Cette thèse aborde le problème de localisation et cartographie simultanée pour un robot mobile. Lorsque le robot Évolue dans un environnement inconnu, il doit construire une carte au fur et mesure qu'il explore le monde, tout en se localisant dans celle-ci. De l'anglais \textit{Simultaneous Localisation And Mapping}, le SLAM est une brique essentielle de l'architecture d'un robot autonome. Plusieurs éléments sont nécessaire ‡ la résolution du SLAM, en particulier la perception de l'environnement permet d'observer les éléments de référence (appelés amers) qui constituent la carte. Ces travaux se focalisent sur l'utilisation de la vision artificielle comme moyen de percevoir l'environnement, ainsi la carte et la position du robot peuvent être estimées dans l'espace 3D complet. Les caméras numériques sont des capteurs bien adaptés aux systèmes embarqués et fournissent une information riche sur l'environnement. Mais une caméra ne permet pas de mesurer la distance aux objets, dont on n'obtient donc que des observations partielles. En particulier, ceci rend difficile l'ajout d'un nouvel amer dans la carte. Une méthode d'initialisation pour des amers de type point est proposée, elle s'appuie sur un mécanisme de génération puis de sélection d'hypothèses. Une architecture SLAM pour un robot terrestre est décrite dans son ensemble, en particulier une caméra panoramique est utilisée et permet de percevoir l'environnement sur 360 degrés. Cette architecture a été implémentée sur un robot de type ATRV. Une carte de points 3D est pertinente pour la localisation d'un robot, mais donne une information limitée sur la structure de l'environnement. Un algorithme permettant d'utiliser des segments de droite est proposé, et testé sur des données réelles

La problématique SLAM (Simultaneous Localization and Mapping) est un thème largement étudié au LAAS depuis plusieurs années. L'application visée concerne le développement d'un système d'aide au roulage sur aéroport des avions de ligne, ce système devant être opérationnel quelques soient les conditions météorologiques et de luminosité (projet SART financé par la DGE en partenariat avec principalement FLIR Systems, Latécoère et Thales). Lors de conditions de visibilité difficile (faible luminosité, brouillard, pluie...), une seule caméra traditionnelle n'est pas suffisante pour assurer la fonction de localisation. Dans un premier temps, on se propose d'étudier l'apport d'une caméra infrarouge thermique. Dans un deuxième temps, on s'intéressera à l'utilisation d'une centrale inertielle et d'un GPS dans l'algorithme de SLAM, la centrale aidant à la prédiction du mouvement, et le GPS à la correction des divergences éventuelles. Enfin, on intègrera dans ce même SLAM des pseudo-observations issues de l'appariement entre des segments extraits des images, et ces mêmes segments contenus dans une cartographie stockée dans une base de données. L'ensemble des observations et pseudo-observations a pour but de localiser le porteur à un mètre près. Les algorithmes devant être portés sur un FPGA muni d'un processeur de faible puissance par rapport aux PC standard (400 MHz), un co-design devra donc être effectué entre les éléments logiques du FPGA réalisant le traitement d'images à la volée et le processeur embarquant le filtre de Kalman étendu (EKF) pour le SLAM, de manière à garantir une application temps-réel à 30 Hz. Ces algorithmes spécialement développés pour le co-design et les systèmes embarqués avioniques seront testés sur la plate-forme robotique du LAAS, puis portés sur différentes cartes de développement (Virtex 5, Raspberry, PandaBoard...) en vue de l'évaluation des performances

This thesis examines the use of multiple robots in cooperative simultaneous localization and mapping (SLAM), where each robot must estimate the poses of all robots in the team, along with the positions of all known landmarks. The robot team must operate under the condition that the communication network between robots is never guaranteed to be fully connected. Under this condition, a novel algorithm is derived that allows each robot to obtain the centralized-equivalent estimate in a decentralized manner, whenever possible. The algorithm is then extended to a decentralized and distributed approach where robots share the computational burden in considering different data association hypotheses in generating the centralized-equivalent consensus estimate.

As the applications of mobile robotics evolve it has become increasingly less practical for researchers to design custom hardware and control systems for each problem. This research presents a new approach to control system design that looks beyond end-of-lifecycle performance and considers control system structure, flexibility, and extensibility. Toward these ends the Control ad libitum philosophy is proposed, stating that to make significant progress in the real-world application of mobile robot teams the control system must be structured such that teams can be formed in real-time from diverse components. The Control ad libitum philosophy was applied to the design of the HAA (Host, Avatar, Agent) architecture: a modular hierarchical framework built with provably correct distributed algorithms. A control system for exploration and mapping, search and deploy, and foraging was developed to evaluate the architecture in three sets of hardware-in-the-loop experiments. First, the basic functionality of the HAA architecture was studied, specifically the ability to: a) dynamically form the control system, b) dynamically form the robot team, c) dynamically form the processing network, and d) handle heterogeneous teams. Secondly, the real-time performance of the distributed algorithms was tested, and proved effective for the moderate sized systems tested. Furthermore, the distributed Just-in-time Cooperative Simultaneous Localization and Mapping (JC-SLAM) algorithm demonstrated accuracy equal to or better than traditional approaches in resource starved scenarios, while reducing exploration time significantly. The JC-SLAM strategies are also suitable for integration into many existing particle filter SLAM approaches, complementing their unique optimizations. Thirdly, the control system was subjected to concurrent software and hardware failures in a series of increasingly complex experiments. Even with unrealistically high rates of failure the control system was able to successfully complete its tasks. The HAA implementation designed following the Control ad libitum philosophy proved to be capable of dynamic team formation and extremely robust against both hardware and software failure; and, due to the modularity of the system there is significant potential for reuse of assets and future extensibility. One future goal is to make the source code publically available and establish a forum for the development and exchange of new agents.

This thesis examines the use of multiple robots in cooperative simultaneous localization and mapping (SLAM), where each robot must estimate the poses of all robots in the team, along with the positions of all known landmarks. The robot team must operate under the condition that the communication network between robots is never guaranteed to be fully connected. Under this condition, a novel algorithm is derived that allows each robot to obtain the centralized-equivalent estimate in a decentralized manner, whenever possible. The algorithm is then extended to a decentralized and distributed approach where robots share the computational burden in considering different data association hypotheses in generating the centralized-equivalent consensus estimate.

As the applications of mobile robotics evolve it has become increasingly less practical for researchers to design custom hardware and control systems for each problem. This research presents a new approach to control system design that looks beyond end-of-lifecycle performance and considers control system structure, flexibility, and extensibility. Toward these ends the Control ad libitum philosophy is proposed, stating that to make significant progress in the real-world application of mobile robot teams the control system must be structured such that teams can be formed in real-time from diverse components. The Control ad libitum philosophy was applied to the design of the HAA (Host, Avatar, Agent) architecture: a modular hierarchical framework built with provably correct distributed algorithms. A control system for exploration and mapping, search and deploy, and foraging was developed to evaluate the architecture in three sets of hardware-in-the-loop experiments. First, the basic functionality of the HAA architecture was studied, specifically the ability to: a) dynamically form the control system, b) dynamically form the robot team, c) dynamically form the processing network, and d) handle heterogeneous teams. Secondly, the real-time performance of the distributed algorithms was tested, and proved effective for the moderate sized systems tested. Furthermore, the distributed Just-in-time Cooperative Simultaneous Localization and Mapping (JC-SLAM) algorithm demonstrated accuracy equal to or better than traditional approaches in resource starved scenarios, while reducing exploration time significantly. The JC-SLAM strategies are also suitable for integration into many existing particle filter SLAM approaches, complementing their unique optimizations. Thirdly, the control system was subjected to concurrent software and hardware failures in a series of increasingly complex experiments. Even with unrealistically high rates of failure the control system was able to successfully complete its tasks. The HAA implementation designed following the Control ad libitum philosophy proved to be capable of dynamic team formation and extremely robust against both hardware and software failure; and, due to the modularity of the system there is significant potential for reuse of assets and future extensibility. One future goal is to make the source code publically available and establish a forum for the development and exchange of new agents.

For robots to operate in human environments they must be able to make their own maps because it is unrealistic to expect a user to enter a map into the robot’s memory; existing floorplans are often incorrect; and human environments tend to change. Traditionally robots have used sonar, infra-red or laser range finders to perform the mapping task. Digital cameras have become very cheap in recent years and they have opened up new possibilities as a sensor for robot perception. Any robot that must interact with humans can reasonably be expected to have a camera for tasks such as face recognition, so it makes sense to also use the camera for navigation. Cameras have advantages over other sensors such as colour information (not available with any other sensor), better immunity to noise (compared to sonar), and not being restricted to operating in a plane (like laser range finders). However, there are disadvantages too, with the principal one being the effect of perspective. This research investigated ways to use a single colour camera as a range sensor to guide an autonomous robot and allow it to build a map of its environment, a process referred to as Simultaneous Localization and Mapping (SLAM). An experimental system was built using a robot controlled via a wireless network connection. Using the on-board camera as the only sensor, the robot successfully explored and mapped indoor office environments. The quality of the resulting maps is comparable to those that have been reported in the literature for sonar or infra-red sensors. Although the maps are not as accurate as ones created with a laser range finder, the solution using a camera is significantly cheaper and is more appropriate for toys and early domestic robots.

Extrair informação de profundidade a partir de imagens bidimensionais é um importante problema na área de visão computacional. Diversas aplicações se beneficiam desta classe de algoritmos tais como: robótica, a indústria de entretenimento, aplicações médicas para diagnóstico e confecção de próteses e até mesmo exploração interplanetária. Esta aplicação pode ser dividida em duas etapas interdependentes: a estimação da posição e orientação da câmera no momento em que a imagem foi gerada, e a estimativa da estrutura tridimensional da cena. Este trabalho foca em técnicas de visão computacional usadas para estimar a trajetória de um veículo equipado com uma câmera, problema conhecido como odometria visual. Para obter medidas objetivas de eficiência e precisão, e poder comparar os resultados obtidos com o estado da arte, uma base de dados de alta precisão, bastante utilizada pela comunidade científica foi utilizada. No curso deste trabalho novas técnicas para rastreamento de detalhes, estimativa de posição de câmera, cálculo de posição 3D de pontos e recuperação de escala são propostos. Os resultados alcançados superam os mais bem ranqueados trabalhos na base de dados escolhida até o momento da publicação desta tese. / Recovering three-dimensional information from bi-dimensional images is an important problem in computer vision that finds several applications in our society. Robotics, entertainment industry, medical diagnose and prosthesis, and even interplanetary exploration benefit from vision based 3D estimation. The problem can be divided in two interdependent operations: estimating the camera position and orientation when each image was produced, and estimating the 3D scene structure. This work focuses on computer vision techniques, used to estimate the trajectory of a vehicle equipped camera, a problem known as visual odometry. In order to provide an objective measure of estimation efficiency and to compare the achieved results to the state-of-the-art works in visual odometry a high precision popular dataset was selected and used. In the course of this work new techniques for image feature tracking, camera pose estimation, point 3D position calculation and scale recovery are proposed. The achieved results outperform the best ranked results in the popular chosen dataset.

SOUZA, Tiago Barbosa. A performance na cantoria nordestina e no slam. 2011. 137f. – Dissertação (Mestrado) – Universidade Federal do Ceará, Programa de Pós-graduação em Letras, Fortaleza (CE), 2011. / Submitted by Márcia Araújo (marcia_m_bezerra@yahoo.com.br) on 2014-09-30T17:27:42Z No. of bitstreams: 1 2011_dis_tbsouza.pdf: 3553587 bytes, checksum: cb30c7ff8d267a6add28686e3d738cf7 (MD5) / Approved for entry into archive by Márcia Araújo(marcia_m_bezerra@yahoo.com.br) on 2014-10-01T11:21:48Z (GMT) No. of bitstreams: 1 2011_dis_tbsouza.pdf: 3553587 bytes, checksum: cb30c7ff8d267a6add28686e3d738cf7 (MD5) / Made available in DSpace on 2014-10-01T11:21:48Z (GMT). No. of bitstreams: 1 2011_dis_tbsouza.pdf: 3553587 bytes, checksum: cb30c7ff8d267a6add28686e3d738cf7 (MD5) Previous issue date: 2011 / A presente dissertação intenciona investigar a performance na cantoria nordestina brasileira e no slam, gênero poético também popular, mas de surgimento mais recente, criado nos Estados Unidos na década de 1980 e de forte influência hoje na França. Algumas formas da literatura oral popular do Nordeste brasileiro têm características muito próximas àquelas do slam, entre as quais, ressalta-se a importância do corpo e de sua emanação, a voz, o que é determinante para a atração e fidelização dos espectadores, seja nos festivais de repente do Brasil, seja nos torneios de slam na França. Entre as linhas gerais que permitem a aproximação dos dois gêneros, podem-se ressaltar o jogo interativo com o público, que se mostra peça fundamental na produção poética; os aspectos relativos às formas do texto, como a métrica dos versos, as rimas e o ritmo; o teor ritualístico das duas formas; entre outros elementos de relevante discussão. O slam encontra também algumas diferenças em relação à cantoria, como o teor primordialmente urbano e a presença determinante da escrita. Esses fatores expõem peculiaridades interessantes nas duas práticas e compõem parte das preocupações com que se depara esta dissertação. Enquanto o slameur, aquele que produz o slam, costuma ter escolaridade, ser formado em um meio urbano e contar necessariamente com a escrita no momento da produção do slam, o tradicional cantador nordestino brasileiro não costuma precisar dela para a sua criação poética: esse poeta cria recitando, memoriza, reproduz, modifica dependendo da situação, improvisa repentes, joga com o público e com seu companheiro de cantoria, enfim, molda e articula sua composição no momento mesmo da criação ou da apresentação. A análise a ser desenvolvida parte da noção de performance utilizada por Paul Zumthor. Para tanto, propõe-se apresentar os dois gêneros paralelamente, levando em consideração os seus índices de oralidade e buscando analogias no que concerne ao aspecto circunstancial e coincidente com a presença do público, ao teor cênico dessas práticas, à métrica dos versos, às temáticas, ao público-alvo e às peculiaridades encontradas em ambos os contextos sociais. / Cette dissertation a pour but de faire des recherches sur la performance dans la cantoria du Nordeste brésilien et sur le slam, genre poétique aussi populaire, mais d’apparition plus récente, créé aux États-Unis dans les années 1980 et de forte influence aujourd’hui en France. Certaines formes de la littérature orale populaire du Nordeste ont des caractéristiques très proches de celles du slam, dont on peut citer l’importance du corps et de son émanation, la voix, ce qui est déterminant pour l’attraction et fidélisation des spectateurs, soit aux festivals de repente du Brésil, soit aux tournois de slam de France. Entre les lignes générales qui permettent le rapprochement des deux genres, on peut observer le jeu interactif avec le public, qui se présente comme une pièce fondamentale dans la production poétique ; les aspects relatifs aux formes du texte, comme la métrique des vers, les rimes et le rythme ; le caractère ritualiste de ses formes ; entre autres éléments de significative discussion. Le slam présente aussi quelques différences par rapport à la cantoria, comme le caractère primordialement urbain et la présence déterminante de l’écriture. Ces facteurs exposent des particularités intéressantes aux deux pratiques et composent une partie des préoccupations que développe cette dissertation. Tandis que le slameur, en général, est scolarisé, formé dans un milieu urbain et compte nécessairement sur l’écriture au moment de sa production, le traditionnel cantador brésilien n’en a généralement pas besoin pour sa création poétique : ce poète crée en récitant, il mémorise, reproduit, modifie en fonction de la situation, improvise des repentes, joue avec le public et avec son rival de cantoria, enfin, il formule et articule sa composition au moment même de la création ou de la présentation. L’analyse développée dans ce travail part de la notion de performance traitée par Paul Zumthor. Pour cela, nous proposons de présenter les deux genres parallèlement, tout en considérant leurs indices d’oralité et en cherchant des analogies en ce qui concerne l’aspect circonstanciel de connivence avec le public, le caractère scénique de ces pratiques, la mesure des vers, les thématiques, le public-cible et les particuliarités trouvées dans les deux contextes sociaux

abstract: This research features a phenomenological investigation of the interactions between adolescent storytellers and audience members during a live storytelling event. The researcher partnered with an English teacher in an urban Southwest high school and a spoken word poet from a youth nonprofit to produce a storytelling workshop and corresponding story slam event for high school students. Fourteen participants, including seven student storytellers and seven student audience members, participated in extensive follow-up interviews where they described the experience of their respective roles during the event. Utilizing a phenomenological design (Moustakas, 1994; Vagle, 2014) and drawing from reception theory (Bennett, 1997; Hall, 1980) as a framework, the researcher used participant descriptions to compose a textural-structural synthesis collectively describing the phenomenon of interaction, connection, and transaction between storytellers and audience members during the live event. The textural-structural synthesis of participants’ descriptions comprises four major essences of the transactional phenomenon. These include 1) the relational symbiosis of storytellers and audience members, 2) the nature of the story slam as a planned and produced event, 3) the storytellers’ inclusions of specific, personal details which resonated with specific, personal details in audience members’ lives, and 4) the storytellers’ intentional style and content choices which corresponded with reactions from audience members. These findings provide a platform for fostering conditions for interaction, connection, and transaction in curricular and extra-curricular secondary contexts. For a classroom teacher, they may be helpful in creating principles for optimizing interactions between teachers and students in instruction and between students in collaboration. In extra-curricular contexts, these findings provide a platform for consideration of how to hold space for creative performance once spaces for creative expression have been made for youth. / Dissertation/Thesis / Doctoral Dissertation English 2018