application domains. Obtained experimental results provide evidence of the scalability of these proposed solutions, for example by evaluating their cost in terms of communication, among other metrics of interest for each solution. These results are compared to those achieved by reference solutions (theoretical optimum and floodingbased), providing indications of the proposed solutions’ efficiency. These results are considered close to the theoretical optimum one and significantly better than the ones achieved by flooding-based solutions.

Pronking is a legged locomotory gait in which all legs are used in synchrony, usually resulting in slow speeds but long flight phases and large jumping heights that may potentially be useful for mobile robots locomoting in cluttered natural environments. Instantiations of this gait for robotic systems suffer from severe pitch instability either due to underactuated leg designs, or the open-loop nature of proposed controllers. Nevertheless, both the kinematic simplicity of this gait and its dynamic nature suggest that the Spring-Loaded Inverted Pendulum Model (SLIP), a very successful predictive model for both natural and robotic runners, would be a good basis for more robust and maneuverable robotic pronking. In the scope of thesis, we describe a novel controller to achieve stable and controllable pronking for a planar, underactuated hexapod model, based on the idea of &ldquo / template-based control&rdquo / , a controller structure based on the embedding of a simple dynamical template within a more complex anchor system. In this context, high-level control of the gait is regulated through speed and height commands to the SLIP template, while the embedding controller based on approximate inverse-dynamics and carefully designed passive robot morphology ensures the stability of the remaining degrees of freedom. We show through extensive simulation experiments that unlike existing open-loop alternatives, the resulting control structure provides stability, explicit maneuverability and significant robustness against sensor noise.

Sistemas de vigilância são geralmente empregados no monitoramento de áreas de grandes dimensões nas quais seus usuários visam detectar ou observar fenômenos de seu interesse. O uso de redes de sensores sem fio nesses sistemas apresenta especial interesse, uma vez que essas redes podem apresentar soluções de baixo custo e robustas para cobrir áreas extensas. Neste contexto, novas aplicações têm surgido propondo o uso de redes de sensores sem fio compostas por nós sensores estáticos e móveis. Uma das motivações para esta tendência é a redução do custo de implantação e operação do sistema, além da possibilidade de proporcionar incremento em suas funcionalidades. O foco desta tese se concentra na proposta de soluções para redes de sensores sem fio com uso cooperativo de sensores estáticos e móveis, com particular atenção a sensibilidade ao contexto na configuração e execução de missões de sensoriamento. O objetivo é manter um baixo custo de comunicação associado às soluções propostas. Esta preocupação se dá pelo fato da comunicação aumentar o consumo de energia em redes de sensores, o que é um problema importante para nós sensores com limitada fonte de energia, i.e. baterias. No caso de nós sensores móveis, esta limitação pode não ser relevante, uma vez que seu movimento deve consumir uma quantidade muito mais expressiva de energia do que a comunicação. Neste caso, o problema se relaciona à estabilidade dos enlaces, bem como ao curto intervalo de tempo disponível para transmitir e receber dados. Logo, o melhor é comunicar o menos possível. Com relação à interação entre nós sensores estáticos, os problemas de disseminação e alocação de missões de sensoriamento são estudados e uma solução que explora o uso de informações locais é proposta e avaliada. Esta solução emprega agentes de software móveis que têm a capacidade de tomar decisões autônomas através do uso de informações de contexto local. Para redes de sensores móveis, o problema estudado se refere a como transferir missões entre os nós sensores de acordo com seu movimento e localização em relação aos locais onde as missões devem ser executadas. Para tratar este problema, uma abordagem baseada em agentes móveis é proposta, na qual os agentes implementam a migração das missões de sensoriamento usando informações de contexto geográfico para decidir a respeito de suas migrações. Para redes de sensores com sensores estáticos e móveis, a cooperação entre eles é abordada através de um mecanismo com inspiração biológica para realizar a realizar a entrega de dados emitidos pelos sensores estáticos aos sensores móveis. Para isto, explora-se uma analogia baseada no comportamento de formigas na construção e seguimento de trilhas. As soluções propostas são flexíveis, sendo aplicáveis a diferentes domínios de aplicação. Resultados experimentais evidenciam sua escalabilidade, avaliando, por exemplo, seu custo em termos de comunicação, além de outras métricas de interesse para cada uma das soluções. Estes resultados são comparados aos atingidos por soluções de referência (solução ótima teórica e baseada em inundação), indicando sua eficiência. Estes resultados são próximos do ótimo teórico e significativamente melhores que aqueles atingidos por soluções baseadas em técnicas de inundação. / Surveillance systems are usually employed to monitor wide areas in which their users are interested in detecting and/or observing events or phenomena of their interest. The use of wireless sensor networks in such systems is of particular interest as these networks can provide a relative low cost and robust solution to cover large areas. Emerging applications in this context are proposing the use of wireless sensor networks composed of both static and mobile sensor nodes. Motivation for this trend is to reduce deployment and operating costs, besides providing enhanced functionalities. This work focuses on the proposal of solutions for wireless sensor networks including static and mobile sensor nodes specifically regarding cooperative and context aware mission setup and performance. The goal is to keep the communication costs as low as possible in the execution of the proposed solutions. This concern comes from the fact that communication increases energy consumption, which is a particular issue for energy constrained sensor nodes often used in wireless sensor networks, especially if battery supplied. In the case of the mobile nodes, this energy constraint may not be valid, since their motion might need much more energy, but links instabilities and short time windows available to receive and transmit data. Therefore, it is better to communicate as little as possible. For the interaction among static sensor nodes, the problems of dissemination and allocation of sensing missions are studied and a solution that explores local information is proposed and evaluated. This solution uses mobile software agents that have capabilities to take autonomous decisions about the mission dissemination and allocation using local context information. For mobile wireless sensor networks, the problem studied is how to perform handover of missions among the nodes according to their movements and locations in relation to the place where the missions have to be performed. To handle this problem, a mobile agent approach is proposed in which the agents implement the sensing missions’ migration from node to node using geographical context information to decide about their migrations. For the networks combining static and mobile sensor nodes, the cooperation among them is approached by a biologically-inspired mechanism to deliver data from the static to the mobile nodes. The data delivery mechanism explores an analogy based on the behaviour of ants building and following trails, inspired by the ant colony algorithm. The proposed solutions are flexible, being able to be applied to different application domains. Obtained experimental results provide evidence of the scalability of these proposed solutions, for example by evaluating their cost in terms of communication, among other metrics of interest for each solution. These results are compared to those achieved by reference solutions (theoretical optimum and floodingbased), providing indications of the proposed solutions’ efficiency. These results are considered close to the theoretical optimum one and significantly better than the ones achieved by flooding-based solutions.

Sistemas de vigilância são geralmente empregados no monitoramento de áreas de grandes dimensões nas quais seus usuários visam detectar ou observar fenômenos de seu interesse. O uso de redes de sensores sem fio nesses sistemas apresenta especial interesse, uma vez que essas redes podem apresentar soluções de baixo custo e robustas para cobrir áreas extensas. Neste contexto, novas aplicações têm surgido propondo o uso de redes de sensores sem fio compostas por nós sensores estáticos e móveis. Uma das motivações para esta tendência é a redução do custo de implantação e operação do sistema, além da possibilidade de proporcionar incremento em suas funcionalidades. O foco desta tese se concentra na proposta de soluções para redes de sensores sem fio com uso cooperativo de sensores estáticos e móveis, com particular atenção a sensibilidade ao contexto na configuração e execução de missões de sensoriamento. O objetivo é manter um baixo custo de comunicação associado às soluções propostas. Esta preocupação se dá pelo fato da comunicação aumentar o consumo de energia em redes de sensores, o que é um problema importante para nós sensores com limitada fonte de energia, i.e. baterias. No caso de nós sensores móveis, esta limitação pode não ser relevante, uma vez que seu movimento deve consumir uma quantidade muito mais expressiva de energia do que a comunicação. Neste caso, o problema se relaciona à estabilidade dos enlaces, bem como ao curto intervalo de tempo disponível para transmitir e receber dados. Logo, o melhor é comunicar o menos possível. Com relação à interação entre nós sensores estáticos, os problemas de disseminação e alocação de missões de sensoriamento são estudados e uma solução que explora o uso de informações locais é proposta e avaliada. Esta solução emprega agentes de software móveis que têm a capacidade de tomar decisões autônomas através do uso de informações de contexto local. Para redes de sensores móveis, o problema estudado se refere a como transferir missões entre os nós sensores de acordo com seu movimento e localização em relação aos locais onde as missões devem ser executadas. Para tratar este problema, uma abordagem baseada em agentes móveis é proposta, na qual os agentes implementam a migração das missões de sensoriamento usando informações de contexto geográfico para decidir a respeito de suas migrações. Para redes de sensores com sensores estáticos e móveis, a cooperação entre eles é abordada através de um mecanismo com inspiração biológica para realizar a realizar a entrega de dados emitidos pelos sensores estáticos aos sensores móveis. Para isto, explora-se uma analogia baseada no comportamento de formigas na construção e seguimento de trilhas. As soluções propostas são flexíveis, sendo aplicáveis a diferentes domínios de aplicação. Resultados experimentais evidenciam sua escalabilidade, avaliando, por exemplo, seu custo em termos de comunicação, além de outras métricas de interesse para cada uma das soluções. Estes resultados são comparados aos atingidos por soluções de referência (solução ótima teórica e baseada em inundação), indicando sua eficiência. Estes resultados são próximos do ótimo teórico e significativamente melhores que aqueles atingidos por soluções baseadas em técnicas de inundação. / Surveillance systems are usually employed to monitor wide areas in which their users are interested in detecting and/or observing events or phenomena of their interest. The use of wireless sensor networks in such systems is of particular interest as these networks can provide a relative low cost and robust solution to cover large areas. Emerging applications in this context are proposing the use of wireless sensor networks composed of both static and mobile sensor nodes. Motivation for this trend is to reduce deployment and operating costs, besides providing enhanced functionalities. This work focuses on the proposal of solutions for wireless sensor networks including static and mobile sensor nodes specifically regarding cooperative and context aware mission setup and performance. The goal is to keep the communication costs as low as possible in the execution of the proposed solutions. This concern comes from the fact that communication increases energy consumption, which is a particular issue for energy constrained sensor nodes often used in wireless sensor networks, especially if battery supplied. In the case of the mobile nodes, this energy constraint may not be valid, since their motion might need much more energy, but links instabilities and short time windows available to receive and transmit data. Therefore, it is better to communicate as little as possible. For the interaction among static sensor nodes, the problems of dissemination and allocation of sensing missions are studied and a solution that explores local information is proposed and evaluated. This solution uses mobile software agents that have capabilities to take autonomous decisions about the mission dissemination and allocation using local context information. For mobile wireless sensor networks, the problem studied is how to perform handover of missions among the nodes according to their movements and locations in relation to the place where the missions have to be performed. To handle this problem, a mobile agent approach is proposed in which the agents implement the sensing missions’ migration from node to node using geographical context information to decide about their migrations. For the networks combining static and mobile sensor nodes, the cooperation among them is approached by a biologically-inspired mechanism to deliver data from the static to the mobile nodes. The data delivery mechanism explores an analogy based on the behaviour of ants building and following trails, inspired by the ant colony algorithm. The proposed solutions are flexible, being able to be applied to different application domains. Obtained experimental results provide evidence of the scalability of these proposed solutions, for example by evaluating their cost in terms of communication, among other metrics of interest for each solution. These results are compared to those achieved by reference solutions (theoretical optimum and floodingbased), providing indications of the proposed solutions’ efficiency. These results are considered close to the theoretical optimum one and significantly better than the ones achieved by flooding-based solutions.

Although in many of the tasks in robotics, what is sought mainly includes accuracy, precision, flexibility, adaptivity, etc., yet in wearable robotics, there are some other aspects as well that could distinguish a reliable and promising approach. The three key elements that are addressed are as follows: control, actuation, and sensors. Where the goal for each of the previously mentioned objectives is to find a solution/design compatible with humans. A possible way to understand the human motor behaviours is to generate them on human-like robots. Biologically inspired action generation is promising in control of wearable robots as they provide more natural movements. Furthermore, wearable robotics shows exciting progress, also with its design. Soft exosuits use soft materials to build both sensors and actuators. This work investigates an adaptive representation model for actions in robotics. The concrete action model is composed of four modularities: pattern selection, spatial coordination, temporal coordination, and sensory-motor adaptation. Modularity in motor control might provide us with more insights about action learning and generalisation not only for humanoid robots but also for their biological counterparts. Successfully, we tested the model on a humanoid robot by learning to perform a variety of tasks (push recovery, walking, drawing, grasping, etc.). In the next part, we suggest several soft actuation mechanisms that overcome the problem of holding heavy loads and also the issue of on-line programming of the robot motion. The soft actuators use textile materials hosting thermoplastic polyurethane formed as inflatable tubes. Tubes were folded inside housing channels with one strain-limited side to create a flexor actuator. We proposed a new design to control the strained side of the actuator by adding four textile cords along its longitudinal axis. As a result, the actuator behaviour can be on-line programmed to bend and twist in several directions. In the last part of this thesis, we organised piezoresistive elements in a superimposition structure. The sensory structure is used on a sensory gripper to sense and distinguish between pressure and curvature stimuli. Next, we elaborated the sensing gripper by adding proximity sensing through conductive textile parts added to the gripper and work as capacitive sensors. We finally developed a versatile soft strain sensor that uses silicone tubes with an embedded solution that has an electrical resistance proportional to the strain applied on the tubes. Therefore, an entirely soft sensing glove exhibits hand gestures recognition. The proposed combinations of soft actuators, soft sensors, and biologically inspired action representation might open a new perspective to obtain smart wearable robots. / Obwohl bei vielen Aufgaben in der Robotik vor allem Genauigkeit, Präzision, Flexibilität, Anpassungsfähigkeit usw. gefragt sind, gibt es in der Wearable-Robotik auch einige andere Aspekte, die einen zuverlässigen und vielversprechenden Ansatz kennzeichnen. Die drei Schlüsselelemente, sind die folgenden: Steuerung, Aktuatoren und Sensoren. Dabei ist das Ziel für jedes der genannten Elemente, eine menschengerechte Lösung und ein menschengerechtes Design zu finden. Eine Möglichkeit, die menschliche Motorik zu verstehen, besteht darin, sie auf menschenähnlichen Robotern zu erzeugen. Biologisch inspirierte Bewegungsabläufe sind vielversprechend bei der Steuerung von tragbaren Robotern, da sie natürlichere Bewegungen ermöglichen. Darüber hinaus zeigt die tragbare Robotik spannende Fortschritte bei ihrem Design. Zum Beispiel verwenden softe Exoskelette weiche Materialien, um sowohl Sensoren als auch Aktuatoren zu erschaffen. Diese Arbeit erforscht ein adaptives Repräsentationsmodell für Bewegungen in der Robotik. Das konkrete Bewegungsmodell besteht aus vier Modularitäten: Musterauswahl, räumliche Koordination, zeitliche Koordination und sensorisch-motorische Anpassung. Diese Modularität in der Motorsteuerung könnte uns mehr Erkenntnisse über das Erlernen und Verallgemeinern von Handlungen nicht nur für humanoide Roboter, sondern auch für ihre biologischen Gegenstücke liefern. Erfolgreich testeten wir das Modell an einem humanoiden Roboter, indem dieser gelernt hat eine Vielzahl von Aufgaben auszuführen (Stoß-Ausgleichsbewegungen, Gehen, Zeichnen, Greifen, etc.). Im Folgenden schlagen wir mehrere weiche Aktuatoren vor, welche das Problem des Haltens schwerer Lasten und auch die Frage der Online- Programmierung der Roboterbewegung lösen. Diese weichen Aktuatoren verwenden textile Materialien mit thermoplastischem Polyurethan, die als aufblasbare Schläuche geformt sind. Die Schläuche wurden in Gehäusekanäle mit einer dehnungsbegrenzten Seite gefaltet, um Flexoren zu schaffen. Wir haben ein neues Design vorgeschlagen, um die angespannte Seite eines Flexors zu kontrollieren, indem wir vier textile Schnüre entlang seiner Längsachse hinzufügen. Dadurch kann das Verhalten des Flexors online programmiert werden, um ihn in mehrere Richtungen zu biegen und zu verdrehen. Im letzten Teil dieser Arbeit haben wir piezoresistive Elemente in einer Überlagerungsstruktur organisiert. Die sensorische Struktur wird auf einem sensorischen Greifer verwendet, um Druck- und Krümmungsreize zu erfassen und zu unterscheiden. Den sensorischen Greifer haben wir weiterentwickelt indem wir kapazitiv arbeitende Näherungssensoren mittels leitfähiger Textilteile hinzufügten. Schließlich entwickelten wir einen vielseitigen weichen Dehnungssensor, der Silikonschläuche mit einer eingebetteten resistiven Lösung verwendet, deren Wiederstand sich proportional zur Belastung der Schläuche verhält. Dies ermöglicht einem völlig weichen Handschuh die Erkennung von Handgesten. Die vorgeschlagenen Kombinationen aus weichen Aktuatoren, weichen Sensoren und biologisch inspirierter Bewegungsrepräsentation kann eine neue Perspektive eröffnen, um intelligente tragbare Roboter zu erschaffen.

Dans cette thèse, nous avons étudié le problème de l'estimation de mouvement chez les mammifères et nous proposons que passer à l’échelle des modèles ancrés dans la biologie pour les applications du monde réel peut nous donner de nouvelles perspectives en vision biologique. En utilisant un modèle classique qui décrit l'activité des neurones dans les aires corticales V1 et MT du cerveau des primates, nous avons proposé une architecture montante pour l'estimation de mouvement et l’avons évaluée sur des exemples de référence de vision par ordinateur (une première pour ce type de modèles), révélant des lacunes telles que le manque de sélectivité au niveau des frontières de mouvement et l'absence d'association spatiale du champ de vitesses. Pour y remédier, nous avons proposé deux extensions, une stratégie d’intégration modulée par la forme pour minimiser les erreurs aux discontinuités de texture et un schéma de régression pour le décodage. Ces extensions ont amélioré la précision de l'estimation, mais aussi souligné à nouveau le débat sur le rôle des différents types de cellules dans le codage mouvement, par exemple le rôle relatif des cellules “pattern” par rapport aux cellules “component”. Pour comprendre cela, nous avons utilisé un modèle de champs neuronaux représentant une population de cellules MT pour comprendre le rôle des récurrences. Nos résultats montrent qu'une variété de comportements peuvent être reproduits, ils expliquent les changements dynamiques en fonction des stimuli, et nous conduisent à remettre en cause les régimes élevés d'inhibition généralement choisis dans la littérature. / In this thesis, we studied the problem of motion estimation in mammals and propose that scaling up models rooted in biology for real world applications can give us fresh insights into the biological vision. Using a classic model that describes the activity of directionally-selective neurons in V1 and MT areas of macaque brain, we proposed a feedforward V1-MT architecture for motion estimation and benchmarked it on computer vision datasets (first publicly available evaluation for this kind of models), revealing interesting shortcomings such as lack of selectivity at motion boundaries and lack of spatial association of the flow field. To address these, we proposed two extensions, a form modulated pooling strategy to minimize errors at texture boundaries and a regression based decoding scheme. These extensions improved estimation accuracy but also reemphasized the debate about the role of different cell types (characterized by their tuning curves) in encoding motion, for example relative role of pattern cells versus component cells. To understand this, we used a phenomenological neural fields model representative of a population of directionally tuned MT cells to check whether different tuning behaviors could be reproduced by a recurrently interacting population or if we need different types of cells explicitly. Our results indicated that a variety of tuning behavior can be reproduced by a minimal network, explaining dynamical changes in the tuning with change of stimuli leading us to question the high inhibition regimes typically considered by models in the literature.

No description available.