<p>Human multi-robot systems constitute a relatively new area of research that focuses on the interaction and collaboration between humans and multiple robots. Well-designed systems can enable a team of humans and robots to effectively work together on complex and sophisticated tasks such as exploration, monitoring, and search and rescue operations. This dissertation introduces an affective workload allocation system capable of adaptively allocating workload in real-time while considering the conditions and work performance of human operators in multi-human multi-robot teams. The proposed system is largely composed of three parts, taking the surveillance scenario involving multi-human operators and multi-robot system as an example. The first part of the system is a framework for an adaptive multi-human multi-robot system that allows real-time measurement and communication between heterogeneous sensors and multi-robot systems. The second part is an algorithm for real-time monitoring of humans' affective states using machine learning techniques and estimation of the affective state from multimodal data that consists of physiological and behavioral signals. The third part is a deep reinforcement learning-based workload allocation algorithm. For the first part of the affective workload allocation system, we developed a robot operating system (ROS)-based affective monitoring framework to enable communication among multiple wearable biosensors, behavioral monitoring devices, and multi-robot systems using the real-time operating system feature of ROS. We validated the sub-interfaces of the affective monitoring framework through connecting to a robot simulation and utilizing the framework to create a dataset. The dataset included various visual and physiological data categorized on the cognitive load level. The targeted cognitive load is stimulated by a closed-circuit television (CCTV) monitoring task on the surveillance scenario with multi-robot systems. Furthermore, we developed a deep learning-based affective prediction algorithm using the physiological and behavioral data captured from wearable biosensors and behavior-monitoring devices, in order to estimate the cognitive states for the second part of the system. For the third part of the affective workload allocation system, we developed a deep reinforcement learning-based workload allocation algorithm to allocate optimal workloads based on a human operator's performance. The algorithm was designed to take an operator's cognitive load, using objective and subjective measurements as inputs, and consider the operator's task performance model we developed using the empirical findings of the extensive user experiments, to allocate optimal workloads to human operators. We validated the proposed system through within-subjects study experiments on a generalized surveillance scenario involving multiple humans and multiple robots in a team. The multi-human multi-robot surveillance environment included an affective monitoring framework and an affective prediction algorithm to read sensor data and predict human cognitive load in real-time, respectively. We investigated optimal methods for affective workload allocations by comparing other allocation strategies used in the user experiments. As a result, we demonstrated the effectiveness and performance of the proposed system. Moreover, we found that the subjective and objective measurement of an operator's cognitive loads and the process of seeking consent for the workload transitions must be included in the workload allocation system to improve the team performance of the multi-human multi-robot teams.</p>

Malgré de nombreuses années de travail en robotique, il existe toujours un manque d’architecture logicielle et de middleware stables pour les systèmes multi-robot. Un intergiciel robotique devrait être conçu pour faire abstraction de l’architecture matérielle de bas niveau, faciliter la communication et l’intégration de nouveaux logiciels. Cette thèse se concentre sur le middleware pour systèmes multi-robot et sur la façon dont nous pouvons améliorer les frameworks existantes dans un contexte multi-robot en ajoutant des services de coordination multi-robot, des outils de développement et de déploiement massif. Nous nous attendons à ce que les robots soient de plus en plus utiles car ils peuvent tirer profit des données provenant d’autres périphériques externes dans leur prise de décision au lieu de simplement réagir à leur environnement local (capteurs, robots coopérant dans une flotte, etc.). Cette thèse évalue d’abord l’un des intergiciels les plus récents pour robot(s) mobile(s), Robot operating system (ROS), suivi par la suite d’un état de l’art sur les middlewares couramment utilisés en robotique. Basé sur les conclusions, nous proposons une contribution originale dans le contexte multi-robots, appelé SDfR (Service discovery for Robots), un mécanisme de découverte des services pour les robots. L’objectif principal est de proposer un mécanisme permettant aux robots de garder une trace des pairs accessibles à l’intérieur d’une flotte tout en utilisant une infrastructure ad-hoc. A cause de la mobilité des robots, les techniques classiques de configuration de réseau pair à pair ne conviennent pas. SDfR est un protocole hautement dynamique, adaptatif et évolutif adapté du protocole SSDP (Simple Service Discovery Protocol). Nous conduisons un ensemble d’expériences, en utilisant une flotte de robots Turtlebot, pour mesurer et montrer que le surdébit de SDfR est limité. La dernière partie de la thèse se concentre sur un modèle de programmation basé sur un automate temporisé. Ce type de programmation a l’avantage d’avoir un modèle qui peut être vérifié et simulé avant de déployer l’application sur de vrais robots. Afin d’enrichir et de faciliter le développement d’applications robotiques, un nouveau modèle de programmation basé sur des automates à états temporisés est proposé, appelé ROSMDB (Robot Operating system Model Driven Behaviour). Il fournit une vérification de modèle lors de la phase de développement et lors de l’exécution. Cette contribution est composée de plusieurs composants : une interface graphique pour créer des modèles basés sur un automate temporisé, un vérificateur de modèle intégré basé sur UPPAAL et un générateur de squelette de code. Enfin, nous avons effectué deux expériences : une avec une flotte de drones Parrot et l’autre avec des Turtlebots afin d’illustre le modèle proposé et sa capacité à vérifier les propriétés. / Despite many years of work in robotics, there is still a lack of established software architecture and middleware for multi-robot systems. A robotic middleware should be designed to abstract the low-level hardware architecture, facilitate communication and integration of new software. This PhD thesis is focusing on middleware for multi-robot system and how we can improve existing frameworks for fleet purposes by adding multi-robot coordination services, development and massive deployment tools. We expect robots to be increasingly useful as they can take advantage of data pushed from other external devices in their decision making instead of just reacting to their local environment (sensors, cooperating robots in a fleet, etc). This thesis first evaluates one of the most recent middleware for mobile robot(s), Robot operating system (ROS) and continues with a state of the art about the commonly used middlewares in robotics. Based on the conclusions, we propose an original contribution in the multi-robot context, called SDfR (Service discovery for Robots), a service discovery mechanism for Robots. The main goal is to propose a mechanism that allows highly mobile robots to keep track of the reachable peers inside a fleet while using an ad-hoc infrastructure. Another objective is to propose a network configuration negotiation protocol. Due to the mobility of robots, classical peer to peer network configuration techniques are not suitable. SDfR is a highly dynamic, adaptive and scalable protocol adapted from Simple Service Discovery Protocol (SSDP). We conduced a set of experiments, using a fleet of Turtlebot robots, to measure and show that the overhead of SDfR is limited. The last part of the thesis focuses on programming model based on timed automata. This type of programming has the benefits of having a model that can be verified and simulated before deploying the application on real robots. In order to enrich and facilitate the development of robotic applications, a new programming model based on timed automata state machines is proposed, called ROSMDB (Robot Operating system Model Driven Behaviour). It provides model checking at development phase and at runtime. This contribution is composed of several components: a graphical interface to create models based on timed automata, an integrated model checker based on UPPAAL and a code skeleton generator. Moreover, a ROS specific framework is proposed to verify the correctness of the execution of the models and to trigger alerts. Finally, we conduct two experiments: one with a fleet of Parrot drones and second with Turtlebots in order to illustrates the proposed model and its ability to check properties.

Cette thèse explore les capacités d’une intelligence ambiante équipée d’un réseau de capteurs de pression au sol. Elle traite le problème de la perception d’un environnement au travers un réseau de capteurs de basse résolution. Les difficultés incluent l’interpretation des poids dispersés pour des objets avec multiples supports, l’ambiguïté de poids entre des objets, la variation du poids des personnes pendant les activités dynamiques, etc. Nous introduisons des nouvelles techniques, partiellement inspirées du domaine de la vision par l’ordinateur, pour la détection, le suivi et la reconnaissance des entités qui se trouvent sur le sol. Nous introduisons également des nouveaux modes d’interaction entre les environnements équipés de tels capteurs aux sols, et les robots qui évoluent dans ces environnements. Ceci permet l’interprétation non-intrusive des événements qui ont lieu dans des environnements dotés d’une intelligence ambiante, avec des applications dans l’assistance automatisée à domicile, l’aide aux personnes âgées, le diagnostic continu de la santé, la sécurité, et la navigation robotique / This thesis explores the capabilities of an ambient intelligence equipped with a load-sensing floor. It deals with the problem of perceiving the environment through a network of low-resolution sensors. Challenges include the interpretation of spread loads for objects with multiple points of support, weight ambiguities between objects, variation of persons’ weight during dynamic activities, etc. We introduce new techniques, partly inspired from the field of computer vision, for detecting, tracking and recognizing the entities located on the floor. We also introduce new modes of interaction between environments equipped with such floor sensors and robots evolving inside them. This enables non-intrusive interpretation of events happening inside environments with embedded ambient intelligence, with applications in assisted living, senile care, continuous health diagnosis, home security, and robotic navigation

The purpose of information acquisition for data and information fusion is to provide relevant and timely information. The acquired information is integrated (or fused) to estimate the state of some environment. The success of information acquisition can be measured in the quality of the environment state estimates generated by the data and information fusion process. In this thesis, we introduce and set out to characterise the concept of large-scale information acquisition. Our interest in this subject is justified both by the identified lack of research on a holistic view on data and information fusion, and the proliferation of networked sensors which promises to enable handy access to a multitude of information sources. We identify a number of properties that could be considered in the context of large-scale information acquisition. The sensors used could be large in number, heterogeneous, complex, and distributed. Also, algorithms for large-scale information acquisition may have to deal with decentralised control and multiple and varying objectives. In the literature, a process that realises information acquisition is frequently denoted sensor management. We, however, introduce the term perception management instead, which encourages an agent perspective on information acquisition. Apart from explictly inviting the wealth of agent theory research into the data and information fusion research, it also highlights that the resource usage of perception management is constrained by the overall control of a system that uses data and information fusion. To address the challenges posed by the concept of large-scale information acquisition, we present a framework which highlights some of its pertinent aspects. We have implemented some important parts of the framework. What becomes evident in our study is the innate complexity of information acquisition for data and information fusion, which suggests approximative solutions. We, furthermore, study one of the possibly most important properties of large-scale information acquisition, decentralised control, in more detail. We propose a recurrent negotiation protocol for (decentralised) multi-agent coordination. Our approach to the negotiations is from an axiomatic bargaining theory perspective; an economics discipline. We identify shortcomings of the most commonly applied bargaining solution and demonstrate in simulations a problem instance where it is inferior to an alternative solution. However, we can not conclude that one of the solutions dominates the other in general. They are both preferable in different situations. We have also implemented the recurrent negotiation protocol on a group of mobile robots. We note some subtle difficulties with transferring bargaining solutions from economics to our computational problem. For instance, the characterising axioms of solutions in bargaining theory are useful to qualitatively compare different solutions, but care has to be taken when translating the solution to algorithms in computer science as some properties might be undesirable, unimportant or risk being lost in the translation. / QC 20100903

This thesis presents a novel approach to several problems in intelligent transportation systems using collaborative driving coordination. With inter-vehicle communication and intelligent vehicle cooperation, important tasks in transportation such as lane position determination, lane assignment and platoon formation can be solved. Several topics in regard to inter-vehicle communication, lane positioning, lane assignment and platoon formation are explored in this thesis: First, the design and experimental results of low-cost lane-level positioning system that can support a large number of transportation applications are discussed. Using a Markov-based approach based on sharing information among a group of vehicles that are traveling within the communication range of each other, the lane positions of vehicles can be determined. The robustness effectiveness of the system is shown in both simulations and real road tests. Second, a decentralized approach to lane scheduling for vehicles with an aim to increase traffic throughput while ensuring the vehicles exit successfully at their destinations is presented. Most of current traffic management systems do not consider lane organization of vehicles and only regulate traffic flows by controlling traffic signals or ramp meters. However, traffic throughput and efficient use of highways can be increased by coordinating driver behaviors intelligently. The lane optimization problem is formulated as a linear programming problem that can be solved using the Simplex method. Finally, a direction for cooperative vehicle platoon formation is proposed. To enhance traffic safety, increase lane capacities and reduce fuel consumption, vehicles can be organized into platoons with the objective of maximizing the travel distance that platoons stay intact. Toward this end, this work evaluates a proposed strategy which assigns vehicles to platoons by solving an optimization problem. A linear model for assigning vehicles to appropriate platoons when they enter the highway is formulated. Simulation results demonstrate that lane capacity can be increased effectively when platooning operation is used.

This thesis presents a novel approach to several problems in intelligent transportation systems using collaborative driving coordination. With inter-vehicle communication and intelligent vehicle cooperation, important tasks in transportation such as lane position determination, lane assignment and platoon formation can be solved. Several topics in regard to inter-vehicle communication, lane positioning, lane assignment and platoon formation are explored in this thesis: First, the design and experimental results of low-cost lane-level positioning system that can support a large number of transportation applications are discussed. Using a Markov-based approach based on sharing information among a group of vehicles that are traveling within the communication range of each other, the lane positions of vehicles can be determined. The robustness effectiveness of the system is shown in both simulations and real road tests. Second, a decentralized approach to lane scheduling for vehicles with an aim to increase traffic throughput while ensuring the vehicles exit successfully at their destinations is presented. Most of current traffic management systems do not consider lane organization of vehicles and only regulate traffic flows by controlling traffic signals or ramp meters. However, traffic throughput and efficient use of highways can be increased by coordinating driver behaviors intelligently. The lane optimization problem is formulated as a linear programming problem that can be solved using the Simplex method. Finally, a direction for cooperative vehicle platoon formation is proposed. To enhance traffic safety, increase lane capacities and reduce fuel consumption, vehicles can be organized into platoons with the objective of maximizing the travel distance that platoons stay intact. Toward this end, this work evaluates a proposed strategy which assigns vehicles to platoons by solving an optimization problem. A linear model for assigning vehicles to appropriate platoons when they enter the highway is formulated. Simulation results demonstrate that lane capacity can be increased effectively when platooning operation is used.

L'experiència de l'autor en la temàtica d'agents intel·ligents i la seva aplicació als robots que emulen el joc de futbol han donat el bagatge suficient per poder encetar i proposar la temàtica plantejada en aquesta tesi: com fer que un complicat robot pugui treure el màxim suc de l'autoconeixement de l'estructura de control inclosa al seu propi cos físic, i així poder cooperar millor amb d'altres agents per optimitzar el rendiment a l'hora de resoldre problemes de cooperació. Per resoldre aquesta qüestió es proposa incorporar la dinàmica del cos físic en les decisions cooperatives dels agents físics unificant els móns de l'automàtica, la robòtica i la intel·ligència artificial a través de la noció de capacitat: la capacitat vista com a entitat on els enginyers de control dipositen el seu coneixement, i a la vegada la capacitat vista com la utilitat on un agent hi diposita el seu autoconeixement del seu cos físic que ha obtingut per introspecció. En aquesta tesi es presenta l'arquitectura DPAA que s'organitza seguint una jerarquia vertical en tres nivells d'abstracció o mòduls &#61630;control, supervisor i agent, els quals presenten una estructura interna homogènia que facilita les tasques de disseny de l'agent. Aquests mòduls disposen d'un conjunt específic de capacitats que els permeten avaluar com seran les accions que s'executaran en un futur. En concret, al mòdul de control (baix nivell d'abstracció) les capacitats consisteixen en paràmetres que descriuen el comportament dinàmic i estàtic que resulta d'executar un controlador determinat, és a dir, encapsulen el coneixement de l'enginyer de control. Així, a través dels mecanismes de comunicació entre mòduls aquest coneixement pot anar introduint-se als mecanismes de decisió dels mòduls superiors (supervisor i agent) de forma que quan els paràmetres dinàmics i estàtics indiquin que pot haver-hi problemes a baix nivell, els mòduls superiors es poden responsabilitzar d'inhibir o no l'execució d'algunes accions. Aquest procés top-down intern d'avaluació de la viabilitat d'executar una acció determinada s'anomena procés d'introspecció. Es presenten diversos exemples per tal d'il·lustrar com es pot dissenyar un agent físic amb dinàmica pròpia utilitzant l'arquitectura DPAA com a referent. En concret, es mostra tot el procés a seguir per dissenyar un sistema real format per dos robots en formació de comboi, i es mostra com es pot resoldre el problema de la col·lisió utilitzant les capacitats a partir de les especificacions de disseny de l'arquitectura DPAA. Al cinquè capítol s'hi exposa el procés d'anàlisi i disseny en un domini més complex: un grup de robots que emulen el joc del futbol. Els resultats que s'hi mostren fan referència a l'avaluació de la validesa de l'arquitectura per resoldre el problema de la passada de la pilota. S'hi mostren diversos resultats on es veu que és possible avaluar si una passada de pilota és viable o no. Encara que aquesta possibilitat ja ha estat demostrada en altres treballs, l'aportació d'aquesta tesi està en el fet que és possible avaluar la viabilitat a partir de l'encapsulament de la dinàmica en unes capacitats específiques, és a dir, és possible saber quines seran les característiques de la passada: el temps del xut, la precisió o inclòs la geometria del moviment del robot xutador. Els resultats mostren que la negociació de les condicions de la passada de la pilota és possible a partir de capacitats atòmiques, les quals inclouen informació sobre les característiques de la dinàmica dels controladors. La complexitat del domini proposat fa difícil comparar els resultats amb els altres treballs. Cal tenir present que els resultats mostrats s'han obtingut utilitzant un simulador fet a mida que incorpora les dinàmiques dels motors dels robots i de la pilota. En aquest sentit cal comentar que no existeixen treballs publicats sobre el problema de la passada en què es tingui en compte la dinàmica dels robots.El present treball permet assegurar que la inclusió de paràmetres dinàmics en el conjunt de les capacitats de l'agent físic permet obtenir un millor comportament col·lectiu dels robots, i que aquesta millora es deu al fet que en les etapes de decisió els agents utilitzen informació relativa a la viabilitat sobre les seves accions: aquesta viabilitat es pot calcular a partir del comportament dinàmic dels controladors. De fet, la definició de capacitats a partir de paràmetres dinàmics permet treballar fàcilment amb sistemes autònoms heterogenis: l'agent físic pot ser conscient de les seves capacitats d'actuació a través de mecanismes interns d'introspecció, i això permet que pugui prendre compromisos amb altres agents físics.

L’interaction homme-robot est un domaine qui en est encore à ses balbutiements.Les développements se sont avant tout concentrés sur l’autonomie et l’intelligence artificielle et doter les robots de capacités avancées pour exécuter des tâches complexes. Dans un proche avenir, les robots développeront probablement la capacité de s’adapter et d’apprendre de leur environnement. Les robots ont confiance, ne s’ennuient pas et peuvent fonctionner dans des environnements hostiles et dynamiques - tous des attributs souhaités à l’exploration spatiale et aux situations d’urgence ou militaires. Ils réduisent également les coûts de mission, augmentent la flexibilité de conception et maximisent la production de données. Cependant, lorsqu’ils sont confrontés à de nouveaux scénarios et à des événements inattendus, les robots sont moins performants par rapport aux êtres humains intuitifs et créatifs (mais aussi faillibles et biaisés). L’avenir exigera que les concepteurs de mission équilibrent intelligemment la souplesse et l’ingéniosité des humains avec des systèmes robotiques robustes et sophistiqués. Ce travail de recherche propose un cadre formel, basé sur la théorie de jeux, pour une équipe de drones qui doit coordonner leurs actions entre eux et fournir à l’opérateur humain des données suffisantes pour prendre des décisions « difficiles » qui maximisent l’efficacité de la mission, selon certaines directives opérationnelles. Notre première contribution a consisté à présenter un cadre décentralisé et une fonction d’utilité pour une mission de patrouille avec une équipe de drones. Ensuite, nous avons considéré l’effet de cadrage, ou « framing effect » en anglais, dans le contexte de notre étude,afin de mieux comprendre et modéliser à terme certains processus décisionnels sous incertitude.Ainsi, nous avons réalisé deux expérimentations avec 20 et 12 participants respectivement. Nos résultats ont révélé que la façon dont le problème a été présenté (effet de cadrage positif ou négatif), l’engagement émotionnel et les couleurs du texte ont affecté statistiquement les choix des opérateurs humains. Les données expérimentales nous ont permis de développer un modèle d’utilité pour l’opérateur humain que nous cherchons à intégrer dans la boucle décisionnelle du système homme-robots. Enfin, nous formalisons et évaluons l’ensemble du cadre proposé où nous "fermons la boucle" à travers une expérimentation en ligne avec 101 participants. Nos résultats suggèrent que notre approche permet d’optimiser le système homme-robots dans un contexte où des décisions doivent être prises dans un environnement incertain. / Human-robot interaction is a field that is still in its infancy. Developments havefocused on autonomy and artificial intelligence, and provide robots with advanced capabilitiesto perform complex tasks. In the near future, robots will likely develop the ability to adapt andlearn from their surroundings. Robots have reliance, do not get bored and can operate in hostileand dynamics environments - all attributes well suited for space exploration, and emergency ormilitary situations. They also reduce mission costs, increase design flexibility, and maximizedata production. However, when coped with new scenarios and unexpected events, robots palein comparison with intuitive and creative human beings. The future will require that missiondesigners balance intelligently the flexibility and ingenuity of humans with robust and sophisticatedrobotic systems. This research work proposes a game-theoretic framework for a drone teamthat must coordinate their actions among them and provide the human operator sufficient datato make “hard” decisions that maximize the mission efficiency, according with some operationalguidelines. Our first contribution was to present a decentralized framework and utility functionfor a drone-team patrolling mission. Then, we considered the framing effect in the context of ourstudy, in order to better understand and model certain human decision-making processes underuncertainty. Hence, two experiments were conducted with 20 and 12 participants respectively.Our findings revealed that the way the problem was presented (positive or negative framing), theemotional commitment and the text colors statistically affected the choices made by the humanoperators. The experimental data allowed us to develop a utility model for the human operatorthat we sought to integrate into the decision-making loop of the human-robot system. Finally,we formalized and evaluated the close-loop of the whole proposed framework with a last onlineexperiment with 101 participants. Our results suggest that our approach allow us to optimize thehuman-robot system in a context where decisions must be made in an uncertain environment.

Cette thèse développe les lois de coordination de systèmes de Lagrange. Elle propose en premier lieu une stratégie complètement décentralisée qui se base sur la technique de cross-coupling pour la commande d'un groupe de robots, appelé réseau, qui synchronisent leurs mouvements en suivant une trajectoire désirée. Cette stratégie est étendue pour faire face à l'incertitude paramétrique des robots ainsi qu’aux retards fréquemment rencontrés dans les applications pratiques de réseaux de communication. Une deuxième architecture basée sur la théorie des graphes est proposée pour les réseaux à leader. L'approche développée est considérée hybride. Une extension adaptative à base de réseaux de neurones est développée pour traiter les cas d'incertitude paramétrique. La stratégie conçue prend en considération les délais dans la réception des données. En se basant sur la notion de système en chaîne, la théorie des graphes, le concept de la passivité et la technique du backstepping, une nouvelle méthodologie de la conception de contrôleur de synchronisation pour une classe de systèmes sous-actionnés est développée. Afin d’avoir la possibilité d’implémenter ces stratégies de contrôle, on a développé une plate-forme d'expérimentation pour la robotique industrielle coopérative. / This thesis investigates the issue of designing decentralized control laws to cooperatively control a team of robot manipulators. The purpose is to synchronize their movements while tracking common desired trajectory. Based on a combination of Lyapunov direct method and cross-coupling technique, To account for unmatched uncertainties, the proposed decentralized control laws are extended to an adaptive synchronization tracking controllers. Moreover, due to communication imperfection, time delay communication problems are considered in the performance analysis of the controllers. Another relevant problem for distributed synchronized systems is the leader-follower control problem. In this strategy, a decentralized control laws based on the backstepping scheme is proposed to deal with a leader-follower multiple robots structure. Based on graph theory, the coordination strategy combines the leader follower control with the decentralized control. The thesis, also considers the cooperative movement of under- actuated manipulators tracking reference trajectories defined by the user. The control problem for a network of class of under-actuated systems is considered. The approach we adopted in this thesis consists in decomposing the under-actuated manipulators into a cascade of passive subsystems that synchronize with he other neighbors subsystems. The resulting synchronized control law is basically a combination of non-regular backstepping procedure aided with some concepts from graph theory. The proposed controllers are validated numerically, assuming that the underlying communication graph is strongly connected. To implement these control strategies, we developed an experimental platform made of three robot manipulators.

Made available in DSpace on 2014-12-17T14:56:04Z (GMT). No. of bitstreams: 1 DennisBA.pdf: 1210954 bytes, checksum: f42a19fb396d47e801ab673ab1f88887 (MD5) Previous issue date: 2005-10-14 / Conselho Nacional de Desenvolvimento Cient?fico e Tecnol?gico / In multi-robot systems, both control architecture and work strategy represent a challenge for researchers. It is important to have a robust architecture that can be easily adapted to requirement changes. It is also important that work strategy allows robots to complete tasks efficiently, considering that robots interact directly in environments with humans. In this context, this work explores two approaches for robot soccer team coordination for cooperative tasks development. Both approaches are based on a combination of imitation learning and reinforcement learning. Thus, in the first approach was developed a control architecture, a fuzzy inference engine for recognizing situations in robot soccer games, a software for narration of robot soccer games based on the inference engine and the implementation of learning by imitation from observation and analysis of others robotic teams. Moreover, state abstraction was efficiently implemented in reinforcement learning applied to the robot soccer standard problem. Finally, reinforcement learning was implemented in a form where actions are explored only in some states (for example, states where an specialist robot system used them) differently to the traditional form, where actions have to be tested in all states. In the second approach reinforcement learning was implemented with function approximation, for which an algorithm called RBF-Sarsa($lambda$) was created. In both approaches batch reinforcement learning algorithms were implemented and imitation learning was used as a seed for reinforcement learning. Moreover, learning from robotic teams controlled by humans was explored. The proposal in this work had revealed efficient in the robot soccer standard problem and, when implemented in other robotics systems, they will allow that these robotics systems can efficiently and effectively develop assigned tasks. These approaches will give high adaptation capabilities to requirements and environment changes. / Em sistemas multi-rob?s a arquitetura de controle e a estrat?gia de trabalho representam um desafio para os pesquisadores. ? importante que a arquitetura de controle seja robusta, de forma que se adapte naturalmente ?s mudan?as nas caracter?sticas do problema e tamb?m que a estrat?gia de trabalho permita aos rob?s desenvolver as tarefas atribu?das eficaz e eficientemente, levando em considera??o a restri??o de que os rob?s v?o interagir diretamente em ambientes povoados de seres humanos. Neste contexto, este trabalho explora duas abordagens para a coordena??o de uma frota de rob?s desenvolvendo tarefas cooperativas. Ambas as abordagens s?o baseadas em uma mistura de aprendizado por imita??o e por experi?ncia. Assim, na primeira abordagem desenvolveu-se uma arquitetura de controle, uma m?quina de infer?ncia difusa para reconhecimento de fatos em jogos de futebol, um software narrador de jogos baseado na m?quina de infer?ncia difusa, e a implementa??o de aprendizado por imita??o a partir de observa??o e an?lise de outros times rob?ticos. Al?m disso, aplicou-se eficientemente abstra??o de estados em aprendizado por refor?o no problema padr?o de futebol de rob?s. Finalmente, o aprendizado por refor?o foi implementado de forma que as a??es somente s?o executadas em certos estados (por exemplo os estados onde algum sistema rob?tico especialista j? as utilizou) diferentemente da forma tradicional onde as a??es no banco de conhecimento t?m que ser testadas em todos os estados. No caso da segunda abordagem, implementou-se aprendizado por refor?o com aproxima??o de fun??es, para o que foi criado um algoritmo chamado RBF-Sarsa($lambda$). Em ambas as abordagens implementou-se o aprendizado por refor?o em lotes e o aprendizado por imita??o como semente para aprendizado por refor?o. Al?m disso, explorou-se o aprendizado com times de rob?s controlados por seres humanos. As propostas deste trabalho mostraram-se eficientes no problema padr?o de futebol de rob?s, e ao serem implementadas em outros sistemas rob?ticos permitir?o que os mesmos sejam eficazes e eficientes no desenvolvimento das tarefas atribu?das com um alto grau de adapta??o ?s mudan?as dos requerimentos e do ambiente.