Un intérêt croissant est aujourd'hui porté sur les robots capables de conduire des activités de collaboration d'une manière naturelle et efficace. Nous avons développé une architecture et un système qui traitent des aspects décisionnels de ce problème. Nous avons mis en oeuvre cette architecture pour traiter trois problèmes différents: le robot observateur, le robot équipier et enfin le robot instructeur. Dans cette thèse, nous discutons des défis et problématiques de la coopération homme-robot, puis nous décrivons l'architecture que nous avons développée et enfin détaillons sa mise oeuvre et les algorithmiques spécifiques à chacun des scénarios.Dans le cadre du scénario du robot observateur, le robot maintient un état du monde à jour au moyen d'un raisonnement géométrique effectué sur les données de perception, produisant ainsi une description symbolique de l'état du monde et des agents présents. Nous montrons également, sur la base d'un système de raisonnement intégrant des processus de décision de Markov (MDPs) et des réseaux Bayésiens, comment le robot est capable d'inférer les intentions et les actions futures de ses partenaires humain, à partir d'une observation de leurs mouvements relatifs aux objets de l'environnement. Nous identifions deux types de comportements proactifs : corriger les croyances de l'homme en lui fournissant l'information pertinente qui lui permettra de réaliser son but, aider physiquement la personne dans la réalisation de sa tâche, une fois celle-ci identifiée par le robot.Dans le cas du robot équipier, ce dernier doir réaliser une tâche en coopération avec un partenaire human. Nous introduisons un planificateur nommé Human-Aware Task Planner et détaillons la gestion par notre systeme du plan partagé par un composant appelé Plan Management component. Grâce à se système, le robot peut collaborer avec les hommes selon trois modalités différentes : robot leader, human leader, ou equal partners. Nous discutons des fonctions qui permettent au robot de suivre les actions de son partenaire humain et de vérifier qu'elles sont compatibles ou non avec le plan partagé et nous montrons comment le robot est capable de produire des comportements sûrs qui permettent de réaliser la tâche en prenant en compte de manière explicite la présence et les actions de l'homme ainsi que ses préférences. L'approche est fondée sur des processus décisionnels de Markov hiérarchisés avec observabilité mixte et permet d'estimer l'engagement de l'homme et de réagir en conséquence à différents niveaux d'abstraction. Enfin, nous discutions d'une approche prospective fondée sur un planificateur multi-agent probabiliste mettant en œuvre des MDPs et de sa pertinence quant à l'amélioration du composant de gestion de plan partagé.Dans le scénario du robot instructeur, nous détaillons les processus décisionnels qui permettent au robot d'adapter le plan partagé (shared plan) en fonction de l'état de connaissance et des désirs de son partenaire humain. Selon, le cas, le robot donne plus ou moins de détails sur le plan et adapte son comportement aux connaissances de l'homme ; Une étude utilisateur a également été menée permettant de valider la pertinence de cette approche.Finalement, nous présentons la mise en œuvre d'un robot guide autonome et détaillons les processu décisionnels que nous y avons intégrés pour lui permettre de guider des voyageurs dans un hall d'aéroport en s'adaptant au mieux au contexte et aux désirs des personnes guidées. Nous illustrons dans ce contexte des comportement adaptatifs et pro-actifs. Ce système a été effectivement intégré sur le robot Spencer qui a été déployé dans le terminal principal de l'aéroport d'Amsterdam (Schiphol). Le robot a fonctionné de manière robuste et satisfaisante. Une étude utilisateur a permis, dans ce cas également, de mesurer les performances et de valider le système. / There has been an increasing interest, in the last years, in robots that are able to cooperate with humans not only as simple tools, but as full agents, able to execute collaborative activities in a natural and efficient way. In this work, we have developed an architecture for Human-Robot Interaction able to execute joint activities with humans. We have applied this architecture to three different problems, that we called the robot observer, the robot coworker, and the robot teacher. After quickly giving an overview on the main aspects of human-robot cooperation and on the architecture of our system, we detail these problems.In the observer problem the robot monitors the environment, analyzing perceptual data through geometrical reasoning to produce symbolic information.We show how the system is able to infer humans' actions and intentions by linking physical observations, obtained by reasoning on humans' motions and their relationships with the environment, with planning and humans' mental beliefs, through a framework based on Markov Decision Processes and Bayesian Networks. We show, in a user study, that this model approaches the capacity of humans to infer intentions. We also discuss on the possible reactions that the robot can execute after inferring a human's intention. We identify two possible proactive behaviors: correcting the human's belief, by giving information to help him to correctly accomplish his goal, and physically helping him to accomplish the goal.In the coworker problem the robot has to execute a cooperative task with a human. In this part we introduce the Human-Aware Task Planner, used in different experiments, and detail our plan management component. The robot is able to cooperate with humans in three different modalities: robot leader, human leader, and equal partners. We introduce the problem of task monitoring, where the robot observes human activities to understand if they are still following the shared plan. After that, we describe how our robot is able to execute actions in a safe and robust way, taking humans into account. We present a framework used to achieve joint actions, by continuously estimating the robot's partner activities and reacting accordingly. This framework uses hierarchical Mixed Observability Markov Decision Processes, which allow us to estimate variables, such as the human's commitment to the task, and to react accordingly, splitting the decision process in different levels. We present an example of Collaborative Planner, for the handover problem, and then a set of laboratory experiments for a robot coworker scenario. Additionally, we introduce a novel multi-agent probabilistic planner, based on Markov Decision Processes, and discuss how we could use it to enhance our plan management component.In the robot teacher problem we explain how we can adapt the plan explanation and monitoring of the system to the knowledge of users on the task to perform. Using this idea, the robot will explain in less details tasks that the user has already performed several times, going more in-depth on new tasks. We show, in a user study, that this adaptive behavior is perceived by users better than a system without this capacity.Finally, we present a case study for a human-aware robot guide. This robot is able to guide users with adaptive and proactive behaviors, changing the speed to adapt to their needs, proposing a new pace to better suit the task's objectives, and directly engaging users to propose help. This system was integrated with other components to deploy a robot in the Schiphol Airport of Amsterdam, to guide groups of passengers to their flight gates. We performed user studies both in a laboratory and in the airport, demonstrating the robot's capacities and showing that it is appreciated by users.

abstract: While developing autonomous intelligent robots has been the goal of many research programs, a more practical application involving intelligent robots is the formation of teams consisting of both humans and robots. An example of such an application is search and rescue operations where robots commanded by humans are sent to environments too dangerous for humans. For such human-robot interaction, natural language is considered a good communication medium as it allows humans with less training about the robot's internal language to be able to command and interact with the robot. However, any natural language communication from the human needs to be translated to a formal language that the robot can understand. Similarly, before the robot can communicate (in natural language) with the human, it needs to formulate its communique in some formal language which then gets translated into natural language. In this paper, I develop a high level language for communication between humans and robots and demonstrate various aspects through a robotics simulation. These language constructs borrow some ideas from action execution languages and are grounded with respect to simulated human-robot interaction transcripts. / Dissertation/Thesis / M.S. Computer Science 2012

abstract: Linear Temporal Logic is gaining increasing popularity as a high level specification language for robot motion planning due to its expressive power and scalability of LTL control synthesis algorithms. This formalism, however, requires expert knowledge and makes it inaccessible to non-expert users. This thesis introduces a graphical specification environment to create high level motion plans to control robots in the field by converting a visual representation of the motion/task plan into a Linear Temporal Logic (LTL) specification. The visual interface is built on the Android tablet platform and provides functionality to create task plans through a set of well defined gestures and on screen controls. It uses the notion of waypoints to quickly and efficiently describe the motion plan and enables a variety of complex Linear Temporal Logic specifications to be described succinctly and intuitively by the user without the need for the knowledge and understanding of LTL specification. Thus, it opens avenues for its use by personnel in military, warehouse management, and search and rescue missions. This thesis describes the construction of LTL for various scenarios used for robot navigation using the visual interface developed and leverages the use of existing LTL based motion planners to carry out the task plan by a robot. / Dissertation/Thesis / M.S. Computer Science 2013

abstract: As robots are increasingly migrating out of factories and research laboratories and into our everyday lives, they should move and act in environments designed for humans. For this reason, the need of anthropomorphic movements is of utmost importance. The objective of this thesis is to solve the inverse kinematics problem of redundant robot arms that results to anthropomorphic configurations. The swivel angle of the elbow was used as a human arm motion parameter for the robot arm to mimic. The swivel angle is defined as the rotation angle of the plane defined by the upper and lower arm around a virtual axis that connects the shoulder and wrist joints. Using kinematic data recorded from human subjects during every-day life tasks, the linear sensorimotor transformation model was validated and used to estimate the swivel angle, given the desired end-effector position. Defining the desired swivel angle simplifies the kinematic redundancy of the robot arm. The proposed method was tested with an anthropomorphic redundant robot arm and the computed motion profiles were compared to the ones of the human subjects. This thesis shows that the method computes anthropomorphic configurations for the robot arm, even if the robot arm has different link lengths than the human arm and starts its motion at random configurations. / Dissertation/Thesis / M.S.Tech Mechanical Engineering 2013

This thesis is a critique on the ease in which humans tend to anthropomorphize chatbots, assigning human characteristics to entities that fundamentally will never understand the human experience. It will be further exploring these consequences on our society's socio-cultural fabric, representations of the self and identity formation in terms of communication and the essence of humanity.

Context: Patients with diseases such as locked in syndrome or motor neuron are paralyzed and they need special care. To reduce the cost of their care, systems need to be designed where human involvement is minimal and affected people can perform their daily life activities independently. To assess the feasibility and robustness of combinations of input modalities, mobile robot (Spinosaurus) navigation is controlled by a combination of Eye gaze tracking and other input modalities. Objectives: Our aim is to control the robot using EEG brain signals and eye gaze tracking simultaneously. Different combinations of input modalities are used to control the robot and turret movement and then we find out which combination of control technique mapped to control command is most effective. Methods: The method includes developing the interface and control software. An experiment involving 15 participants was conducted to evaluate control of the mobile robot using a combination of eye tracker and other input modalities. Subjects were required to drive the mobile robot from a starting point to a goal along a pre-defined path. At the end of experiment, a sense of presence questionnaire was distributed among the participants to take their feedback. A qualitative pilot study was performed to find out how a low cost commercial EEG headset, the Emotiv EPOCTM, can be used for motion control of a mobile robot at the end. Results: Our study results showed that the Mouse/Keyboard combination was the most effective for controlling the robot motion and turret mounted camera respectively. In experimental evaluation, the Keyboard/Eye Tracker combination improved the performance by 9%. 86% of participants found that turret mounted camera was useful and provided great assistance in robot navigation. Our qualitative pilot study of the Emotiv EPOCTM demonstrated different ways to train the headset for different actions. Conclusions: In this study, we concluded that different combinations of control techniques could be used to control the devices e.g. a mobile robot or a powered wheelchair. Gaze-based control was found to be comparable with the use of a mouse and keyboard; EEG-based control was found to need a lot of training time and was difficult to train. Our pilot study suggested that using facial expressions to train the Emotiv EPOCTM was an efficient and effective way to train it.

Face-to-face human communication is a multimodal and incremental process. Humans employ  different information channels (modalities) for their communication. Since some of these modalities are more error-prone to specic type of data, a multimodal communication can benefit from strengths of each modality and therefore reduce ambiguities during the interaction. Such interfaces can be applied to intelligent robots who operate in close relation with humans. With this approach, robots can communicate with their human colleagues in the same way they communicate with each other, thus leading to an easier and more robust human-robot interaction (HRI).In this work we suggest a new method for implementing multimodal interfaces in HRI domain and present the method employed on an industrial robot. We show that operating the system is made easier by using this interface. / Robot Colleague

As people respond strongly to faces and facial features, both consciously and subconsciously, faces are an essential aspect of social robots. Robotic faces and heads until recently belonged to one of the following categories: virtual, mechatronic or animatronic. As an original contribution to the field of human-robot interaction, I present the R-PAF technology (Retro-Projected Animated Faces): a novel robotic head displaying a real-time, computer-rendered face, retro-projected from within the head volume onto a mask, as well as its driving software designed with openness and portability to other hybrid robotic platforms in mind. The work constitutes the first implementation of a non-planar mask suitable for social human-robot interaction, comprising key elements of social interaction such as precise gaze direction control, facial expressions and blushing, and the first demonstration of an interactive video-animated facial mask mounted on a 5-axis robotic arm. The LightHead robot, a R-PAF demonstrator and experimental platform, has demonstrated robustness both in extended controlled and uncontrolled settings. The iterative hardware and facial design, details of the three-layered software architecture and tools, the implementation of life-like facial behaviours, as well as improvements in social-emotional robotic communication are reported. Furthermore, a series of evaluations present the first study on human performance in reading robotic gaze and another first on user’s ethnic preference towards a robot face.

Nowadays, robot is commonly used to perform automation tasks. With the trend of low volume and customised products, flexible manufacturing is introduced to increase working efficiency and flexibility. Therefore, human robot collaboration plays an important role in automation production and safety should be considered in the design of this kind of robot cell. This work presents the design of safe human robot collaboration by equipping an industrial robot cell with SICK laser scanners, safety monitoring system and trap routine speed control. It also investigates the reliability of RGB-D camera for robot safety. This work aims to find a safety robot system using standard industrial robot for human robot collaboration. The challenge is to ensure the operator's safety at all times. It investigates safety standards and directives, safety requirements of collaboration, and related works for the design of collaborative robot cell, and makes risk assessment before carrying out the valuation. Based on literature review, it gives the concept of layout design and logic for slow down and resume of robot motion. The speed will be first reduced to manual speed and then zero speed depending on the distance between the human and the robot. Valuation and verification are made in the proposed safe solution for human robot collaboration to test the reliability and feasibility. This project realizes the automatic resume that the robot can con-tinue working without manually pressing reset button after the operator leaves the robot cell if there is no access to the prohibited area. In addition, it also adopts the manual reset at the same time to ensure the safety when people access the prohibited area. Several special cases that may happen in the human robot collaboration are described and analysed. Furthermore, the future work is presented to make improvements for the proposed safety robot cell design.

Robots are required in many jobs. The jobs related to tele-operation may be very challenging and often require reaching a destination quickly and with minimum collisions. In order to succeed in these jobs, human operators are asked to tele-operate a robot manually through a user interface. The design of a user interface and of the information provided in it, become therefore critical elements for the successful completion of robot tele-operation tasks. Effective and timely robot tele-navigation mainly relies on the intuitiveness provided by the interface and on the richness and presentation of the feedback given. This project investigated the use of both haptic and visual feedbacks in a user interface for robot tele-navigation. The aim was to overcome some of the limitations observed in a state of the art works, turning what is sometimes described as contrasting into an added value to improve tele-navigation performance. The key issue is to combine different human sensory modalities in a coherent way and to benefit from 3-D vision too. The proposed new approach was inspired by how visually impaired people use walking sticks to navigate. Haptic feedback may provide helpful input to a user to comprehend distances to surrounding obstacles and information about the obstacle distribution. This was proposed to be achieved entirely relying on on-board range sensors, and by processing this input through a simple scheme that regulates magnitude and direction of the environmental force-feedback provided to the haptic device. A specific algorithm was also used to render the distribution of very close objects to provide appropriate touch sensations. Scene visualization was provided by the system and it was shown to a user coherently to haptic sensation. Different visualization configurations, from multi-viewpoint observation to 3-D visualization, were proposed and rigorously assessed through experimentations, to understand the advantages of the proposed approach and performance variations among different 3-D display technologies. Over twenty users were invited to participate in a usability study composed by two major experiments. The first experiment focused on a comparison between the proposed haptic-feedback strategy and a typical state of the art approach. It included testing with a multi-viewpoint visual observation. The second experiment investigated the performance of the proposed haptic-feedback strategy when combined with three different stereoscopic-3D visualization technologies. The results from the experiments were encouraging and showed good performance with the proposed approach and an improvement over literature approaches to haptic feedback in robot tele-operation. It was also demonstrated that 3-D visualization can be beneficial for robot tele-navigation and it will not contrast with haptic feedback if it is properly aligned to it. Performance may vary with different 3-D visualization technologies, which is also discussed in the presented work.