Skill acquisition and task specific planning are essential components of any robot system, yet they have long been studied in isolation. This, I contend, is due to the lack of a common representational framework. I present a holistic approach to planning robot behavior, using previously acquired skills to represent control knowledge (and objects) directly, and to use this background knowledge to build plans in the space of control actions. Actions in this framework are closed-loop controllers constructed from combinations of sensors, effectors, and potential functions. I will show how robots can use reinforcement learning techniques to acquire sensorimotor programs. The agent then builds a functional model of its interactions with the world as distributions over the acquired skills. In addition, I present two planning algorithms that can reason about a task using the functional models. These algorithms are then applied to a variety of tasks such as object recognition and object manipulation to achieve its objective on two different robot platforms.

" We designed an interactive 3D user interface system to perform object modeling in virtual environments. Expanding on existing 3D user interface techniques, we integrate low-cost human gesture recognition that endows the user with powerful abilities to perform complex virtual object modeling tasks in an immersive game setting. Much research has been done to explore the possibilities of developing biosensors for Virtual Reality (VR) use. In the game industry, even though full body interaction techniques are involved in modern game consoles, most of the utilizations, in terms of game control, are still simple. In this project, we extended the use of motion tracking and gesture recognition techniques to create a new 3D UI system to support immersive gaming. We set a goal for the usability, which is virtual object modeling, and finally developed a game application to test its performance. "

Dans les années 90, la commission européenne a sollicité la mise au point d’un système de contrôle commande et de signalisation ferroviaire commun à tous les réseaux des états membres : le système ERTMS « European Railway Traffic Management System ». Il s’agit d’un système réparti complexe dont le déploiement complet est long et coûteux. L’objectif global consiste à diminuer les coûts de validation et de certification liés à la mise en œuvre de ce nouveau système en Europe. La problématique scientifique réside dans la modélisation formelle de la spécification afin de permettre la génération automatique des scénarios de test. Les verrous scientifiques, traités dans cette thèse, sont liés d’une part à la transformation de modèle semi-formel en modèle formel en préservant les propriétés structurelles et fonctionnelles des constituants réactifs du système réparti, et d’autre part à la couverture des tests générés automatiquement. Les constituants sont sous la forme de boîte noire. L’objectif consiste à tester ces derniers à travers la spécification ERTMS. Nous avons développé une approche de modélisation basée sur le couplage de modèles semi-formels (UML) et de modèles formels (Réseaux de Petri). Ce couplage se fait à travers une technique de transformation de modèles. Nous avons développé ensuite une méthode de génération automatique de scénarios de test de conformité à partir des modèles en réseaux de Petri. Les scénarios de test ont été considérés comme une séquence de franchissement filtrée puis réduite du réseau de Petri interprété représentant la spécification. Ces scénarios ont été exécutés sur notre plateforme de simulation ERTMS / European Union set up a European rail traffic management system “ERTMS” to ensure, with high level of safety, train operation on different European networks. As the full deployment of this system is long and expensive, evolutions are necessary and raise other technological challenges. The goal is to determine how to use ERTMS specifications to produce test scenarios. This work presents methods, models and tools dedicated to the generation of test scenarios for the validation of ERTMS components based on functional requirements. The development of ERTMS system requires adequate methods for Modelling and evaluating its behavior. Evaluation and certification of the system can be done by generating test scenarios applying formal methods. The Unified Modelling Language (UML) is a widely accepted Modelling standard in industry. However, it is a semi-formal language and it does not allow verification of system behavior. In this case, formal models like Petri Net can be used. These methods are used in order to formalize ERTMS specification. Tests scenarios are generated on the basis of Petri net models. One scenario is considered like a firing sequence in the reachability graph of the Petri net. Then, test scenarios are applied on ERTMS platform simulator in order to check the components and to give test verdicts. Finally, the approach, developed in this document, has been applied to ERTMS components in order to demonstrate the validation and certification costs reduction and also to minimize the upgrade and retrofit constraints and validation cost

Cette thèse traite des problèmes de modélisation, reconnaissance, localisation et utilisation du contexte pour la manipulation d'objets par un robot. Le processus de modélisation se divise en quatre composantes : le système réel, les données capteurs, les propriétés à reproduire et le modèle. En spécifiant chacune des ces composantes, il est possible de définir un processus de modélisation adapté au problème présent, la manipulation d'objets par un robot. Cette analyse mène à l'adoption des descripteurs de texture locaux pour la modélisation. La modélisation basée sur des descripteurs de texture locaux a été abordé dans de nombreux travaux traitant de structure par le mouvement (SfM) ou de cartographie et localisation simultanée (SLAM). Les méthodes existantes incluent Bundler, Roboearth et 123DCatch. Pourtant, aucune de ces méthodes n'a recueilli le consensus. En effet, l'implémentation d'une approche similaire montre que ces outils sont difficiles d'utilisation même pour des utilisateurs experts et qu'ils produisent des modèles d'une haute complexité. Cette complexité est utile pour fournir un modèle robuste aux variations de point de vue. Il existe deux façons pour un modèle d'être robuste : avec le paradigme des vues multiple ou celui des descripteurs forts. Dans le paradigme des vues multiples, le modèle est construit à partir d'un grand nombre de points de vue de l'objet. Le paradigme des descripteurs forts compte sur des descripteurs résistants aux changements de points de vue. Les expériences réalisées montrent que des descripteurs forts permettent d'utiliser un faible nombre de vues, ce qui résulte en un modèle simple. Ces modèles simples n'incluent pas tout les point de vus existants mais les angles morts peuvent être compensés par le fait que le robot est mobile et peut adopter plusieurs points de vue. En se basant sur des modèles simples, il est possible de définir des méthodes de modélisation basées sur des images seules, qui peuvent être récupérées depuis Internet. A titre d'illustration, à partir d'un nom de produit, il est possible de récupérer des manières totalement automatiques des images depuis des magasins en ligne et de modéliser puis localiser les objets désirés. Même avec une modélisation plus simple, dans des cas réel ou de nombreux objets doivent être pris en compte, il se pose des problèmes de stockage et traitement d'une telle masse de données. Cela se décompose en un problème de complexité, il faut traiter de nombreux modèles rapidement, et un problème d'ambiguïté, des modèles peuvent se ressembler. L'impact de ces deux problèmes peut être réduit en utilisant l'information contextuelle. Le contexte est toute information non issue des l'objet lui même et qui aide a la reconnaissance. Ici deux types de contexte sont abordés : le lieu et les objets environnants. Certains objets se trouvent dans certains endroits particuliers. En connaissant ces liens lieu/objet, il est possible de réduire la liste des objets candidats pouvant apparaître dans un lieu donné. Par ailleurs l'apprentissage du lien lieu/objet peut être fait automatiquement par un robot en modélisant puis explorant un environnement. L'information appris peut alors être fusionnée avec l'information visuelle courante pour améliorer la reconnaissance. Dans les cas des objets environnants, un objet peut souvent apparaître au cotés d'autres objets, par exemple une souris et un clavier. En connaissant la fréquence d'apparition d'un objet avec d'autres objets, il est possible de réduire la liste des candidats lors de la reconnaissance. L'utilisation d'un Réseau de Markov Logique est particulièrement adaptée à la fusion de ce type de données. Cette thèse montre la synergie de la robotique et du contexte pour la modélisation, reconnaissance et localisation d'objets. / This Thesis addresses the modeling, recognition, localization and use of context for objects manipulation by a robot. We start by presenting the modeling process and its components: the real system, the sensors' data, the properties to reproduce and the model. We show how, by specifying each of them, one can define a modeling process adapted to the problem at hand, namely object manipulation by a robot. This analysis leads us to the adoption of local textured descriptors for object modeling. Modeling with local textured descriptors is not a new concept, it is the subject of many Structure from Motion (SfM) or Simultaneous Localization and Mapping (SLAM) works. Existing methods include bundler, roboearth modeler and 123DCatch. Still, no method has gained widespread adoption. By implementing a similar approach, we show that they are hard to use even for expert users and produce highly complex models. Such complex techniques are necessary to guaranty the robustness of the model to view point change. There are two ways to handle the problem: the multiple views paradigm and the robust features paradigm. The multiple views paradigm advocate in favor of using a large number of views of the object. The robust feature paradigm relies on robust features able to resist large view point changes. We present a set of experiments to provide an insight into the right balance between both. By varying the number of views and using different features we show that small and fast models can provide robustness to view point changes up to bounded blind spots which can be handled by robotic means. We propose four different methods to build simple models from images only, with as little a priori information as possible. The first one applies to planar or piecewise planar objects and relies on homographies for localization. The second approach is applicable to objects with simple geometry, such as cylinders or spheres, but requires many measures on the object. The third method requires the use of a calibrated 3D sensor but no additional information. The fourth technique doesn't need a priori information at all. We apply this last method to autonomous grocery objects modeling. From images automatically retrieved from a grocery store website, we build a model which allows recognition and localization for tracking. Even using light models, real situations ask for numerous object models to be stored and processed. This poses the problems of complexity, processing multiple models quickly, and ambiguity, distinguishing similar objects. We propose to solve both problems by using contextual information. Contextual information is any information helping the recognition which is not directly provided by sensors. We focus on two contextual cues: the place and the surrounding objects. Some objects are mainly found in some particular places. By knowing the current place, one can restrict the number of possible identities for a given object. We propose a method to autonomously explore a previously labeled environment and establish a correspondence between objects and places. Then this information can be used in a cascade combining simple visual descriptors and context. This experiment shows that, for some objects, recognition can be achieved with as few as two simple features and the location as context. The objects surrounding a given object can also be used as context. Objects like a keyboard, a mouse and a monitor are often close together. We use qualitative spatial descriptors to describe the position of objects with respect to their neighbors. Using a Markov Logic Network, we learn patterns in objects disposition. This information can then be used to recognize an object when surrounding objects are already identified. This Thesis stresses the good match between robotics, context and objects recognition.

<p>This thesis presents a computational model of the surgical stitching tasks and a path planning algorithm for robotic assisted stitching. The overall goal of the research is to enable surgical robots to perform automatic suturing. Suturing comprises several distinct steps, one of them is the stitching. During stitching, reaching the desired exit point is difficult because it must be accomplished without direct visual feedback. Moreover, the stitching is a time consuming procedure repeated multiple times during suturing. Therefore, it would be desirable to enhance the surgical robots with the ability of performing automatic suturing. The focus of this work is on the automation of the stitching task. The thesis presents a model based path planning algorithm for the autonomous stitching. The method uses a nonlinear model for the curved needle - soft tissue interaction. The tissue is modeled as a deformable object using continuum mechanics tools. This thesis uses a mesh free deformable tissue model namely, Reproducing Kernel Particle Method (RKPM). RKPM was chosen as it has been proven to accurately handle large deformation and requires no re-meshing algorithms. This method has the potential to be more realistic in modeling various material characteristics by using appropriate strain energy functions. The stitching task is simulated using a constrained deformable model; the deformable tissue is constrained by the interaction with the curved needle. The stitching model was used for needle trajectory path planning during stitching. This new path planning algorithm for the robotic stitching was developed, implemented, and evaluated. Several simulations and experiments were conducted. The first group of simulations comprised random insertions from different insertion points without planning to assess the modeling method and the trajectory of the needle inside the tissue. Then the parameters of the simulations were set according to the measured experimental parameters. The proposed path planning method was tested using a surgical ETHICON needle of type SH 1=2 Circle with the radius of 8:88mm attached to a robotic manipulator. The needle was held by a grasper which is attached to the robotic arm. The experimental results illustrate that the path planned curved needle insertions are fifty percent more accurate than the unplanned ones. The results also show that this open loop approach is sensitive to model parameters.</p> / Master of Applied Science (MASc)

Esta tese de doutorado aborda os tópicos de modelagem e de reconhecimento de objetos estruturados, ou sistemas estruturados de objetos, em imagens. Um objeto ou sistema estruturado é aquele que pode ser descrito através de elementos primitivos que o compõem e pelas relações existentes entre esses elementos. Por exemplo, uma aeronave pode ser descrita pelos seguintes elementos primitivos: asas direita e esquerda, fuselagem e cockpit. O aspecto relacional de um objeto estruturado direciona sua representação computacional e seu reconhecimento em imagens ao paradigma estrutural de reconhecimento de padrões. Contudo, a variabilidade das características dos seus elementos primitivos é melhor representada através do paradigma estatístico de reconhecimento de padrões. Devido à complementaridade dos paradigmas, a conjunção dessas abordagens é um tema de pesquisa de interesse atual. Para conjugar esses dois aspectos, esta tese propôs uma metodologia que combina o conhecimento a priori das relações que caracterizam um objeto estruturado com dados estatísticos coletados de amostras desse objeto, num modelo híbrido denominado grafo estatístico-relacional (GER). Segundo essa representação, foi estudada uma abordagem probabilística para reconhecer um objeto estruturado em imagens. Nesse cenário, o GER modelo é considerado uma variável aleatória, enquanto uma rotulação de uma imagem de entrada é interpretada como uma potencial observação do modelo. A tarefa de reconhecimento foi então formulada como um problema de otimização, que busca maximizar a probabilidade da observação de acordo com o modelo. O método foi aplicado à modelagem de órgãos abdominais em imagens de ressonância magnética não-contrastadas. Esses órgãos apresentam um arranjo espacial consistente em imagens distintas, além de propriedades de aparência e anatômicas variáveis, o que vem ao encontro da proposta da representação por GER e da abordagem probabilística para o reconhecimento dos órgãos em novas imagens. / The purpose of this thesis was to propose a formalism for the problems of modeling and recognition of a structured object, or a system of structured objects, in images. A structured object is one that may be described in terms of its compound primitive elements and their inherent relations. For instance, an aircraft may be described in terms of the following primitives: right and left wings, fuselage, and cockpit. The relational aspect of structured objects leads these problems to solutions in structural pattern recognition, which describes patterns as primitives and relations. Nevertheless, the variability of primitive elements and of their relations is better modeled by traditional statistical pattern recognition methods. Because of the complementary capabilities of these approaches, the fusion of both has recently been pointed out as a trend in computer vision. To consider these sources of information, the methodology presented herein combines relational cues inherent to a structured object with statistical information learned from a set of object samples. A hybrid model of a structured object is represented by means of a statistical relational graph (SRG). The SRG is a prototype attributed relational graph (ARG) in which nodes represent primitive elements and arcs link nodes representing related primitives. Each node or arc is associated with attributes which are parameters of probability distributions that describe random variables representing primitive or relational attributes. Based on this representation, a probabilistic approach was proposed to tackle the problem of recognizing a structured object in an input image. The model SRG is interpreted as a random variable, whereas a labeling of the input image is considered a potential observation of the model. The recognition task was formulated as the optimization of an objective-function that is actually a probability measure to be maximized. The proposed approach was applied to the modeling of abdominal organs in non-contrasted magnetic resonance images. These organs present consistent spatial arrangement in distinct images, as well as varying appearance and anatomical properties, which meet the principle of the SRG representation and the associated probabilistic recognition scenario.

Esta tese de doutorado aborda os tópicos de modelagem e de reconhecimento de objetos estruturados, ou sistemas estruturados de objetos, em imagens. Um objeto ou sistema estruturado é aquele que pode ser descrito através de elementos primitivos que o compõem e pelas relações existentes entre esses elementos. Por exemplo, uma aeronave pode ser descrita pelos seguintes elementos primitivos: asas direita e esquerda, fuselagem e cockpit. O aspecto relacional de um objeto estruturado direciona sua representação computacional e seu reconhecimento em imagens ao paradigma estrutural de reconhecimento de padrões. Contudo, a variabilidade das características dos seus elementos primitivos é melhor representada através do paradigma estatístico de reconhecimento de padrões. Devido à complementaridade dos paradigmas, a conjunção dessas abordagens é um tema de pesquisa de interesse atual. Para conjugar esses dois aspectos, esta tese propôs uma metodologia que combina o conhecimento a priori das relações que caracterizam um objeto estruturado com dados estatísticos coletados de amostras desse objeto, num modelo híbrido denominado grafo estatístico-relacional (GER). Segundo essa representação, foi estudada uma abordagem probabilística para reconhecer um objeto estruturado em imagens. Nesse cenário, o GER modelo é considerado uma variável aleatória, enquanto uma rotulação de uma imagem de entrada é interpretada como uma potencial observação do modelo. A tarefa de reconhecimento foi então formulada como um problema de otimização, que busca maximizar a probabilidade da observação de acordo com o modelo. O método foi aplicado à modelagem de órgãos abdominais em imagens de ressonância magnética não-contrastadas. Esses órgãos apresentam um arranjo espacial consistente em imagens distintas, além de propriedades de aparência e anatômicas variáveis, o que vem ao encontro da proposta da representação por GER e da abordagem probabilística para o reconhecimento dos órgãos em novas imagens. / The purpose of this thesis was to propose a formalism for the problems of modeling and recognition of a structured object, or a system of structured objects, in images. A structured object is one that may be described in terms of its compound primitive elements and their inherent relations. For instance, an aircraft may be described in terms of the following primitives: right and left wings, fuselage, and cockpit. The relational aspect of structured objects leads these problems to solutions in structural pattern recognition, which describes patterns as primitives and relations. Nevertheless, the variability of primitive elements and of their relations is better modeled by traditional statistical pattern recognition methods. Because of the complementary capabilities of these approaches, the fusion of both has recently been pointed out as a trend in computer vision. To consider these sources of information, the methodology presented herein combines relational cues inherent to a structured object with statistical information learned from a set of object samples. A hybrid model of a structured object is represented by means of a statistical relational graph (SRG). The SRG is a prototype attributed relational graph (ARG) in which nodes represent primitive elements and arcs link nodes representing related primitives. Each node or arc is associated with attributes which are parameters of probability distributions that describe random variables representing primitive or relational attributes. Based on this representation, a probabilistic approach was proposed to tackle the problem of recognizing a structured object in an input image. The model SRG is interpreted as a random variable, whereas a labeling of the input image is considered a potential observation of the model. The recognition task was formulated as the optimization of an objective-function that is actually a probability measure to be maximized. The proposed approach was applied to the modeling of abdominal organs in non-contrasted magnetic resonance images. These organs present consistent spatial arrangement in distinct images, as well as varying appearance and anatomical properties, which meet the principle of the SRG representation and the associated probabilistic recognition scenario.

The advancements in robotic perception in the recent years have empowered robots to better execute tasks in various environments. The perception of objects in the robot work space significantly relies on how sensory data is represented. In this context, 3D models of object’s surfaces have been studied as a means to provide useful insights on shape of objects and ultimately enhance robotic perception. This involves several challenges, because sensory data generally presents artifacts, such as noise and incompleteness. To tackle this problem, we employ Gaussian Process Implicit Surface (GPIS), a non-parametric probabilistic reconstruction of object’s surfaces from 3D data points. This thesis investigates different configurations for GPIS, as a means to tackle the extraction of shape information. In our approach we interpret an object’s surface as the level-set of an underlying sparse Gaussian Process (GP) with variational formulation. Results show that the variational formulation for sparse GP enables a reliable approximation to the full GP solution. Experiments are performed on a synthetic and a real sensory data set. We evaluate results by assessing how close the reconstructed surfaces are to the ground-truth correspondences, and how well objects from different categories are clustered based on the obtained representation. Finally we conclude that the proposed solution derives adequate surface representations to reason about object shape and to discriminate objects based on shape information. / Framsteg inom robotperception de senaste åren har resulterat i robotar som är bättre på attutföra uppgifter i olika miljöer. Perception av objekt i robotens arbetsmiljö är beroende avhur sensorisk data representeras. I det här sammanhanget har 3D-modeller av objektytorstuderats för att ge användbar insikt om objektens form och i slutändan bättre robotperception. Detta innebär flera utmaningar, eftersom sensoriska data ofta innehåller artefakter, såsom brus och brist på data. För att hantera detta problem använder vi oss av Gaussian Process Implicit Surface (GPIS), som är en icke-parametrisk probabilistisk rekonstruktion av ett objekts yta utifrån 3D-punkter. Detta examensarbete undersöker olika konfigurationer av GPIS för att på detta sätt kunna extrahera forminformation. I vår metod tolkar vi ett objekts yta som nivåkurvor hos en underliggande gles variational Gaussian Process (GP) modell. Resultat visar att en gles variational GP möjliggör en tillförlitlig approximation av en komplett GP-lösningen. Experiment utförs på ett syntetisk och ett reellt sensorisk dataset. Vi utvärderar resultat genom att bedöma hur nära de rekonstruerade ytorna är till grundtruth- korrespondenser, och hur väl objektkategorier klustras utifrån den erhållna representationen. Slutligen konstaterar vi att den föreslagna lösningen leder till tillräckligt goda representationer av ytor för tolkning av objektens form och för att diskriminera objekt utifrån forminformation.