Search

In this paper, we propose a method for coarse camera pose computation which is robust to viewing conditions and does not require a detailed model of the scene. This method meets the growing need of easy deployment of robotics or augmented reality applications in any environments, especially those for which no accurate 3D model nor huge amount of ground truth data are available. It exploits the ability of deep learning techniques to reliably detect objects regardless of viewing conditions. Previous works have also shown that abstracting the geometry of a scene of objects by an ellipsoid cloud allows to compute the camera pose accurately enough for various application needs. Though promising, these approaches use the ellipses fitted to the detection bounding boxes as an approximation of the imaged objects. In this paper, we go one step further and propose a learning-based method which detects improved elliptic approximations of objects which are coherent with the 3D ellipsoid in terms of perspective projection. Experiments prove that the accuracy of the computed pose significantly increases thanks to our method and is more robust to the variability of the boundaries of the detection boxes. This is achieved with very little effort in terms of training data acquisition -- a few hundred calibrated images of which only three need manual object annotation. Code and models are released at https://github.com/zinsmatt/3D-Aware-Ellipses-for-Visual-Localization., Comment: Presented at 3DV 2020. Code and models released at https://github.com/zinsmatt/3D-Aware-Ellipses-for-Visual-Localization

International audience; We present the use of a new computationaly efficient 3D physics model for the simulation of cells in a virtual aquatic world. In this model, cells can freely assemble and disconnect along the simulation without any separation between the development and evaluation stages, as is the case in most evo-devo models which only consider one cell cluster. While allowing for the discovery of interesting behaviors through the addition of new degrees of freedom, this 3D center-based physics engine and its associated virtual world also come with their drawbacks when applied to evolutionnary experiments: larger search space and numerous local optima. In this paper, we have designed an experiment in which cells must learn to survive by keeping their genome alive as long as possible in a demanding world. No morphology or strategy is explicitly enforced; the only objective the cells have to optimize is the survival time of the organism they build. We show that a novelty metric, adapted to our evo-devo matter, dramatically improves the outcome of the evolutionary runs. This paper also details some of the developmental strategies the evolved multicellular organisms have found in order to survive.

International audience; In this paper, we present a medical image integrity verification system to detect and approximate local malevolent image alterations (e.g. removal or addition of lesions) as well as identifying the nature of a global processing an image may have undergone (e.g. lossy compression, filtering ...). The proposed integrity analysis process is based on non significant region watermarking with signatures extracted from different pixel blocks of interest and which are compared with the recomputed ones at the verification stage. A set of three signatures is proposed. The two firsts devoted to detection and modification location are cryptographic hashes and checksums, while the last one is issued from the image moment theory. In this paper, we first show how geometric moments can be used to approximate any local modification by its nearest generalized 2D Gaussian. We then demonstrate how ratios between original and recomputed geometric moments can be used as image features in a classifier based strategy in order to determine the nature of a global image processing. Experimental results considering both local and global modifications in MRI and retina images illustrate the overall performances of our approach. With a pixel block signature of about 200 bit long, it is possible to detect, to roughly localize and to get an idea about the image tamper.

National audience; Real-time adaptive production control in the flexible manufacturing cell (FMC) is a complex issue that needs to be addressed to realize good performance and high productivity. In this paper, we have considered a support vector machine (SVM)-based simulation approach to resolve a production control problem in an FMC that operates in a dynamic environment. A SVM-based simulation approach chooses the most relevant scheduling rule out of several predefined ones on the basis of the current states of the system. This paper examines and compares the performance of the SVM-based simulation approach with the competent scheduling rules under two different operational environments which are characterized by the uncertainty of demand. We have also developed a Visual Basic-based simulation approach for scheduling of component parts in the context of FMC under different situations. The SVM methodology to control the production offers better performance than the single-rule-based production control system.

In this paper, the duality in differential form is developed between a 3D primal surface and its dual manifold formed by the surface's tangent planes, that is, each tangent plane of the primal surface is represented as a four-dimensional vector that constitutes a point on the dual manifold. The iterated dual theorem shows that each tangent plane of the dual manifold corresponds to a point on the original 3D surface, that is, the "dual" of the "dual" goes back to the "primal." This theorem can be directly used to reconstruct 3D surface from image edges by estimating the dual manifold from these edges. In this paper, we further develop the work in our original conference papers resulting in the robust differential dual operator. We argue that the operator makes good use of the information available in the image data by using both points of intensity discontinuity and their edge directions; we provide a simple physical interpretation of what the abstract algorithm is actually estimating and why it makes sense in terms of estimation accuracy; our algorithm operates on all edges in the images, including silhouette edges, self occlusion edges, and texture edges, without distinguishing their types (thus, resulting in improved accuracy and handling locally concave surface estimation if texture edges are present); the algorithm automatically handles various degeneracies; and the algorithm incorporates new methodologies for implementing the required operations such as appropriately relating edges in pairs of images, evaluating and using the algorithm's sensitivity to noise to determine the accuracy of an estimated 3D point. Experiments with both synthetic and real images demonstrate that the operator is accurate, robust to degeneracies and noise, and general for reconstructing free-form objects from occluding edges and texture edges detected in calibrated images or video sequences.

The placement of Virtual Network Function - Forwarding Graphs (VNF-FGs) is one of the basic operations in the networks of the future. Being NP-hard, several heuristics and metaheuristics have been proposed. However, these approaches are inefficient due to the need to recalculate the solution at each service placement. In this paper, we adapt one of the most advanced approaches in Deep Reinforcement Learning (DRL), in order to improve exploration by generalizing the neural network calculating action values. We also propose an evolutionary algorithm to evolve these neural networks in order to discover better ones, which also avoids getting stuck in local minima. In order to avoid going through the almost innumerable number of infeasible solutions, we propose a heuristic, which combined with our DRL, makes it possible to guarantee the feasibility of the solutions and therefore to make the placement much more efficient. The simulation results we obtained confirm the quality of the solutions obtained as well as the superiority of the proposed solution over the existing one.

Renewable resources like fish stock or forests should be exploited at a rate that supports regeneration and sustainability—a complex problem that requires adaptive approaches to maintain a sufficiently high exploitation while avoiding depletion. In the presence of oblivious agents that cannot keep track of all available resources—a frequent condition in swarm robotics—ensuring that the exploitation effort is correctly balanced is particularly challenging. Additionally, the possibility to exploit resources by multiple robots opens the way to focusing the effort either on a single or on multiple resources in parallel. This means that the swarm needs to collectively decide whether to remain cohesive or split among multiple resources, as a function of the ability of the available resources to replenish after exploitation. In this paper, we propose a decentralised strategy for a swarm of robots that adapts to the available resources and balances the effort among them, hence allowing to maximise the exploitation rate while avoiding to completely deplete the resources. A detailed analysis of the strategy parameters provides insights into the working principles and expected performance of the robot swarm., SCOPUS: ar.j, info:eu-repo/semantics/published

International audience; Cet article examine l'utilisation de langages de haut niveau dans la conception d'agents autonomes éthiques. Il propose un cadre logique nouveau et modulaire pour représenter et raisonner sur une variété de théories éthiques, sur la base d'une version modifiée du calcul des évènements, implémentée en Answer Set Programming. Le processus de prise de décision éthique est conçu comme une procédure en plusieurs étapes, capturée par quatre types de mo-dèles interdépendants qui permettent à l'agent d'évaluer son environnement, de raisonner sur sa responsabilité et de faire des choix éthiquement informés. Notre ambition est double. Tout d'abord, elle est de permettre la représentation systématique d'un nombre illimité de processus de raisonnements éthiques, à travers un cadre adaptable et extensible. Deuxièmement, elle est d'éviter l'écueil trop courant d'intégrer directement l'information morale dans l'engin de rai-sonnement général sans l'expliciter, alimentant ainsi les agents avec des réponses atomiques qui ne représentent pas la dynamique sous-jacente. Nous visons à déplacer de manière globale le processus de raisonnement moral du programmeur vers le programme lui-même. ABSTRACT. This paper investigates the use of high-level action languages for designing ethical autonomous agents. It proposes a novel and modular logic-based framework for representing and reasoning over a variety of ethical theories, based on a modified version of the Event Calculus and implemented in Answer Set Programming. The ethical decision-making process is conceived of as a multi-step procedure captured by four types of interdependent models which allow the agent to assess its environment, reason over its accountability and make ethically informed choices. The overarching ambition of the presented research is twofold. First, to allow the systematic representation of an unbounded number of ethical reasoning processes, through a framework that is adaptable and extensible. Second, to avoid the common pitfall of too readily embedding moral information within computational engines, thereby feeding agents with atomic answers that fail to truly represent underlying dynamics. We aim instead to comprehensively displace the burden of moral reasoning from the programmer to the program itself. MOTS-CLÉS : éthique computationelle, answer set programming, calcul d'évènements, raisonne-ment sur l'action et le changement.

International audience; Genetic Regulatory Networks (GRNs) implementations have a high degree of variability in their details. Parameters, encoding methods, and dynamics formulas all differ in the literature, and some GRN implementations have a high degree of model complexity. In this paper, we present a comparative study of different implementations of a GRN and introduce new variants for comparison. We use a modified Genetic Algorithm (GA) to evaluate GRN performance on a number of common benchmark tasks, with a focus on real-time control problems. We propose an encoding scheme and set of dynamics equations that simplifies implementation and evaluate the evolutionary fitness of this proposed method. Lastly, we use the comparative modifications study to demonstrate overall enhancements for GRN models.

National audience; In this paper we first present the STTL (SPARQL Template TransformationLanguage) language for the transformation of RDF graphs, designed as an exten-sion of SPARQL. Then we present a STTL-based platform for the design of Webbrowsers for the Linked Data. This platform is a SPARQL endpoint augmentedwith an STTL engine and services to run STTL transformations. Finally, weshow the capabilities of the platform by presenting three Web browsers: a firstone to execute SPARQL queries and present teir results in HTML; a secondone to navigate on the DBpedia RDF graph with HTML presentation formatsadapted to certain types of data; a third one that generates a mashup of a localRDF graph with the DBpedia RDF graph and provides a unified view; and alast one to manage and exploit a base of predefined SPARQL queries.; Dans cet article nous commençons par présenter le langage STTL (SPARQL Template Transformation Language) pour la transformation de graphes RDF, conçu comme une extension du langage SPARQL.Nous présentons ensuite une plate-forme qui implémente ce langage pour permettre la conception de navigateurs Web offrant une navigation hypertextuelle en HTML dans des graphes RDF sur le Web de données.La plateforme se présente sous la forme d'un serveur HTTP embarquant, outre un service SPARQL, un moteur de transformation STTL et des services Web permettant d'exécuter des transformations. Nous montrons les capacités du système en présentant quatre navigateurs~: un premier pour exécuter des requêtes SPARQL sur un graphe RDF local ou sur le Web et pour présenter les résultats en HTML; un second pour naviguer sur le graphe RDF de DBpedia avec des formats de présentation dédiés à certains types de ressources; un troisième pour présenter une vue unifiée d'un graphe local lié au graphe de DBpedia; et un dernier pour gérer et exploiter une base de requêtes SPARQL prédéfinies.

International audience; In this paper, we show how a dangerousness metric can be used to modify the input of a gene regulatory network when plugged to a virtual car. In the context of the 2015 Simulated Car Racing Championship organized during GECCO 2015, we have developed a new cartography methodology able to inform the controller of the car about the incoming complexity of the track: turns (slipperiness, angle, etc.) and bumps. We show how this dangerousness metric improves the results of our controller and outperforms other approaches on the tracks used in the competition.

National audience; Spatial relations constitute the core of many methods for scene understanding based on structural information. When a scene is analyzed by comparison with a model, or when it is dynamic and its evolution should be assessed, then tools for comparing spatial relations, often known or expressed imprecisely, have to be developed. In this paper, we propose two approaches to compare spatial relations represented as fuzzy sets, relying on optimal transport and mathematical morphology, respectively. Examples on medical images and video sequences illustrate the interest of these approaches; Les relations spatiales sont au cœur de beaucoup de méthodes d’interprétation de scènes à l’aide d’informations structurelles. Lorsque ces scènes sont analysées par comparaison avec un modèle, ou lorsqu’elles sont dynamiques et que l’on s’intéresse à leur évolution, il faut alors développer des outils pour comparer des relations spatiales, souvent exprimées ou connues de manière imprécise. Dans cet article, nous proposons deux approches pour comparer des relations spatiales représentées par des ensembles flous, l’une par transport optimal et l’autre par morphologie mathématique. Des exemples sur des images médicales et des séquences vidéo illustrent l’intérêt de ces approches

TAAABLE is a Case-Based Reasoning (CBR) system that uses a recipe book as a case base to answer cooking queries. TAAABLE participates in the Computer Cooking Contest since 2008, and succeeds thanks to a smart combination of various knowledge-based system methods and techniques, such as: CBR, knowledge representation, acquisition, discovery and management, and natural language processing. In this paper, we first present the CBR engine and its features such as the retrieval process based on minimal generalization of a query and different adaptation processes. Then the knowledge containers used by the system, and how they were acquired is detailed. To conclude, we discuss some research developments resulting from this application.

National audience; This paper addresses the task of emotion recognition in unstructured textual documents. It first reviews existing representations of documents able to cope with the subjectivity of their emotional content. We then describe the proposed method: following an early fusion strategy, features defined as n-grams of several orders are combined. Moreover, dictionaries specific to each emotion label are automatically extracted. The proposed decision process is implemented as a two level "one vs. all" strategy relying on linear SVM. The resulting system has been applied to the I2B2 track2 challenge and obtained a good ranking among systems relying on a low level representation of the data. We detail the results obtained over the corpus made of real data describing 4 241 sentences labeled with 12 emotion labels and 3 non emotional labels.; Cet article considère la tâche de classification de textes selon leur contenu émotionnel. Nous présentons d'abord un état de l'art des représentations textuelles pour extraire le contenu émotionnel des documents. Nous décrivons ensuite la méthode proposée : elle consiste à combiner, par fusion anticipée, des descripteurs définis comme des n-grammes de plusieurs ordres. De plus, elle extrait automatiquement des dictionnaires spécialisés pour chacune des émotions considérées. Le processus de décision proposé, de type « un contre tous » à deux niveaux, met en œuvre des classifieurs linéaires à vaste marge. Le système résultant a fait l'objet d'une participation à la compétition I2B2 track2 et s'est bien classé parmi ceux exploitant uniquement des descripteurs bas niveau. Nous analysons les résultats obtenus sur le corpus de données réelles fourni, qui représente 4 241 phrases étiquetées par 12 émotions et 3 classes non émotionnelles.

National audience; Conflicts are first-class citizen in Multi-Agents Systems and negotiation allows to handle these conflicts. We consider here the decision of agents having partial preferences since some alternatives are equivalent or incomparable. In order to evaluate the alternatives, we refine here the Pareto-optimality criteria by defining two kinds of compromise. We propose in this paper a negotiation game, i.e. a protocol and two strategies~: a conciliatory one and a temporizing one. Finally, we prove that the first one is social optimal while the second one is self-interested. Our experiments show that the temporizing strategy is dominant in very restrictive conditions and the number of agreements is smaller than the outcomes of a single agent decision and so less arbitrary.; Les oppositions sont intrinsèques aux systèmes multi-agents (SMA) et la négociation est un processus permettant de résoudre ces conflits. Nous nous intéressons ici à la négociation bilatérale mono-attribut. Elle consiste en un échange d'offres pour résoudre un problème de décision collective où les préférences sont partielles, certaines alternatives étant incomparables ou équivalentes. Afin d'évaluer les alternatives du point de vue de la société d'agents, nous raffinons ici le critère de Pareto-optimalité en définissant deux types de compromis. Nous proposons dans cet article un jeu de négociation bilatérale, c'est-à-dire un protocole et deux stratégies qui s'appuient sur des concessions : l'une conciliante et l'autre temporisatrice. Finalement, nous montrons que la première est meilleure socialement et la seconde meilleure individuellement. Nos expériences montrent que temporiser est une stratégie dominante dans un nombre très restreint de situations. De plus, nous observons que le résultat de la négociation est plus restreint que celui d'une décision mono-agent et donc réduit l'arbitraire de la décision.

National audience; The new application domains of multiagent-based simulation provide very large databases, which must be take into account not only for validating simulation results, but also for calibrating the behaviors of the agents. Indeed, the confidence in simulation predictions and explanations highly depends on the statistical realism of the agents. In this paper, we propose a method for automatically retrieving behavioral prototypes from statistical measures. This method has been experimented within the context of consumer behavior. The agents are endowed with the same overall behavior, but are given different profiles based on the data analysis. They are put into a spatially realistic store, where their purchase reproduce the original clusters. The knowledge retrieving process is general enough to be used in various application domains. Thus, we argue that such techniques are crucial to enhance the predictive accuracy of multi-agent simulations and make them a powerful decision support tool.; Les nouveaux domaines d'application des simulations multi-agents produisent de grandes quantités de données, qu'il convient de prendre en compte non seulement pour la validation des résultats de simulation, mais pour la calibration même des comportements des agents. En effet, la fiabilité des prédictions et des explications fournies par une simulation est fortement dépendante du réalisme statistique des agents qui y participent. Dans cet article, nous proposons une méthode pour extraire automatiquement des profils comportementaux à partir de données réelles, méthode que nous avons mise à l'épreuve dans le cadre de comportements de consommateurs dans un magasin. Les agents disposent des mêmes capacités globales d'interaction, mais sont munis de profils différenciés résultant de l'exploration des données. Placés dans un magasin virtuel réaliste, ils effectuent des achats qui reflètent la diversité des clients réels ainsi que les profils initiaux. Le processus de construction de connaissances que nous avons élaboré est assez général pour couvrir des domaines d'application variés. Aussi, nous défendons l'idée que de telles techniques sont indispensables pour renforcer le pouvoir prédictif des simulations multi-agents et en faire un puissant outil d'aide à la décision.

National audience; Recently government agencies have started to utilize innovative contracting methods that provide incentives for improving construction quality. These emerging contracting methods place an enormous pressure on the contractors to improve construction quality. For a general contractor, which subcontracts most tasks of a project and invites a number of bids, choosing an appropriate bid which satisfies the time, cost and quality of construction project is complex and challenging. To solve this problem involving conflicting objectives, a fuzzy clustering-based genetic algorithm (FCGA) approach is proposed in this paper. A case study of highway construction is used to demonstrate the applicability of the proposed approach. A comparative study is conducted over three test cases involving varying dimensions and complexities to test performance of the proposed FCGA against existing approaches. Results reveal that the FCGA is capable of generating better Pareto front than other existing approaches.

International audience; Technological advances in terms of data acquisition enable to better monitor dynamic phenomena in various domains including environment. The collected data are more and more complex (spatial, temporal, heterogeneous and multi-scale). The exploitation of this data requires new methods of data analysis and knowledge discovery. In this context, approaches for discovering spatio-temporal patterns are particularly relevant. This paper proposes to make a detailed review of these works. We focus on two examples of patterns : colocation and spatiosequential patterns. These patterns have been used to study real applications in the field of environment.; Les avancées technologiques en termes d’acquisition de données permettent de mieux surveiller les phénomènes évolutifs dans divers domaines dont l’environnement. Les données collectées sont de plus en plus complexes (spatiales, temporelles, hétérogènes et multi-échelles). L’exploitation de ces données par leurs propriétaires (experts du domaine) nécessite de concevoir de nouvelles méthodes d’analyse de données et de découverte de connaissances. Dans ce contexte, les approches de découverte de motifs spatio-temporels se révèlent particulièrement pertinentes. Ce papier propose de faire une revue détaillée de ces travaux. Nous nous focalisons sur deux exemples de motifs : les colocalisations et les motifs spatio-séquentiels. Ces motifs ont été utilisés pour étudier deux applications réelles dans le domaine de l’environnement.

Novelty-based segmentation of audio signals has proven good performances for the estimation of boundaries of structural sections within music pieces. However, boundaries are detected only if structural sections satisfy the condition of sufficient acoustic inner-homogeneity. While this constraint is very restrictive and not representative of all musical contents, we propose in this paper to extend the detection of acoustic novelty to transitions between homogeneous and non-homogeneous sections and vice versa. Moreover, the length of the considered sections for the boundary detection is crucial, we also introduce a multi-scale novelty approach that allows to capture boundaries between sections of different temporal scales in a same segmentation. Evaluation of the combination of these two methods proves convincing results for temporal segmentation of music pieces. Embedding the algorithm in a music structure segmentation system, we show that performances can be consistently improved for this task.

In this paper, we introduce a new approach to music structure segmentation that is based on the joint estimation of structural segments, keys and chords in one probabilistic framework. More precisely, the boundaries of a structure segment are determined by detecting key changes and by utilizing the difference in prior probability of chord transitions according to their position in a structural segment. In contrast to many of the recent approaches to structural segmentation, this system does not work with self-similarity matrices, although it has been designed to integrate this kind of approach into the framework at a later stage. However, just the current version of the system, using only the estimated harmony, is already producing encouraging results, especially with respect to the precise localization of the boundaries.

International audience; Metamorphic robots are robots that can change their shape by reorganizing the connectivity of their modules to adapt to new environments, perform new tasks, or recover from damages. In this paper we present a decentralized method for structural evolving of a class of lattice-based simulated metamorphic robots in a static environment. These robots are considered as a set of crystalline (compressible) modules that are able to connect or disconnect one from each another or even exchange information and energy with the neighbor modules in order to form various structures/patterns dynamically. Our approach is splitted in two layers: in the first layer a genetic algorithm is used to generate a number of well suited target configurations based on current information perceived from environment, while in the second layer a PacMan-like algorithm is used to make a plan for modules movement to transform the robot from its current pattern to the target pattern emerged in first layer.

National audience; In this paper, we propose a novel planner, called Moving Goal Planner (MGP) in order to adapt plans when the goal changes over time. This planner draws inspiration from Moving Target Search (MTS) algorithms. In order to limit the number of search iterations and to improve its efficiency, MGP delays as much as possible starting new searches when the goal changes. To this purpose, MGP uses two strategies: Open Check (OC) that checks if the new goal is still in the current search tree and Plan Follow (PF) that estimates whether executing the actions of the current plan brings MGP closer to the new goal. Moreover, MGP uses a parsimonious strategy to adapt incrementally the search tree at each new search that reduces the number of calls to the heuristic function and speeds up the search. Finally, we show evaluation results that demonstrate the effectiveness of our approach.; Dans cet article, nous proposons un nouvel algorithme de planification temps réel ap- pelé MGP (Moving Goal Planning) capable de s'adapter lorsque le but évolue dynamiquement au cours du temps. Cet algorithme s'inspire des algorithmes de type Moving Target Search (MTS). Afin de réduire le nombre de recherches effectuées et améliorer ses performances, MGP retarde autant que possible le déclenchement de nouvelles recherches lorsque que le but change. Pour cela, MGP s'appuie sur deux stratégies : Open Check (OC) qui vérifie si le nouveau but est présent dans l'arbre de recherche déjà construit lors d'une précédente recherche et Plan Follow (PF) qui estime s'il est préférable d'exécuter les actions du plan courant pour se rapprocher du nouveau but plutôt que de relancer une nouvelle recherche. En outre, MGP utilise une stratégie "conservatrice" de mise à jour incrémentale de l'arbre de recherche lui permettant de réduire le nombre d'appels à la fonction heuristique et ainsi d'accélérer la recherche d'un plan solu- tion. Finalement, nous présentons des résultats expérimentaux qui montrent l'efficacité de notre approche.

National audience; In this paper, we address a characterization problem coming from plant biology. The multiple characterization problem consists of entities (represented by Boolean assignments) belonging to several groups, and the goal is to find a characterization for each group using propositional logic. This characterization must be exact and the main difficulty is to compute the minimal one. We show that this problem is W[2]-Complete. We also propose a reformulation to a linear program and describe different approaches for its resolution. We experiment on random and real instances whose solutions are used to design a patent-protected diagnostic test.; Dans cet article, nous présentons un problème de caractérisation issu de la biologie végétale. Ce problème de caractérisation multiple consiste à traiter simultanément plusieurs groupes d'entités (représentées par des interprétations booléennes) et à trouver une caractérisation pour chacun d'eux sous forme de formules booléennes. Cette caractérisation doit être exacte et une des difficultés majeures est de trouver une caractérisation minimale. Une étude de complexité de ce problème est réalisée et nous arrivons à la conclusion que le problème est W[2]-Complet. Nous proposons une reformulation du problème en programmation linéaire ainsi que différentes approches de résolutions. Une étude expérimentale est réalisée sur des instances aléatoires ainsi que des instances réelles. Les résultats obtenus sur ces dernières ont pu être valorisés par le dépôt d'un brevet et la validation au niveau européen d'un test de dépistage basé sur les caractérisations trouvées.

National audience; The context of this work is multirobot exploration and mapping of unknown environments. Frontiers (boundaries between empty and unexplored areas) are points to go to in order to increase explored area. In this paper, we propose a frontier allocation method for the exploration and mapping of indoor environments using multiple robots. A wavefront propagation algorithm is used to build a local minimum free potential field with a gradient descending towards frontiers used for navigation and path distance computation. Exploration is done by successively exploring frontiers assigned using a novel, computationally inexpensive algorithm based on the cardinal of the set of robots closer to the frontier than the robot being assigned. Experiments in simulation and on robots demonstrated the validity of the frontier allocation approach.; Le contexte de ce travail est le problème de l'exploration multirobot d'environnements inconnus pour la construction d'une carte métrique. Nous proposons une nouvelle technique de déploiement distribuée, basée sur le choix de la frontière à explorer (limites entre les zones accessibles et inexplorées) en fonction de la position (rang relatif en termes de distance) du robot par rapport à ses voisins. Un champ de potentiels sans minimum local est calculé depuis chaque frontière permettant de connaître en tout point le chemin le plus court pour s'y rendre. L'exploration consiste à affecter régulièrement à chaque robot une frontière à atteindre. L'assignation d'une frontière à un robot est réalisée par un nouvel algorithme utilisant comme critère le nombre de robots plus proches de la frontière considérée. Des mesures de performance en simulation et avec des robots sont présentées et montrent la validité et l'efficacité de notre approche en comparaison à d'autres approches.

National audience; Supplier selection is nowadays one of the critical topics in supply chain management. This paper presents a new decision making approach for group multi-criteria supplier selection problem, which clubs supplier selection process with order allocation for dynamic supply chains to cope market variations. More specifically, the developed approach imitates the knowledge acquisition and manipulation in a manner similar to the decision makers who have gathered considerable knowledge and expertise in procurement domain. Nevertheless, under many conditions, exact data are inadequate to model real-life situation and fuzzy logic can be incorporated to handle the vagueness of the decision makers. As per this concept, fuzzy-AHP method is used first for supplier selection through four classes (CLASS I: Performance strategy, CLASS II: Quality of service, CLASS III: Innovation and CLASS IV: Risk), which are qualitatively meaningful. Thereafter, using simulation based fuzzy TOPSIS technique, the criteria application is quantitatively evaluated for order allocation among the selected suppliers. As a result, the approach generates decision-making knowledge, and thereafter, the developed combination of rules order allocation can easily be interpreted, adopted and at the same time if necessary, modified by decision makers. To demonstrate the applicability of the proposed approach, an illustrative example is presented and the results analyzed.

National audience; In this paper, we present a general framework for supervised classification. This framework only needs the definition of a generalisation operator and provides ensemble methods. For sequence classification tasks, we show that grammatical inference has already defined such learners for automata classes like reversible automata or k-TSS automata. Then we propose a generalisation operator for the class of balls of words. Finally, we show through experiments that our method efficiently resolves sequence classification tasks.; Dans cet article, nous présentons un cadre d'apprentissage général pour la classification supervisée. Ce cadre ne nécessite que la définition d'un opérateur de généralisation et fournit en particulier des méthodes d'ensemble. Pour les tâches de classification de séquences, nous montrons que l'inférence grammaticale, avec des objectifs différents, a déjà défini de tels apprenants pour certaines familles d'automates comme les réversibles ou les k-TSS. Nous proposons ensuite un opérateur de généralisation original pour la famille des boules de mots. Enfin, nous montrons au travers de différentes expérimentations que notre approche permet effectivement de résoudre des tâches de classification de séquences.

cote interne IRCAM: Lanchantin11a; None / None; National audience; Hidden Markov chains (HMC) are a very powerful tool in hidden data restoration and are currently used to solve a wide range of problems. However, when these data are not stationary, estimating the parameters, which are required for unsupervised processing, poses a problem. Moreover, taking into account correlated non-Gaussian noise is difficult without model approximations. The aim of this paper is to propose a simultaneous solution to both of these problems using triplet Markov chains (TMC) and copulas. The interest of the proposed models and related processing is validated by different experiments some of which are related to semi-supervised and unsupervised image segmentation.

This article deals with logical and graphical representations of uncertain information in a quantitative possibilistic theory framework. We first provide a deep analysis of relationships between these two forms of representational frameworks. Then, we provide a novel algorithm for reasoning with quantitative possibilistic logic. The algorithm exploits the syntactic relations between quantitative possibilistic logic bases and penalty logic bases. We provide experimental results that compare the propagation algorithm developed for the possibilistic product-based networks and the inference algorithm developed in this paper. quantitative possibilistic theory, penalty logic, uncertainty propagation algorithm.

[Departement_IRSTEA]Ecotechnologies [TR1_IRSTEA]MOTIVE [Coll_IRSTEA]Series: Lecture Notes in Computer Science; National audience; Models for representing multidimensional systems usually consider that facts and dimensions are two different things. In this paper we propose a model based on UML which unifies the representations of fact and dimension member. Since a given element can play the role of a fact or a dimension member, this model permits more flexibility in the design and the implementation of multidimensional systems. Moreover this model offers the possibility to express various constraints to guarantee desirable properties for data. We then show that this model is able to handle most of the hierarchies which have been suggested to take real situations into account and to characterize certain properties of summarizability. Using this model we propose a complete development cycle of a multidimensional system. It appears that this cycle can be partially automated and that an end user can control the design and the implementation of his system himself.

International audience; This paper proposes a local, cooperative and real-time multi-agent approach to build adaptive and incremental profiles where a user is supposed to be represented by a set of textual documents. These documents are sequentially parsed, which leads to the construction of a temporary terminological network (TTN). This network is then merged with the TTN resulting from other documents, in order to create a permanent terminological network (PTN). This PTN is representative of the studied collection and can be used to index this collection thanks to a clustering approach. Preliminary results of the built system as well as perspectives are then presented.; Ce papier propose une approche multi-agent locale, coopérative et temps réel pour la création de profils adaptatifs et incrémentaux dans laquelle un usager est supposé être représenté par un ensemble de documents textuels. Ces documents sont analysés séquentiellement conduisant alors à la création d’un réseau terminologique temporaire (RTT). Ce réseau est ensuite fusionné avec les RTT issus d’autres documents, afin de générer un réseau terminologique permanent (RTP) représentatif de la collection étudiée et pouvant être ensuite indexé pour en extraire un profil. Les résultats préliminaires obtenus ainsi que les perspectives associées sont enfin présentés.

cote interne IRCAM: Lanchantin08b; None / None; National audience; The hidden Markov chain (HMC) model is a couple of random sequences (X,Y), in which X is an unobservable Markov chain, and Y is its observable noisy version. Classically, the distribution p(y|x) is simple enough to ensure the Markovianity of p(x|y), that enables one to use different Bayesian restoration techniques. HMC model has recently been extended to "pairwise Markov chain" (PMC) model, in which one directly assumes the Markovianity of the pair Z=(X,Y), and which still enables one to recover X from Y. Finally, PMC has been extended to "triplet Markov chain" (TMC) model, which is obtained by adding a third chain U and considering the Markovianity of the triplet T=(X,U,Y). When U is not too complex, X can still be recovered from Y. Then U can model different situations, like non-stationarity or semi-Markovianity of (X,Y). Otherwise, PMC and TMC have been extended to pairwise "partially" Markov chains (PPMC) and triplet "partially" Markov chains (TPMC), respectively. In a PPMC Z=(X,Y) the distribution p(x|y) is a Markov distribution, but p(y|x) may not be and, similarly, in a TPMC T=(X,U,Y) the distribution p(x,u|y) is a Markov distribution, but p(y|x,u) may not be. However, both PPMC and TPMC can enable one to recover X from Y, and TPMC include different long-memory noises. The aim of this paper is to show how a particular Gaussian TPMC can be used to segment a discrete signal hidden with long-memory noise. An original parameter estimation method, based on "Iterative Conditional Estimation" (ICE) principle, is proposed and some experiments concerned with unsupervised segmentation are provided. The particular unsupervised segmentation method used in experiments can also be seen as identification of different stationarities in fractional Brownian noise, which is widely used in different problems in telecommunications, economics, finance, or hydrology.

Content based image retrieval using spatial image content (i.e. using multiple regions and their spatial relationships) is still an open problem which has received considerable attention in literature. In this paper we introduce a new representation of image based on the most general spatial image content representation that is Attributed Relation Graphs (ARG) representation and also a new method of image indexation. Like all CBIR systems, the one proposed here has two components: a segmentation component and a matching component using a novel inexact graph matching algorithm. We tested our work in lettrines image but it's also valid in general image.

In this paper, a graph classification approach based on a multi-objective genetic algorithm is presented. The method consists in the learning of sets composed of synthetic graph prototypes which are used for a classification step. These learning graphs are generated by simultaneously maximizing the recognition rate while minimizing the confusion rate. Using such an approach the algorithm provides a range of solutions, the couples (confusion, recognition) which suit to the needs of the system. Experiments are performed on real data sets, representing 10 symbols. These tests demonstrate the interest to produce prototypes instead of finding representatives which simply belong to the data set.

cote interne IRCAM: Schwarz07a; None / None; National audience; Corpus-based concatenative methods for musical sound synthesis have attracted much attention recently. They make use of a variety of sound snippets in a database to assemble a desired sound or phrase according to a target specification given in sound descriptors or by an example sound. With ever-larger sound databases easily available, together with a pertinent description of their contents, they are increasingly used for composition, high-level instrument synthesis, interactive exploration of a sound corpus, and others. This paper gives an overview of the components needed for corpus-based concatenative synthesis, and details of some realisations. Signal processing methods are crucial for all parts of analysis, (segmentation and descriptor analysis), for synthesis, and can intervene in the selection part e.g. for spectral matching.

In most works on negotiation dialogues, agents are supposed to be ideally honest. However, there are many situations where such a behaviour cannot always be expected from the agents (e.g. advertising, political negotiation, etc.). The aim of this paper is to reconsider the role of deceitful arguments in argumentation frameworks. We propose a logical tool for representing and handling deceitful arguments in a dialogue between two formal agents having to face their respective knowledge and trying to convince each other. X-logics, a nonmonotonic extension of classical propositional logics, is used as the background formalism for representing the reasoning of the agents on arguments. Starting from a previous work dedicated to the generation of new arguments, we propose to define the notion of lie as a new kind of possible agent's answer. Finally, we describe the way an agent may trick and how the other agent may detect it

This paper describes a methodology for recognizing equivalent knowledge-based diagnosis applications at knowledge level. This methodology is based on the notion of Conceptual Equivalence, that is formally developed. This notion of Conceptual Equivalence induces the definition of a generic inference structure for knowledge-based diagnosis applications named COPE, acronym for Compare, Observe, Predict and Evaluate, that is a canonical representation of this kind of applications at knowledge level.

Periodicity estimation of an audio signal, for applications such as pitch, multiple pitch or tempo estimation is often problematic due to the presence of multiple harmonics in the audio signal producing octave errors. While pitch models or rhythm models can be used, they remain often dedicated to a specific problem. In this paper, we propose a straightforward approach for periodicity estimation based on the combination of a spectral representation and a temporal representation. This method allows a better emphasis on the frequencies corresponding to the various pitches. We show the ability of this representation to adequately estimate pitch and visualize signals with multiple pitch content.

National audience; The reliability of critical real time distributed applications must be guaranty by formal techniques of validation, as the model-checking. However these techniques often lead to combinatory explosion problems. This paper proposes efficient abstractions of the timed automata model of TTA (Time-Triggered Architecture) in a temporal validation context.; La fiabilité des applications distribuées temps réel critiques doit être garantie par des techniques formelles de validation, comme le model-checking. Cependant, ces méthodes ont souvent des problèmes d’explosion combinatoire. Cet article propose des abstractions efficaces pour la modélisation et la validation temporelle de l’'architecture TTA (Time-Triggered Architecture) avec des automates temporisés (UPPAAL).

International audience; This paper presents a general approack both syntactic and semantic, for fusing prioritized bases where priorities are encoded in the possibilistic logic framework First a survey of différent classes of possibilistic merging operators is provided, analyzing the behaviors of conjunctive and disjunctive operators, having or not a reinforrement effect. We then show that approaches which have been recently proposed for fusing, propositional bases can be easily encoded with possibilistic setting. This has two, advantages: first, the result of merging is a prioritized base, hence the merging process can be decomposed and iterated in a coherent way. Moreover it provides a syntactic counterpart to the merging of propositional bases.; Cet article présente une approche générale, syntaxique et sémantique, pour la fusion de bases propositionnelles avec priorités explicites, ces dernières étant représentées dans le cadre de la logique possibiliste. Dans un premier temps, nous présentons différentes classes d'opérateurs de fusion possibilistes conjonctifs ou disjonctes, ayant ou non des effets de renforcement, etc. Nous montrons ensuite que les approches qui ont été récemment proposées pour la fusion des bases propositionnelles sans priorités peuvent être facilement exprimées dans le cadre possibiliste. Cela a deux avantages majeurs : le résultat de la fusion est une base avec priorités explicites, et par conséquent le processus de fusion peut être itéré d'une manière cohérente. De plus, on fournit une contrepartie syntaxique, de la fusion de bases propositionnelles généralement définie de manière sémantique.

International audience; This paper describes an original approach for content-based video indexing and retrieval. We aim at providing a global interpretation of the dynamic content of video shots without any prior motion segmentation and without any use of dense optic flow fields. To this end, we exploit the spatio-temporal distribution, within a shot, of appropriate local motion-related measurements derived from the spatio-temporal derivatives of the intensity function. These distributions are then represented by causal Gibbs models. To be independent of camera movement, the motion-related measurements are computed in the image sequence generated by compensating the estimated dominant image motion in the original sequence. The statistical modeling framework considered makes the exact computation of the conditional likelihood of a video shot belonging to a given motion or more generally to an activity class feasible. This property allows us to develop a general statistical framework for video indexing and retrieval with query-by-example. We build a hierarchical structure of the processed video database according to motion content similarity. This results in a binary tree where each node is associated to an estimated causal Gibbs model. We consider a similarity measure inspired from Kullback-Leibler divergence. Then, retrieval with query-by-example is performed through this binary tree using the maximum a posteriori (MAP) criterion. We have obtained promising results on a set of various real image sequences

In this paper, the issue of document structuring is addressed. To achieve this task, we advocate that Segmented Discourse Representation Theory (SDRT) is a most expressive discourse framework. Then we sketch a discourse planning mechanism which aims at producingas many paraphrastic document structures as possible from a set of factual data encoded into a logical form.

Le medium algorithmique est une infrastructure de communication qui augmente les pouvoirs des médias antérieurs en y ajoutant la mécanisation des opérations symboliques. Son émergence au milieu du vingtième siècle résulte d’une longue histoire scientifique et technique que je résume au début de l’article. Je rappelle ensuite les grandes étapes de son développement (ordinateurs centraux, internet et PC, Web social, Cloud augmenté par l’intelligence artificielle et la chaîne de blocs) ainsi que leurs conséquences sociocognitives. J’évoque pour finir les développements futurs de ce médium dans la perspective d’une intelligence collective réflexive basée sur une nouvelle forme de calcul sémantique., The algorithmic medium is an infrastructure of communication augmenting the powers of previous media by adding the automation of symbolic operations. Its emergence in the middle of the twentieth century results from a long scientific and technological history that I summarize at the beginning of the paper. Then I recall in this article the main stages of its development (mainframes, Internet and PC, social Web, cloud augmented by artificial intelligence and the blockchain) as well as their socio-cognitive consequences. I evoke in the end the future developments of this medium, in the perspective of a reflexive collective intelligence based on a new form of semantic computation.