Automatic target recognition imposes the integration of a large variety of heterogeneous knowledge. This leads us to design an architecture distributing knowledge and performing parallel and concurrent processing. We chose a multi-agent approach with the implementation of specialized agents based on incrementality, cooperation, distribution, focus of attention and adaptability. The architecture being used is a multi-threaded one. It is build around an administrator and allows the formalisation of communication protocol between the agents. These agents differ in their role, their behavior ans information they handle and generate. At a given moment, many agent coexist in the image. Each one behaves in an autonomous way for reaching the data a...
International audienceMulti-agent systems is a discipline that grew out of Distributed Artificial In...
The Applied Artificial Intelligence group has developed a surveillance system based on the agents th...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThe aim of this work is ...
Automatic target recognition imposes the integration of a large variety of heterogeneous knowledge. ...
Cette thèse présente l'utilisation conjointe de la théorie de l'évidente et du suivi multi-hypothèse...
International audienceA multi-agent system is composed of numerous entities, called agents, interact...
This paper presents a model to define heterogeneous agents that solve problems by sharing the knowle...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThis thesis describes ou...
In this thesis, we address the problem of performing event exploration. We define event exploration ...
Un système multi-agents est composé d’un ensemble d’agents interagissant entre eux et avec leur envi...
This thesis describes our works on interaction policies for heterogeneous multiagent systems (hMAS),...
This thesis proposes a novel approach for computer vision, insisting on the role played by the infor...
This PhD thesis has been interested in two fields of artificial intelligence : reinforcement learnin...
AbstractInformation systems for networks of small and inexpensive sensors attached to computational ...
Cette thèse explore l'utilisation de fonctions de perte structurées dans deux domaines distincts. Da...
International audienceMulti-agent systems is a discipline that grew out of Distributed Artificial In...
The Applied Artificial Intelligence group has developed a surveillance system based on the agents th...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThe aim of this work is ...
Automatic target recognition imposes the integration of a large variety of heterogeneous knowledge. ...
Cette thèse présente l'utilisation conjointe de la théorie de l'évidente et du suivi multi-hypothèse...
International audienceA multi-agent system is composed of numerous entities, called agents, interact...
This paper presents a model to define heterogeneous agents that solve problems by sharing the knowle...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThis thesis describes ou...
In this thesis, we address the problem of performing event exploration. We define event exploration ...
Un système multi-agents est composé d’un ensemble d’agents interagissant entre eux et avec leur envi...
This thesis describes our works on interaction policies for heterogeneous multiagent systems (hMAS),...
This thesis proposes a novel approach for computer vision, insisting on the role played by the infor...
This PhD thesis has been interested in two fields of artificial intelligence : reinforcement learnin...
AbstractInformation systems for networks of small and inexpensive sensors attached to computational ...
Cette thèse explore l'utilisation de fonctions de perte structurées dans deux domaines distincts. Da...
International audienceMulti-agent systems is a discipline that grew out of Distributed Artificial In...
The Applied Artificial Intelligence group has developed a surveillance system based on the agents th...
Texte intégral accessible uniquement aux membres de l'Université de LorraineThe aim of this work is ...