Search

SARL is a general-purpose agent-oriented programming language. This language aims at providing the fundamental abstractions for dealing with concurrency, distribution, interaction, decentralization, reactivity, autonomy and dynamic reconfiguration that are usually considered as essential for implementing agent-based applications. Every programming language specifies an execution model. For SARL, this run-time model is supported by a SARL run-time environment. The goals of this paper are to highlight the key principles for creating a SARL run-time environment, and its concrete implementation into the Janus agent platform. Fil: Galland, Stéphane. Universite de Bourgogne; Francia Fil: Rodriguez, Sebastian Alberto. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Tucumán; Argentina. Universidad Tecnológica Nacional; Argentina Fil: Gaud, Nicolas. Universite de Bourgogne; Francia

Growth of population in the capital city of Pakistan—Islamabad—is too high. This growth rate has caused a negative impact on the smooth flow of traffic system. The aim of this paper is to provide a solution to facilitate the car-based commuters to pick the route with minimal bottlenecks and to minimize the distance to reach the destination. The proposed solution is to manage and control the traffic system in the city of Islamabad. The current traffic data collection system in Islamabad and other urban areas does not provide timely and reliable data that can be useful to the Regional Transportation Authority for planning activities. To overcome this problem, our approach is based on collecting the missing data using a custom-built mobile app. Our system analyses and manipulates the collected information based on artificial neural network scheme that can indicate the bottlenecks for each route and predicts the shortest route based on the user’s severity levels. To validate our proposed approach, we tested six different randomly selected routes in Islamabad with different bottlenecks.

The use of technologies such as Virtual Reality (VR) and Augmented Reality (AR) is more and more widespread in our everyday life and is now mature enough to be used in critical medical or aerospace applications. The main issue is then to provide more adaptive abilities to VR/AR applications in developing them using human concerns as primary element. To that way, beyond the classical HITL concept this paper proposes an integrative point of view for virtual environment design based on the concept of Bio-CPS. The goal of this paper is to present Bio-CPS related concepts and to sketch some guidelines for future virtual environments design focusing on specific application fields.

We propose a parallel computation model, called cellular matrix model (CMM), to address large-size Euclidean graph matching problems in the plane. The parallel computation takes place by partitioning the plane into a regular grid of cells, each cell being affected to a single processor. Each processor operates on local data, starting from its cell location and extending its search to the neighborhood cells in a spiral search way. In order to deal with large-size problems, memory size and processor number are fixed as O ( N ), where N is the problem size. Then one key point is that closest point searching in the plane is performed in O (1) expected time for uniform or bounded distribution, for each processor independently. We define a generic loop that models the parallel projection between graphs and their matching, as executed by the many cells at a given level of computation granularity. To illustrate its efficacy and versatility, we apply the CMM, on GPU platforms, to two problems in image processing: superpixel segmentation and stereo matching energy minimization. Firstly, we propose an extended version of the well-known SLIC superpixel segmentation algorithm, which we call SPASM algorithm, by using a parallel 2D self-organizing map instead of k -means algorithm. Secondly, we investigate the idea of distributed variable neighborhood search , and propose a parallel search heuristic, called distributed local search (DLS), for global energy minimization of stereo matching problem. We evaluate the approach with regards to the state-of-the-art graph cut and belief propagation algorithms. For each problem, we argue that the parallel GPU implementation provides new competitive quality/time trade-offs, with substantial acceleration factors as the problem size increases.

International audience

International audience

International audience

International audience

Agent-Based modelling has been around us for quite some time now and has thus become a crucial factor for executing prediction-based planning, such as the transportation models for metropolitan cities. This paper undertakes the fundamental understanding of the agent-based modeling and simulation and its application to the transportation models while discussing the scope of its applications and advantages too. The paper then presents the concepts attributed to the social behaviors in conjunction with the agent-based modelling techniques applied so far. The literature review conducted in lieu of this work has resulted in agreement with the fact that the potential of agent-based modelling is by far greater than ever due to the ever-improving computing speeds and capabilities, while the understanding of complex human behavior will continue to be a challenge for simulations and automation techniques developed so far. (C) 2017 The Authors. Published by Elsevier B.V.

The intelligent vehicle concept has been widely developed with the aim of solving problems caused by the increasing of vehicles in cities, such as congestion, air pollution and accident. With the increasing use of intelligent vehicles, traffic flow control methods have been improved as compared to the traditional methods, such as traffic light management. Among new possible methods, the one we want to explore in this paper is to combine several relative intelligent vehicles into one platoon with a reduced distance and allowing an increase of the road capacity. However, the use of platoons brings some issues at system level, for instance when several platoons encounter with each other at road nodes. In order to give answers to these issues, we define one organization strategies including defined interactions between vehicles and between platoons. In this paper, one multi-agent model is proposed to tackle with this issue. The proposed algorithm is implemented based on multi-level control method and is experimented in the scenario where one vehicles-train composed by three vehicles is reconfigured in two lane road.

This paper proposes a parallel computation model for the self-organizing map(SOM) neural network applied to Euclidean traveling salesman problems(TSP). This model is intended for implementation on the graphics processing unit(GPU) platform. The Euclidean plane is partitioned into an appropriate number of cellular units, called cells, and each cell is responsible of a certain part of the data and network. Compared to existing GPU implementations of optimization metaheuristics, which are often based on data duplication or mixed sequential/parallel solving, the advantage of the proposed model is that it is decentralized and based on data decomposition. Designed for handling large-scale problems in a massively parallel way, the required computing resources grow linearly along the problem size. Experiments are conducted on 52 publicly available Euclidean TSP instances with up to 85,900 cities for the largest TSPLIB instance and 71,009 cities for the largest National TSP instance. Experimental results show that our GPU implementations of the proposed model run significantly faster than the currently best-performing neural network approaches, to obtain results of similar quality.

This paper proposes a first comparison of different agent-oriented programming languages, including the SARL agent-programming language. The study of those tools is based upon various criteria that are defining the essential aspects of multi-agent systems. For the sake of clarity, the comparative study is presented in a tabular form, including the languages and all the criteria. For each criterion, a definition is made to understand its meaning. At the end of the article, all the languages will be described in order to define their advantages and disadvantages.

Synchronization mechanism is a key component of an agent-based simulation model and platform. Conservative and optimistic models were proposed in the domain of distributed and parallel simulations. However, the SARL agent-programming language is not equipped with specific simulation features, including synchronization mechanisms. The goal of this paper is to propose a conservative synchronization model for the SARL language and its run-time platform Janus.

International audience

Aktuelle Verkehrssimulationssysteme sind in der Lage Verkehrssituationen nahezu realitätsgetreu abzubilden. Die meisten dieser Systeme bilden die Physik der zu simulierenden Elemente ab und reproduzieren auf Grundlage dieser Modelle das Verkehrsgeschehen von Straßen, Städten, ja sogar von ganzen Ländern. Gerne wird in diesen Modellen jedoch der Faktor Mensch vernachlässigt - dabei trägt Letzterer durch sein Verhalten entschieden zu der Entwicklung von Verkehrssituationen bei. Das erste Ziel dieser Arbeit ist es einen Überblick darüber zu schaffen, bis zu welchem Grad aktuelle Verkehrssimulationssysteme in der Lage sind menschliches Verhalten zu reproduzieren. Zu diesem Zweck werden psychologische Modelle für menschliches Fahr- und Verkehrsverhalten analysiert und deren Ausdrucksstärke mit jenen Modellen verglichen, die derzeit in computergestützten Verkehrssimulationssystemen umgesetzt sind. Diese Analyse zeigt auf, dass es insbesondere auf der Ebene des strategischen Verkehrsverhaltens Defizite in aktuellen Implementierungen gibt. Strategisches Verkehrsverhalten hat jedoch einen gravierenden Einfluss auf das Verkehrsgeschehen und somit auch eine signifikante Bedeutung für Simulationssysteme. Die identifizierten Defizite beziehen sich in erster Linie auf die Repräsentation und die Umsetzung von Faktoren, welche aus Sicht von Psychologen für strategisches Verkehrsverhalten signifikant sind. Das zweite Ziel dieser Arbeit ist es diesen Missstand zu korrigieren und ein Simulationsmodell vorzustellen welches strategisches Verkehrsverhalten im Einklang mit psychologischen Erkenntnissen reproduziert. Diese Arbeit belegt die These, dass ein solches Simulationsmodell mit den Mitteln der Agententechnologie sowie der Dienst-Metapher umgesetzt werden kann. Contemporary traffic simulation systems are able to reproduce traffic situations in a highly realistic fashion. Most of these systems capture the physics of relevant elements and use these models to reproduce traffic scenes of selected roads, cities, and even entire countries. All too often, these models neglect human factors, yet, is it not that human beings significantly determine the outcome of traffic situations? The aim of this thesis is twofold. The first objective is to determine to what extend current traffic simulations are able to reproduce human behavior in traffic situations. For this purpose, psychological behavior conceptualizations are analyzed and compared to the expressiveness of those models that are currently implemented in computer-aided traffic simulation frameworks. The comparison reveals that there are in fact deficiencies - especially in the representation of one particular form of behavior, namely strategic level driver behavior. This particular form of behavior, however, has a serious impact on traffic situations and is therefore of great importance for traffic simulation systems, respectively. Identified deficiencies mainly concern the representation and implementation of those factors that, following human factors psychology, significantly affect strategic level driver behavior. The second objective of this work is to correct this misalignment and to present a simulation model which reproduces strategic level driver behavior in compliance with psychological findings. This work substantiates the thesis that such a simulation model can be realized by means of agent-technology and the service metaphor.