Le récit est un outil de communication qui permet aux individus de donner un sens au monde qui les entoure. Il représente une plate-forme pour comprendre et partager leur culture, connaissances et identité. Le récit porte une série d'événements réels ou imaginaires, en provoquant un ressenti, une réaction ou même, déclenche une action. Pour cette raison, il est devenu un sujet d'intérêt pour différents domaines au-delà de la Littérature (Éducation, Marketing, Psychologie, etc.) qui cherchent d'atteindre un but particulier au travers de lui (Persuader, Réfléchir, Apprendre, etc.).Cependant, le récit reste encore sous-développé dans le contexte informatique. Il existent des travaux qui visent son analyse et production automatique. Les algorithmes et implémentations, par contre, restent contraintes à imiter le processus créatif derrière des textes littéraires provenant de sources textuelles. Ainsi, il n'existent pas des approches qui produisent automatiquement des récits dont 1) la source est constitué de matériel non formatées et passé dans la réalité et 2) et le contenu projette une perspective qui cherche à transmettre un message en particulier. Travailler avec des données brutes devient relevante vu qu'elles augmentent exponentiellement chaque jour grâce à l'utilisation d'appareils connectés.Ainsi, vu le contexte du Big Data, nous présentons une approche de génération automatique de récits à partir de données ambiantes. L'objectif est de faire émerger l'expérience vécue d'une personne à partir des données produites pendant une activité humaine. Tous les domaines qui travaillent avec des données brutes pourraient bénéficier de ce travail, tels que l'Éducation ou la Santé. Il s'agit d'un effort interdisciplinaire qui inclut le Traitement Automatique de Langues, la Narratologie, les Sciences Cognitives et l'Interaction Homme-Machine.Cette approche est basée sur des corpus et modèles et comprend la formalisation de ce que nous appelons le récit d'activité ainsi qu'une démarche de génération adaptée. Elle a est composé de 4 étapes : la formalisation des récits d'activité, la constitution de corpus, la construction de modèles d'activité et du récit, et la génération de texte. Chacune a été conçue pour surmonter des contraintes liées aux questions scientifiques posées vue la nature de l'objectif : la manipulation de données incertaines et incomplètes, l'abstraction valide d'après l'activité, la construction de modèles avec lesquels il soit possible la transposition de la réalité gardée dans les données vers une perspective subjective et la rendue en langage naturel. Nous avons utilisé comme cas d'usage le récit d'activité, vu que les pratiquant se servent des appareils connectés, ainsi qu'ils ont besoin de partager son expérience. Les résultats obtenus sont encourageants et donnent des pistes qui ouvrent beaucoup de perspectives de recherche. / Stories are a communication tool that allow people to make sense of the world around them. It represents a platform to understand and share their culture, knowledge and identity. Stories carry a series of real or imaginary events, causing a feeling, a reaction or even trigger an action. For this reason, it has become a subject of interest for different fields beyond Literature (Education, Marketing, Psychology, etc.) that seek to achieve a particular goal through it (Persuade, Reflect, Learn, etc.).However, stories remain underdeveloped in Computer Science. There are works that focus on its analysis and automatic production. However, those algorithms and implementations remain constrained to imitate the creative process behind literary texts from textual sources. Thus, there are no approaches that produce automatically stories whose 1) the source consists of raw material that passed in real life and 2) and the content projects a perspective that seeks to convey a particular message. Working with raw data becomes relevant today as it increase exponentially each day through the use of connected devices.Given the context of Big Data, we present an approach to automatically generate stories from ambient data. The objective of this work is to bring out the lived experience of a person from the data produced during a human activity. Any areas that use such raw data could benefit from this work, for example, Education or Health. It is an interdisciplinary effort that includes Automatic Language Processing, Narratology, Cognitive Science and Human-Computer Interaction.This approach is based on corpora and models and includes the formalization of what we call the activity récit as well as an adapted generation approach. It consists of 4 stages: the formalization of the activity récit, corpus constitution, construction of models of activity and the récit, and the generation of text. Each one has been designed to overcome constraints related to the scientific questions asked in view of the nature of the objective: manipulation of uncertain and incomplete data, valid abstraction according to the activity, construction of models from which it is possible the Transposition of the reality collected though the data to a subjective perspective and rendered in natural language. We used the activity narrative as a case study, as practitioners use connected devices, so they need to share their experience. The results obtained are encouraging and give leads that open up many prospects for research.

This thesis investigates the design of sociable technologies and is divided into three main parts described below. In the first part, we introduce sociable technologies. We review our the definition of technology and propose categories of technologies according to the motivation underlying their design: improvement of control, improvement of communication or improvement of cooperation. Sociable technologies are then presented as an extension of techniques to improve cooperation. The design of sociable technologies are then discussed leading to the observation that acquisition of social common sense is a key challenge for designing sociable technologies. Finally, polite technologies are presented as an approach for acquiring social common sense. In the second part, we focus on the premises for the design of sociable technologies. A key aspect of social common sense is the ability to act appropriately in social situations. Associating appropriate behaviour with social situations is presented as a key method for implementing polite technologies. Reinforcement learning is proposed as a method for learning such associations and variation of this algorithm are experimentally evaluated. Learning the association between situation and behaviour relies on the strong assumption that mutual understanding of social situations can be achieved between technologies and people during interaction. We argue that in order to design sociable technologies, we must change the model of communication used by our technologies. We propose to replace the well-known code model of communication, with the ostensive-inferential model proposed by Sperber and Wilson. Hypotheses raised by this approach are evaluated in an experiment conducted in a smart environment, where, subjects by group of two or three are asked to collaborate with a smart environment in order to teach it how to behave in an automated meeting. A novel experimental methodology is presented: The Sorceress of Oz. The results collected from this experiment validate our hypothesis and provide insightful information for the design. We conclude by presenting, what we believe are, the premises for the design of sociable technologies. The final part of the thesis concerns an infrastructure for the design of sociable technologies. This infrastructure provides the support for three fundamental components. First, it provides the support for an inferential model of context. This inferential model of context is presented; a software architecture is proposed and evaluated in an experiment conducted in a smart-environment. Second, it provides the support for reasoning by analogy and introduces the concept of eigensituations. The advantage of this representation are discussed and evaluated in an experiment. Finally, it provides the support for ostensive-inferential communication and introduces the concept of ostensive interface.

Animated agent technology has been rapidly developed to provide ubiquitously psychological and functional benefits for fulfilling communicative goals. However, the character motions of most character-centered models based on pre-stored movement, finite state machine and scripted conditional logic are generally restrictive. The major drawback lies in the lack of maturity of integrating the elements between personality, emotion and behaviour. To bridge the gap between cognitive and behavioural elements, we examine the connections between human personality, emotion, movement and cartoon modeling for the agent design. Human personality and emotional behaviour are the essences in the recognition of a believable synthetic character. Personality and emotion come from the storylines and result in characters’ motions. Cartoon animations successfully engage the audience and create emotional connections with the spectators. However, even a sophisticated animator often faces some difficulties while performing a very laborious task to simulate an emotion- and personality-rich character. This thesis focuses on exploring effective techniques to extract personality and emotion features for a high-level control of character movements. A hierarchical fuzzy rule-based system was constructed, in which personality and emotion were mapped into the body’s movement zones of a character. This facilitates agent designers to control the personality and emotion of a dynamic synthetic character. The system was then applied to a Narrative Intelligent system and extended to an Ambient Intelligent environment. An innovative storyboard-structured storytelling method was devised by using story scripts and action descriptions in a form similar to the content description of storyboards to predict specific personality and emotion. As software or device agents evolve into the Ambient Intelligence, new concepts for effective agent presentations and delegating control are necessary to minimise the human’s tasks and interventions in the complex and dynamic environment. A novel customizable personalised agent framework was developed by utilising the spirit of cartoon animation to match each user’s profile in the form of a cartoon reciprocal agent. As a result, users could explicitly modify personality and emotion values to change the psychology traits of the agent, which would affect their appearance and behaviour through body posture expression. An evaluation of the system was conducted to verify the effectiveness and the applicability in both Narrative and Ambient intelligent agent frameworks. The significance of this research is that applying higher cognitive factors to animated characters can lead to a better animation design tool and reduce strenuous animation production efforts in agent designs. It will also enable animated characters to embody more adaptive, flexible and stylised performance.

Darmstadt, Techn. Universiẗat, Diss., 2007. / Dateien im PDF-Format.

Zugl.: München, Univ., Diss., 2008

Τα μελλοντικά περιβάλλοντα υπολογισμού περιλαμβάνουν την ενσωμάτωση καθημερινών αντικειμένων, εφοδιασμένα με μικροσκοπικούς επεξεργαστές, αισθητήρες και κάρτες ασύρματων δικτύων. Τα έξυπνα αυτά αντικείμενα (τεχνουργήματα) μπορούν να εξερευνούν το περιβάλλον στο οποίο βρίσκονται και να επικοινωνούν μεταξύ τους. Η διαδραστικότητα με τον άνθρωπο μπορεί να παρέχει τη δυνατότητα αντιμετώπισης διαφόρων εργασιών με διαισθητικό τρόπο. Γίνεται αντιληπτό ότι μέσα σε ένα τέτοιο περιβάλλον, προκύπτουν σοβαρά ζητήματα που σχετίζονται με την ιδιωτικότητα των χρηστών. Αρχικά, εξαιτίας της αορατότητας των υπολογισμών που έχει σαν αποτέλεσμα οι χρήστες να μην τους αντιλαμβάνονται και έτσι να μην αισθάνονται ασφαλείς στο περιβάλλον αυτό. Επιπλέον, η παροχή ορισμένων υπηρεσιών απαιτεί τη μετάδοση και επεξεργασία προσωπικών δεδομένων και, ως εκ τούτου, εγκυμονεί κινδύνους για την προσωπική ζωή. Στην παρούσα εργασία ένα τέτοιο περιβάλλον (περιβάλλον περιρρέουσας νοημοσύνης) με τα παραπάνω χαρακτηριστικά, μοντελοποιείται μέσω των σφαιρών δραστηριοτήτων. Μια σφαίρα δραστηριοτήτων περιλαμβάνει όλη εκείνη την πληροφορία που απαιτείται για να εκτελεστεί μια συγκεκριμένη εργασία μέσα στο περιβάλλον. Στόχος της εργασίας είναι η μοντελοποίηση πολιτικών ιδιωτικότητας με κέντρο το χρήστη, η οποία μπορεί να πραγματοποιηθεί σε μια σφαίρα σε οποιοδήποτε περιβάλλον περιρρέουσας νοημοσύνης. Για να επιτευχθεί σημασιολογική ομοιογένεια, παρά την πιθανή ετερογένεια των πόρων ενός τέτοιου συστήματος, έχει σχεδιαστεί μια οντολογία για την αναπαράσταση αυτών των πολιτικών. Επιπλέον το σημασιολογικό αυτό πλαίσιο μοντελοποιεί τις βασικές αρχές και τους κανόνες αναφορικά με την προστασία των προσωπικών δεδομένων και την ιδιωτικότητα. Η προτεινόμενη οντολογία αξιολογείται βάσει αναγνωρισμένων κριτηρίων όπως είναι οι ερωτήσεις επάρκειας / Future computing environments involve integrating everyday objects equipped with tiny processors, sensors and wireless network cards. These smart objects (artifacts) may explore their environment and communicate with each other. Interactivity with humans may provide the ability of dealing with tasks in an intuitive way. It is clear that within this environment, serious issues related to the privacy of the users arise. Initially, due to the invisibility of all computations which results to the users being unaware of them. Moreover, the provision of certain services requires the transmission and processing of user’s personal data and thus poses a serious threat to their privacy. In the present project such an environment (ambient intelligence environment) with the above characteristics, is modeled through the concept of activity spheres. An activity sphere contains all the necessary information needed to realize a specific task within this environment. The aim of the project is to model a user-centered privacy policy which could be realized for a sphere in any ambient intelligence environment it is instantiated. To achieve semantic homogeneity, despite the possible heterogeneity of the resources within such an environment, an ontology has been designed. Furthermore, this semantic framework, models the fundamental principles and rules regarding personal data protection and privacy. The proposed ontology is evaluated by means of well-appreciated criteria such as competency questions

Cette thèse concerne à la gestion globale à base de modèle des flux énergétiques dans le bâtiment. L'objectif des systèmes de gestion de l’énergie proposés est d’aider les occupants à gérer leur système bâtiment en planifiant la consommation/production des différents équipements présents en fonction des tarifs, de la disponibilité de l'énergie et des usages de l'occupant. L’objectif de cette thèse est de proposer une approche de résolution multi-solveurs s'appuyant sur le paradigme multi-agent.Pour y parvenir, nous avons développé, dans un premier temps, un service multi-phase, qui représente plusieurs phases flexibles avec des niveaux de consommation différents, offrant un niveau de précision supérieure pour des équipements comme une machine à laver. Dans un second temps, notre travail a consisté à proposer une nouvelle approche d’optimisation combinant différents solveurs embarqués dans des agents logiciels. Le résultat est une approche d’optimisation hybride à base d’agents, s’appuyant sur des algorithmes PLNE et des méta-heuristiques. / This PhD focuses on the global energy management based on energetical flux models ofbuildings. The objective of the energy management system is to help the inhabitants to manage theirbuilding, by scheduling the consumption/production of the different appliances, taking into accountenergy costs, availability et inhabitants’ preferences. The PhD objective is to propose a resolution approach with several solvers inspired by the multi agent systems.A multi-phasis service representing several phasis has been developped. Each phasis is defined by its own consumption level. This type of service presents a better precision than singlephasis approaches to model some appliances. A new optimization approach has been developped. Itcombines different solvers embedded into software agents. The results is an hybrid approach forthe optimization based on the multi-agent system, using MILP algorithms and meta-heuristics.

La complexité et l'ampleur des scénarios de l'Intelligence Ambiante impliquent que des attributs tels que l'expressivité de modelisation, la flexibilité de representation et de deploiement et la facilité de configuration et de developpement deviennent des caracteristiques centrales pour les systèmes de gestion de contexte. Cependant, les ouvrages existants semblent explorer ces attributs orientés-developpement a un faible degré.Notre objectif est de créer un intergiciel de gestion de contexte flexible et bien configurable, capable de répondre aux différents scenarios. A cette fin, notre solution est construite a base de techniques et principes du Web Semantique (WS) et des systèmes multi-agents (SMA).Nous utilisons le WS pour proposer un noveau meta-modèle de contexte, permettant une modelisation expressive et extensible du contenu, des meta-proprietés (e.g. validité temporelle, parametres de qualité) et des dépendances (e.g. les contraintes d'integrité) du contexte.De plus, une architecture a base de SMA et des composants logiciels, ou chaque agent encapsule un aspect fonctionnel du processus de gestion de contexte (acquisition, coordination, diffusion, utilisation) est developpée.Nous introduisons un nouveau moyen de structurer le deploiement d'agents selon les dimensions du modèle de contexte de l'application et nous elaborons des politiques déclaratives gouvernant le comportement d'adaptation du provisionnement contextuel des agents. Des simulations d'un scenario d'université intelligente montrent que un bon outillage construit autour de notre intergiciel peut apporter des avantages significatifs dans la génie des applications sensibles au contexte. / The complexity and magnitude of Ambient Intelligence scenarios imply that attributes such as modeling expressiveness, flexibility of representation and deployment, as well as ease of configuration and development become central features for context management systems.However, existing works in the literature seem to explore these development-oriented attributes at a low degree.Our goal is to create a flexible and well configurable context management middleware, able to respond to different scenarios. To this end, our solution is built on the basis of principles and techniques of the Semantic Web and Multi-Agent Systems.We use the Semantic Web to provide a new context meta-model, allowing for an expressive and extensible modeling of content, meta-properties (e.g. temporal validity, quality parameters) and dependencies (e.g. integrity constraints).In addition, we develop a middleware architecture that relies on Multi-Agent Systems and a service component based design. Each agent of the system encapsulates a functional aspect of the context provisioning processes (acquisition, coordination, distribution, use).We introduce a new way to structure the deployment of agents depending on the multi-dimensionality aspects of the application's context model. Furthermore, we develop declarative policies governing the adaptation behavior of the agents managing the provisioning of context information.Simulations of an intelligent university scenario show that appropriate tooling built around our middleware can provide significant advantages in the engineering of context-aware applications.

This thesis aims to investigate the eect context could have to interaction between a user and a spoken dialogue system. It was assumed that using context-dependent voice commands instead of absolute semantic voice commands would make the dialogue more natural and also increase the usability. This thesis also investigate if introducing context could aect the user's privacy and if it could expose a threat for the user from a user perspective. Based on an extended literature review of spoken dialogue system, voice recognition, ambient intelligence, human-computer interaction and privacy, a spoken dialogue system was designed and implemented to test the assumption. The test study included two steps: experiment and interview. The participants conducted the dierent scenarios where a spoken dialogue system could be used with both context-dependent commands and absolute semantic commands. Based on these studies, qualitative results regarding natural, usability and privacy validated the authors hypothesis to some extent. The results indicated that the interaction between users and spoken dialogue systems was more natural and increased the usability when using context. The participants did not feel more monitored by the spoken dialogue system when using context. Some participants stated that there could be a theoretical privacy issues, but only if the security measurements were not met. The paper concludes with suggestions for future work in the scientic area. / Denna uppsats har som mal att undersoka vilken eekt kontext kan ha pa interaktion mellan en anvandare och ett spoken dialogue system. Det antogs att anvandbarheten skulle oka genom att anvanda kontextberoende rostkommandon istallet for absolut semantiska rostkommandon. Denna uppsats granskar aven om kontext kan paverka anvandarens integritet och om den, ur ett anvandarperspektiv, kan utgora ett hot. Baserat pa den utokade litteraturstudien av spoken dialogue system, rostigenkanning, ambient intelligence, manniska-datorinteraktion och integritet, designades och implementerades ett spoken dialogue system for att testa detta antagande. Teststudien bestod av tva steg: experiment och intervju. Deltagarna utforde olika scenarier dar ett spoken dialogue system kunde anvands med kontextberoende rostkommandon och absolut semantiska rostkommandon. Kvalitativa resultat angaende naturlighet, anvandbarhet och integritet validerade forfattarens hypotes till en viss grad. Resultatet indikerade att interaktionen mellan anvandare och ett spoken dialogue system var mer naturlig och mer anvandbar vid anvandning av kontextberoende rostkommandon istallet for absolut semantiska rostkommandon. Deltagarna kande sig inte mer overvakade av ett spoken dialogue system vid anvandning av kontextberoende rostkommandon. Somliga deltagare angav att det, i teorin, fanns integritetsproblem, men endast om inte alla sakerhetsatgarder var uppnadda. Uppsatsen avslutas med forslag pa framtida studier inom detta vetenskapliga omrade.

Ce travail présente une architecture logicielle concrète dédiée aux besoins et caractéristiques des systèmes d'Intelligence Ambiante (AmI). Le modèle comportemental proposé, appelé Higher-order Agent (HoA), capture simultanément l'évolution de l'état mental de l'agent ainsi que l'état de son plan d'actions. Les expressions du plan sont écrites et composées en utilisant un langage algébrique formel, nommé AgLOTOS. Les plans sont construits automatiquement et à la volée, comme un système de processus concurrents, déduits des intentions de l'agent et de ses préférences d'exécution. Basé sur une sémantique de plans et d'actions concurrentes, un service de guidance est aussi proposé afin d'assister l'agent dans le choix de ses prochaines exécutions. Cette guidance permet d'améliorer la satisfaction des intentions de l'agent au regard des plans concurrents possibles et en fonction du contexte actuel de l'agent. La "localité" et le "temps" étant considérés comme des informations contextuelles clés dans l'activité de l'agent, nous les prenons en compte au travers de deux fonctions utilitaires originales conçues à partir des expériences des exécutions d'action et pouvant être combinées suivant les préférences stratégiques de l'agent. La structure compositionnelle des expressions AgLOTOS est mise à profit pour permettre des révisions ciblées du plan de l'agent, Les révisions des sous-plans sont donc réalisées automatiquement en fonction des mises à jour apportées aux intentions, tout en maintenant la consistance du comportement de l'agent. Un cas d'étude est développé afin de montrer comment l'agent peut agir, même s'il subit des changements inattendus de son contexte, en fonction de ses expériences passées qui révèlent certains cas de d'échecs. / This work presents a concrete software architecture dedicated to ambient intelligence (AmI) features and requirements. The proposed behavioral model, called Higher-order Agent (HoA) captures the evolution of the mental representation of the agent and the one of its plan simultaneously. Plan expressions are written and composed using a formal algebraic language, namely AgLOTOS, so that plans are built automatically and on the fly, as a system of concurrent processes. Due to the compositional structure of AgLOTOS expressions, the updates of sub-plans are realized automatically accordingly to the revising of intentions, hence maintaining the consistency of the agent. Based on a specific semantics, a guidance service is also proposed to assist the agent in its execution. This guidance allows to improve the satisfaction of the agent's intentions with respect to the possible concurrent plans and the current context of the agent. Adopting the idea that "location" and "time" are key stones information in the activity of the agent, we show how to enforce guidance by ordering the different possible plans. As a major contribution, we demonstrate two original utility functions that are designed from the past-experiences of the action executions, and that can be combined accordingly to the current balance policy of the agent. A use case scenario is developed to show how the agent can act, even if it suffers from unexpected changes of contexts, it does not have many experiences and whose past experiences reveals some failure cases.