Autism spectrum disorder (ASD) affects about 1.5 million individuals in the US alone. The consequences of ASD affect families, caregivers, and social structures. This thesis adds to a growing group of people performing research on mitigating the effects of autism through robotics. Children with ASD tend to interact with robots more easily than with other humans. The goal of robotic therapy is not to help children interact with robots, but to generalize the behavior to humans. An articulated spine is a key to human emotional expression through shaping, weight shifting, and flow. Despite this importance, this feature is all but lacking in robots. The primary contribution of this work is a novel 3-link planar spine with compliant, partial-gravity-compensating springs, capable of reproducing simple emotion-conveying poses for use in robot-based therapy for children with ASD. The design was based on the movements of expression experts using motion tracking markers. This information was used to optimize the number of links in the spine and their corresponding lengths. It is the goal of this research to make robotic therapy more effective for the children, raising the potential for life-changing results.

Submitted by Silvana Teresinha Dornelles Studzinski (sstudzinski) on 2016-05-18T16:03:18Z No. of bitstreams: 1 Edward Simon John_.pdf: 2766704 bytes, checksum: 51ba143145d5779779cf7302cfbcf429 (MD5) / Made available in DSpace on 2016-05-18T16:03:18Z (GMT). No. of bitstreams: 1 Edward Simon John_.pdf: 2766704 bytes, checksum: 51ba143145d5779779cf7302cfbcf429 (MD5) Previous issue date: 2016-02-24 / Nenhuma / Pessoas que enfrentam dificuldades de comunicação em suas atividades diárias, por apresentarem necessidades especiais para ver ou ouvir, são uma significativa parcela da população brasileira. Técnicas de robótica assistiva vêm sendo desenvolvidas para apoiar este público em determinadas atividades, com bons resultados sendo observados. Entretanto os dispositivos de robótica assistiva disponíveis para comunicação são, em geral, direcionados ao atendimento de um público específico e não consideram o atendimento das necessidades de um público misto, composto por pessoas com diferentes necessidades. Embora existam modelos versáteis quanto a canais de entrada e saída, não se observa a implementação dos recursos para atendimento de um amplo conjunto de necessidades. Dado esse contexto, este trabalho propõe um modelo de sistema de Interação Multimodal Humano Computador, embarcado em um robô assistivo, capaz de adaptar o conjunto de meios de interação necessários para a comunicação de acordo com o tipo e o grau de necessidades do usuário, fornecendo informações relevantes por meio dos canais adequados de acordo com cada deficiência. O modelo também inclui um conjunto de recursos destinados a obter informações em fontes diversas e disponibilizar estes resultados aos usuários. A abordagem proposta enfatiza o gerenciamento de usuários e a adaptação do uso dos canais de interação às suas características. Foi desenvolvido um protótipo com um conjunto de serviços ambientados no contexto de um campus universitário, com capacidade de atender à dúvidas e necessidades sobre este ambiente. Os testes realizados com este protótipo envolveram um grupo de 14 (quatorze) usuários com deficiência e suscitaram atitudes positivas quanto a aspectos de usabilidade como facilidade de uso, utilidade, conforto e eficácia. / People facing communication difficulties in their daily activities, because they have special needs to see or hear, are a significant portion of the Brazilian population. Robotic assistive techniques have been developed to support this public in certain activities, with good results being observed. However, assistive robotic devices available for communication are generally oriented to give heed to a specific audience and do not meet the needs of a mixed audience, composed of people with different needs. While there are versatile models in terms of input and output channels, the implementation of the resources in order to attend a wide range of needs is not seen. Given this context, this work proposes a model of Multimodal Human-Computer Interaction System, embedded in an assistive robot, able to adapt the set of interaction means for communication according to the type and degree of user needs, providing relevant information through appropriate channels according to each disability. The model also includes a set of features to obtain information from various sources and provide these results to users. The proposed approach emphasizes user management and adaptation of the use of interaction channels to their characteristics. A prototype with a set of services in the context of a university campus and capable of meeting the questions and needs of this environment was developed. The experiments with this prototype involved a group of 14 (fourteen) handicapped users and elicited positive attitudes towards usability aspects as ease of use, utility, comfort and efficiency.

Supondo-se que os robôs coexistirão conosco num futuro próximo, é então evidente a necessidade de Arquiteturas de Controle Inteligentes voltadas para a Interação Humano-Robô. Portanto, este trabalho desenvolveu uma Organização de Arquitetura de Controle Inteligente comportamental, cujo objetivo principal é permitir que o robô interaja com as pessoas de maneira intuitiva e que motive a colaboração entre pessoas e robôs. Para isso, um módulo emocional sintético, embasado na teoria bidimensional de emoções, foi integrado para promover a adaptação dos comportamentos do robô, implementados por Esquemas Motores, e a comunicação de seu estado interno de modo inteligível. Esta Organização subsidiou a implantação da Arquitetura de Controle em uma aplicação voltada para a área assistencial da saúde, consistindo, destarte, em um estudo de caso em robótica social assistiva como ferramenta auxiliar para educação especial. Os experimentos realizados demonstraram que a arquitetura de controle desenvolvida é capaz de atender aos requisitos da aplicação, conforme estipulado pelos especialistas consultados. Isto posto, esta tese contribui com o projeto de uma arquitetura de controle capaz de agir mediante a avaliação subjetiva baseada em crenças cognitivas das emoções, o desenvolvimento de um robô móvel de baixo-custo, e a elaboração do estudo de caso em educação especial. / Assuming that robots will coexist with humans in the near future, it is conspicuous the need of Intelligent Control Architectures suitable for Human-Robot Interaction. Henceforth, this research has developed a behavioral Control Architecture Organization, whose main purpose is to allow the intuitive interaction of robot and people, thus fostering the collaboration between them. To this end, a synthetic emotional module, based on the Circumplex emotion theory, promoted the adaptation of the robot behaviors, implemented using Motor Schema theory, and the communication of its internal state. This Organization supported the adoption of the Control Architecture into an assistive application, which consists of the case study of assistive social robots as an auxiliary tool for special education. The experiments have demonstrated that the developed control architecture was able to meet the requirements of the application, which were conceived according to the opinion of the consulted experts. Thereafter, this thesis contributes with the design of a control architecture that is able to act upon the subjective evaluation based on cognitive beliefs of emotions, the development of a low-cost mobile robot, and the development of the case study in special education.

Supondo-se que os robôs coexistirão conosco num futuro próximo, é então evidente a necessidade de Arquiteturas de Controle Inteligentes voltadas para a Interação Humano-Robô. Portanto, este trabalho desenvolveu uma Organização de Arquitetura de Controle Inteligente comportamental, cujo objetivo principal é permitir que o robô interaja com as pessoas de maneira intuitiva e que motive a colaboração entre pessoas e robôs. Para isso, um módulo emocional sintético, embasado na teoria bidimensional de emoções, foi integrado para promover a adaptação dos comportamentos do robô, implementados por Esquemas Motores, e a comunicação de seu estado interno de modo inteligível. Esta Organização subsidiou a implantação da Arquitetura de Controle em uma aplicação voltada para a área assistencial da saúde, consistindo, destarte, em um estudo de caso em robótica social assistiva como ferramenta auxiliar para educação especial. Os experimentos realizados demonstraram que a arquitetura de controle desenvolvida é capaz de atender aos requisitos da aplicação, conforme estipulado pelos especialistas consultados. Isto posto, esta tese contribui com o projeto de uma arquitetura de controle capaz de agir mediante a avaliação subjetiva baseada em crenças cognitivas das emoções, o desenvolvimento de um robô móvel de baixo-custo, e a elaboração do estudo de caso em educação especial. / Assuming that robots will coexist with humans in the near future, it is conspicuous the need of Intelligent Control Architectures suitable for Human-Robot Interaction. Henceforth, this research has developed a behavioral Control Architecture Organization, whose main purpose is to allow the intuitive interaction of robot and people, thus fostering the collaboration between them. To this end, a synthetic emotional module, based on the Circumplex emotion theory, promoted the adaptation of the robot behaviors, implemented using Motor Schema theory, and the communication of its internal state. This Organization supported the adoption of the Control Architecture into an assistive application, which consists of the case study of assistive social robots as an auxiliary tool for special education. The experiments have demonstrated that the developed control architecture was able to meet the requirements of the application, which were conceived according to the opinion of the consulted experts. Thereafter, this thesis contributes with the design of a control architecture that is able to act upon the subjective evaluation based on cognitive beliefs of emotions, the development of a low-cost mobile robot, and the development of the case study in special education.

In a home environment, there are many tasks that a human may need to accomplish. These activities, which range from picking up a telephone to clearing rooms in the house, all have the common trend of fetching. These tasks can only be completed correctly with the consideration of many things including an understanding of what the human wants, recognition of the correct item from the environment, and manipulation and grasping of the object of interest. The focus of this work is on addressing one aspect of this problem, decomposing an image scene such that a task-specific object of interest can be identified. In this work, communication between human and robot is represented using a feedback formalism. This involves the back-and-forth transfer of textual information between the human and the robot such that the robot receives all information necessary to recognize the task-specific object of interest. We name this new communication mechanism Interactive Text Response (ITR), which we believe will provide a novel contribution to the field of Human Robot Interaction. The methodology employed involves capturing a view of the scene that contains an object of interest. Then, the robot makes inquiries based on its current understanding of the scene to disambiguate between objects in the scene. In this work, we discuss development of ITR in human-robot interaction, and understanding of variability, ease of recognition, clutter, and workload needed to develop an interactive robot system.

La robotique constitue une solution prometteuse pour développer des systèmes d'assistance visant à améliorer l'autonomie et les conditions de vie des personnes dépendantes. Ainsi, de nombreuses recherches sont menées actuellement à travers le monde pour concevoir et développer des robots portables ou exosquelettes, en tant que dispositifs d'aide à la mobilité pour augmenter les capacités motrices des sujets porteurs, ou comme auxiliaires de rééducation neuro-musculaire. Cette thèse vise le développement des modèles de connaissances nécessaires pour la mise en oeuvre de commandes assistives d'un exosquelette de l'articulation du genou, notamment celles basées sur l'intention du sujet porteur. Cet exosquelette est destiné à l'assistance des mouvements de flexion/extension du genou pour des personnes souffrant de pathologies du genou, ou pour le renforcement musculaire et la rééducation de sujets âgés ou hémiparétiques. Pour l'estimation de l'intention de mouvement du porteur, nous proposons modèle musculo-squelettique polynomial, complété par un modèle muscle-tendons de type Hill et le modèle bi-linéaire de Zajac pour modéliser la dynamique d'activation et de désactivation musculaire. Le modèle musculo-squelettique polynomial proposé offre le même niveau de réalisme et de précision qu'un modèle musculo-squelettique générique anatomique, sans nécessiter l'emploi de méthodes d'optimisation gourmandes en temps de calcul. Dans cette thèse, nous proposons un ensemble de trois commandes assistives destinées à guider ou à assister, via l'exosquelette, un sujet dans un contexte d'assistance à la rééducation en mode actif-aidé: La première, basée sur la passivité, exploite les propriétés physiques de l'exosquelette et du sujet porteur pour stabiliser asymptotiquement l'ensemble exosquelette-membre inférieur du porteur. Les paramètres du contrôleur sont ajustés automatiquement en fonction de la contribution du sujet au mouvement. A travers cette commande, l'exosquelette développe un couple correctif pour guider le genou vers la trajectoire de référence ou son voisinage. La seconde commande introduit une saturation pour maintenir le couple d'assistance dans un intervalle donné, garantissant ainsi la sécurité du sujet porteur. Cette commande garantit aussi des mouvements à des vitesses raisonnables et une convergence vers la trajectoire de référence. La deuxième loi de commande est complétée par une fonction permettant de moduler le couple d'assistance en fonction de la phase de rééducation. Enfin, la troisième commande proposée vise à maximiser la transparence de l'exosquelette pour éviter d'altérer les mouvements naturels du sujet porteur. Elle exploite la dynamique d'interaction induite par les mouvements relatifs du sujet porteur par rapport à l'exosquelette dus aux compliances intrinsèques de l'ensemble exosquelette-membre inférieur. Ces commandes ont été évaluées sur un sujet volontaire sain âgé de 29 ans, en considérant les modes d'assistance passif et actif-aidé. L'analyse des résultats expérimentaux montre de bonnes performances en termes de précision de poursuite de trajectoire, de robustesse vis-à-vis des incertitudes paramétriques et des perturbations externes. Ces résultats montrent également des propriétés importantes comme la sécurité du sujet porteur, le suivi précis de l'intention du porteur, l'assistance adaptative pour la rééducation active et la transparence de l'interaction exosquelette-porteur / Nowadays, robotics constitutes a promising solution to develop assistive systems to improve autonomy of dependent people during everyday activities. Thus, much research is being conducted currently worldwide to design and develop wearable robots or exoskeletons as assistive devices for mobility in order to improve the capabilities of the wearer. These devices can also be used during neuromuscular rehabilitation processes. This thesis aims to develop models necessary for the implementation of subject's intention wearer assistive control strategies using a knee joint exoskeleton. In order to estimate the movement intention of the wearer, we propose a Hill- Zajac based musculoskeletal model. This musculoskeletal model provides a high level of realism and accuracy compared to an anatomical generic musculoskeletal model without requiring the use of optimization methods techniques that are generally computational effort consuming. Three assistive control strategies are developed in this thesis to assist the wearer in a context of assistance and rehabilitation. In this thesis, we propose a set of three assistive commands to guide or assist through the exoskeleton, a subject in the context of rehabilitation assistance to active-assisted method: The first, based on passivity, operates the physical properties of the exoskeleton about the wearer and to stabilize the lower assembly asymptotically exoskeleton-member carrier. The first one is based on passivity and uses the physical properties of the exoskeleton and the wearer to stabilize asymptotically the human- lower-limb exoskeleton system. The second one introduces a saturation threshold to maintain the assistive torque in a given interval, ensuring the safety of the wearer. The third one aims to maximize the transparency of the exoskeleton to avoid altering the natural movements of the wearer. It uses the interaction dynamics induced by the relative movements between the wearer and the exoskeleton. These control strategies were evaluated on a 29-year-old healthy volunteer subject. The analysis of the experimental results shows satisfactory performances in terms of trajectory tracking accuracy, robustness with respect to parametric uncertainties and external disturbances. The results show also a good accuracy in the human intention detection and an adaptive support for active rehabilitation and transparent human-robot interaction

Cette thèse a pour but de contribuer à améliorer les interfaces Homme-machine. En particulier, nos appareils devraient répliquer notre capacité à traiter continûment des flux d'information. Cependant, le domaine de l’apprentissage statistique dédié à la reconnaissance de séries temporelles pose de multiples défis. Nos travaux utilisent la reconnaissance de gestes comme exemple applicatif, ces données offrent un mélange complexe de poses corporelles et de mouvements, encodées sous des modalités très variées. La première partie de notre travail compare deux modèles temporels de l’état de l’art pour la reconnaissance continue sur des séquences, plus précisément l’hybride réseau de neurones -- modèle de Markov caché (NN-HMM) et les réseaux de neurones récurrents bidirectionnels (BD-RNN) avec des unités commandées par des portes. Pour ce faire, nous avons implémenté un environnement de test partagé qui est plus favorable à une étude comparative équitable. Nous proposons des ajustements sur les fonctions de coût utilisées pour entraîner les réseaux de neurones et sur les expressions du modèle hybride afin de gérer un large déséquilibre des classes de notre base d’apprentissage. Bien que les publications récentes semblent privilégier l’architecture BD-RNN, nous démontrons que l’hybride NN-HMM demeure compétitif. Cependant, ce dernier est plus dépendant de son modèle d'entrées pour modéliser les phénomènes temporels à court terme. Enfin, nous montrons que les facteurs de variations appris sur les entrées par les deux modèles sont inter-compatibles. Dans un second temps, nous présentons une étude de l'apprentissage dit «en un coup» appliqué aux gestes. Ce paradigme d'apprentissage gagne en attention mais demeure peu abordé dans le cas de séries temporelles. Nous proposons une architecture construite autour d’un réseau de neurones bidirectionnel. Son efficacité est démontrée par la reconnaissance de gestes isolés issus d’un dictionnaire de langage des signes. À partir de ce modèle de référence, nous proposons de multiples améliorations inspirées par des travaux dans des domaines connexes, et nous étudions les avantages ou inconvénients de chacun / This thesis aims to improve the intuitiveness of human-computer interfaces. In particular, machines should try to replicate human's ability to process streams of information continuously. However, the sub-domain of Machine Learning dedicated to recognition on time series remains barred by numerous challenges. Our studies use gesture recognition as an exemplar application, gestures intermix static body poses and movements in a complex manner using widely different modalities. The first part of our work compares two state-of-the-art temporal models for continuous sequence recognition, namely Hybrid Neural Network--Hidden Markov Models (NN-HMM) and Bidirectional Recurrent Neural Networks (BDRNN) with gated units. To do so, we reimplemented the two within a shared test-bed which is more amenable to a fair comparative work. We propose adjustments to Neural Network training losses and the Hybrid NN-HMM expressions to accommodate for highly imbalanced data classes. Although recent publications tend to prefer BDRNNs, we demonstrate that Hybrid NN-HMM remain competitive. However, the latter rely significantly on their input layers to model short-term patterns. Finally, we show that input representations learned via both approaches are largely inter-compatible. The second part of our work studies one-shot learning, which has received relatively little attention so far, in particular for sequential inputs such as gestures. We propose a model built around a Bidirectional Recurrent Neural Network. Its effectiveness is demonstrated on the recognition of isolated gestures from a sign language lexicon. We propose several improvements over this baseline by drawing inspiration from related works and evaluate their performances, exhibiting different advantages and disadvantages for each

No description available.

<div> <p><br></p> </div> Individuals with disabilities and persons operating in inaccessible environments can greatly benefit from the aid of robotic manipulators in performing activities of daily living (ADLs) and other remote tasks. Users relying on robotic manipulators to interact with their environment are restricted by the lack of sensory information available through traditional operator interfaces. These interfaces only allow visual task access and deprive users of somatosensory feedback that would be available through direct contact. Multimodal sensory feedback can bridge these perceptual gaps effectively. Given a set of object properties (e.g. temperature, weight) to be conveyed and sensory modalities (e.g. visual, haptic) available, it is necessary to determine which modality should be assigned to each property for an effective interface design. However, the effectiveness of assigning properties to modalities has varied with application and context. The goal of this study was to develop an effective multisensory interface for robot-assisted pouring tasks, which delivers nuanced sensory feedback while permitting high visual demand necessary for precise teleoperation. To that end, an optimization approach is employed to generate a combination of feedback properties to modality assignments that maximizes effective feedback perception and minimizes cognitive load. A set of screening experiments tested twelve possible individual assignments to form the combination. Resulting perceptual accuracy, load, and user preference measures were input into a cost function. Formulating and solving as a linear assignment problem, a minimum cost combination was generated. Results from experiments evaluating efficacy in practical use cases for pouring tasks indicate that the solution is significantly more effective than no feedback and has considerable advantage over an arbitrary design. <br>