Papers by patrick reignier
OMiSCID 2.0, un intergiciel libre et opensource pour la construction d'applications ubiquitaires
... Rémi Barraquand, Dominique Vaufreydaz, Rémi Emonet, Amaury Nègre, Jean-Pascal Mercier et Patr... more ... Rémi Barraquand, Dominique Vaufreydaz, Rémi Emonet, Amaury Nègre, Jean-Pascal Mercier et Patrick Reignier ... C'est le rôle de ce que l'on nomme un intergiciel (middleware), une couche logicielle intermédiaire permettant de simplifier la tâche des développeurs. ...
Proceedings of the 13th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
Social robots are transitioning from lab experiments to commercial products, creating new needs f... more Social robots are transitioning from lab experiments to commercial products, creating new needs for prototyping and design tools. In this paper, we present a framework to facilitate the prototyping of expressive animated robots. For this, we start by reviewing the design of existing social robots in order to define a set of basic components of social robots. We then show how to extend an existing 3D animation software to enable the animation of these components. By composing those basic components, robots of various morphologies can be prototyped and animated. We show the capabilities of the presented framework through 2 case studies.
Unmasking the causal relationships latent in the interplay between occupant’s actions and indoor ambience: A building energy management outlook
Applied Energy
Modélisation et utilisation du contexte
Reducing energy consumption is an individual and collective challenge that requires people to be ... more Reducing energy consumption is an individual and collective challenge that requires people to be proactive and fully involved. However, most approaches and solutions to this problem promote automated and autonomous systems that take full control of the decisions. Although these systems relieve users from setting the temperature in offices and homes, the level of thermal comfort chosen by the technology may not meet the individuals' requirements. Automating control is an obvious solution but it keeps the human out of the loop. In this work, an alternative approach is promoted based on system-human cooperation that allows people to take the final decision. However, to make sound decisions, users need to understand the system functioning and rationale and to be convinced and motivated to change their habits with regard to energy consumption. Our approach is based on an e-coach system, called Involved, that provides users with contextual explanations along with a user interface designed to persuade and keep the user involved. The results of this research are the development of an early prototype that provides end-users with a 24 hour-plan of recommended actions along with contextual explanations that justify each action. This plan satisfies the inhabitant's preferred compromise between thermal comfort, air quality and financial cost specified by the inhabitant (i.e. user) using a novel interaction technique, the Trade-Off-Pareto sliders. Users can edit the plan (e.g. suppress an action), skip some actions, perform additional actions, or even change their preferred compromise, and be informed in real time of the consequences on energy consumption and comfort.
Isas, 1999
This paper introduces a Virtual Reality platform based on a dynamic multi-agent programming langu... more This paper introduces a Virtual Reality platform based on a dynamic multi-agent programming language. These tools have been designed to show that simulating a Multi-Agent System in a virtual environment with dynamic properties can be used for Interactive Prototyping. This kind of prototyping has to be considered when the designed system cannot be described as a whole but as a set of autonous components with many interactions. Due to the fact that these interactions are very complex to model before simulating the system, we propose to let the designer enter inside the system and dynamically build, tune and mend the model. After making out a list of requirements to achieve this goal, we present our tool. Then, an example shows, through a very simple application, what an Interactive Prototyping session looks like.
O3MiSCID, a Middleware for Pervasive Environments
Abstract, This paper introduces a new lightweight middle-ware for pervasive environments. This mi... more Abstract, This paper introduces a new lightweight middle-ware for pervasive environments. This middleware abstracts network communications and provides service introspection and discovery using DNS-SD (DNS-based Service Discovery [1]). Services can declare simplex or duplex communication channels and variables. The middleware supports the low-latency, high-bandwidth communications required in interactive perceptual applications. It has been designed to be easy to learn in
O3MiSCID: an Object Oriented Opensource Middleware for Service Connection, Introspection and Discovery
ARéVi : une bo^ite à outil 3D pour des applications coopératives
Intelligence Ambiante Pro-Active : de la Spécification à l'Implémentation
ABSTRACT L'objectif de l'informatique ubiquitaire ou ambiante, telle que définit ... more ABSTRACT L'objectif de l'informatique ubiquitaire ou ambiante, telle que définit par Weiser dans son article de référence, est de faire disparaître l'informatique traditionnelle au profit d'un espace informatisé. L'ordinateur ambiant doit également offrir des capacités d'interaction plus naturelles, être transparent et utilisable sans effort. L'intelligence ambiante est la rencontre de l'intelligence artificielle et de l'informatique ambiante. Il s'agit de déterminer, grâce à l'ensemble des dispositifs de perception présents, l'activité des utilisateurs (le contexte) afin de mieux comprendre et anticiper leurs besoins et leur proposer automatiquement des services appropriés (assistants virtuels). On parle d'applications sensibles au contexte. La conception et la réalisation d'une application sensible au contexte est une tâche complexe, aussi bien du point de vue du développeur que de l'utilisateur final. Il est important de proposer une approche adaptée à ces deux catégories d'acteurs. Nous avons tout d'abord proposé un modèle formel de spécification de contexte permettant d'établir le dialogue entre l'utilisateur et le développeur de l'application. Notre objectif est ensuite de proposer des approches permettant d'automatiser une partie de la production du code de manière à raccourcir le chemin entre cette spécification du modèle de contexte et sa mise en oeuvre au sein d'une application. Dans le cadre de l'aide au développeur, nous avons proposé une approche basée sur l'apprentissage supervisé pour l'interprétation des données capteurs sous forme d'entités et de rôles. Cette interprétation des données capteurs sert d'entrée à la reconnaissance de contexte (scénarios). En nous appuyant sur une approche de type Ingénierie Dirigée par les Modèles, nous avons projeté la spécification du contexte vers deux méta-modèles pour la reconnaissance de scénarios : les réseaux de Petri synchronisés, et les réseaux de Petri Flous. Nous nous sommes également intéressés à l'apprentissage automatique d'un modèle de situations basé sur un ensemble d'observations annotées. Dans le cadre de l'aide à l'utilisateur final, nous avons proposé deux approches permettant à l'usager d'adapter précisément l'application à ses besoins réels. La première approche est basée sur une analyse hors ligne du comportement de l'application (apprentissage supervisé). La seconde approche propose une modification en situation (punition – récompense) en s'appuyant sur une approche de type apprentissage renforcé indirect.
ARéVi : A Virtual Reality Multiagent Platform
... 1 LI2, ENIB, Technopole Brest Iroise, CP 15, 29608 BREST cedex, France [reignier, harrouet, t... more ... 1 LI2, ENIB, Technopole Brest Iroise, CP 15, 29608 BREST cedex, France [reignier, harrouet, tisseau, morvan]@enib.fr 2 ENSAI, rue Blaise Pascal, Campus de Ker Lann, 35170 BRUZ, Francethierry.duval@ensai.fr ... ARéVi is built around a dynamic multiagent language: oRis. ...
Reinforced learning of context models for ubiquitous computing: a ubiquitous personal assistant
ABSTRACT delegation, auto-adaptative system. Abstract: Ubiquitous environments may become a reali... more ABSTRACT delegation, auto-adaptative system. Abstract: Ubiquitous environments may become a reality in a foreseeable future and research is aimed on making them more and more adapted and comfortable for users. Our work consists on applying reinforcement learning techniques in order to adapt services provided by a ubiquitous assistant to the user. The learning produces a context model, associating actions to perceived situatio ns of the user. Associations are based on feedback given by the user as a reaction to the behavior of the assistant. Our method brings a solution to some of the problems encountered when applying reinforcement learning to systems where the user is in the loop. For instance, the behavior of the system is completely incoherent at the beginning and needs time to converge. The user does not accept to wait that long to train the system. The user's habits may change over time and the assistant needs to integrate these changes quickly. We study methods to accelerate the reinforced learning process.
-Cet article présente les caractéristiques du langage de programmation par objets actifs oRis et ... more -Cet article présente les caractéristiques du langage de programmation par objets actifs oRis et son environnement d'exécution. Celui-ci constitue un outil générique pour la simulation de systèmes multi-agents. Parce qu'il intègre les principes de la programmation objet et une interface avec un langage d'IA (Prolog), oRis permet de simuler des modèles multi-formalismes (agents réactifs et cognitifs). Il est, de ce fait, particulièrement adaptés à la simulation des systèmes manufacturiers de production pour lesquels il est nécessaire de simuler à la fois le comportement du système opérants et les règles de gestion et de pilotage. La présentation du modèle de systèmes d'agents retenu montre l'intérêt de l'approche agents dans ce cadre.
oRis : un environnement de simulation interactive multi-agents
Tsi, 2002
Pervasive Computing:A Multidimensional Approach
Iwuc, Jun 1, 2007
This paper proposes a framework intended to help developers to create ubiquitous applications. We... more This paper proposes a framework intended to help developers to create ubiquitous applications. We argue that context is a key concept in ubiquitous computing and that, by nature, a ubiquitous application is distributed and needs to be easily deployable. Thus we propose an easy way to build applications made of numerous modules spread in the environment and interconnected. This network of modules forms a permanently running system. The control (installation, update, etc.) of such a module is obtained by a simple, possibly remote, command and without requiring to stop the whole system. We ourselves used this architecture to create a ubiquitous application, which we present here as an illustration.
Virtual Reality and Multi-Agent Systems for Manufacturing System Interactive Prototyping
This paper introduces a virtual reality platform based on a d ynamic multi-agent pro- gramming la... more This paper introduces a virtual reality platform based on a d ynamic multi-agent pro- gramming language. These tools have been designed to show that simulating a multi- agent system in a virtual environment with dynamic properties can be used for inter- active prototyping. This kind of prototyping has to be considered when the designed system cannot be described as a
Appeared in Journal of Robotics and Autonomous Systems
Humans and autonomous agents interactions in a virtual environment for fire-fighting training
This paper addresses the problem of segmenting small group meetings in order to detect different ... more This paper addresses the problem of segmenting small group meetings in order to detect different group configurations in an intelligent environment. To track and understand human activity, we need to identify human actors and their interpersonal links. A small group can be seen as basic entity, within which individuals collaborate in order to achieve a common goal. The segmentation of a small group meeting into different small group configurations is an important issue to understand the dynamics of the meeting as well as to detect meeting activity. Our approach takes speech activity detection of individuals attending a meeting as input. The goal is to separate distinct distributions of speech activity observation corresponding to distinct group configurations and activities. We propose an unsupervised method based on the calculation of the Jeffrey divergence between histograms of speech activity observations. These histograms are generated from adjacent windows of variable size slid from the beginning to the end of a meeting recording. The peaks of the resulting Jeffrey divergence curves are detected using successive robust mean estimation. After a merging and filtering process, the retained peaks are used to select the best model, i.e. the best speech activity distribution allocation for a given meeting recording. These distinct distributions can be interpreted as distinct segments of group configuration and activity. To evaluate, we recorded 5 small group meetings. We measured the correspondence between detected segments and labeled group configurations and activities. The obtained results are promising, in particular as our method is completely unsupervised.
This article lies within the interactive virtual stories telling scope and proposes the fuzzy cog... more This article lies within the interactive virtual stories telling scope and proposes the fuzzy cognitive use maps as a tool to model emotional behaviour of virtual actors improvising in free interaction within the framework of a "nouvelle vague" scenario, as could Godard do. We describe the implementation carried out, starting from work in cognitive psychology and let us illustrate it
Uploads
Papers by patrick reignier