Mahdi Zargayouna

Management of urban parking: an agent-based approach

In the context of road urban traffic management, the problem of parking spots search is a major issue because of its serious economic and ecological fallout. In this paper, we propose a multi-agent system that aims to decrease, for private vehicles drivers, the parking spots search time. In the system that we propose, a community of drivers shares information about spots availability. Our solution has been tested following different configurations. The first results show a decrease in parking spots search time.

Agent information server: a middleware for traveler information

This paper proposes an Agent Traveler Information Server (ATIS) for a daily trip in an urban area. It is based on the multi-agent paradigm and is using the Environment as Active Support of Interaction (EASI) model. It instantiates the mutual awareness concept. The purpose is to allow services, information sources and human travelers to be represented by a unified agent structure and to allow them to interact homogeneously although they are conceptually different. Given that the whole information process must be envisaged in a real time configuration, the increase of the interactions has to be taken into account and the classical interaction modes become rapidly inefficient. The EASI model enables agents to build their interaction interests egocentrically and delegates the interaction management to the multi-agent environment.

Simulating the impact of future Internet on multimodal mobility

In the context of the EC-funded project Instant Mobility, we have defined a comprehensive architecture for transport and mobility applications that aim to innovate by introducing future Internet technologies to this domain. We have defined an Internet-based “multimodal travel platform” that provides information and services able to support new types of connected transport applications. The considered scenario is centered on multimodal travelers (both drivers and passengers). In this paper, we present the SM4T1 simulator, that we have designed and implemented to test the platform and to interact with it on behalf of multimodal travelers. SM4T is a fully agent-based simulator for multimodal travelers mobility. The application simulates the movements of travelers on the different transport networks (road and public transport) while taking into account the changes in travel times and the status of the networks.

Agent-based coordination model for designing transportation applications

This paper presents an environment-centered approach to design multi-agent solutions to transportation problems. Based on the property-based coordination principle (PbC), the objective of our approach is to solve three recurrent issues in the design of these solutions: the knowledge problem, the space-time dimension and the dynamics of the real environment. To demonstrate the benefits of our approach, two completely different applications, a demand-responsive transportation system and a simulator for crisis management, both based on this principle are presented. For each of them, we show how these recurrent issues have been solved.

Property based coordination

For a multiagent system (MAS), coordination is the assumption that agents are able to adapt their behavior according to those of the other agents. The principle of Property Based Coordination (PBC) is to represent each entity composing the MAS by its observable properties, and to organize their perception by the agents. The main result is to enable the agents to have contextual behaviors. In this paper, we instantiate the PBC principle by a model, called EASI -Environment as Active Support of Interaction-, which is inspired from the Symbolic Data Analysis theory. It enables to build up an interaction as a connection point between the needs of the initiator, those of the receptor(s) and a given context. We demonstrate that thanks to PBC, EASI is expressive enough to instantiate other solutions to the connection problem. Our proposition has been used in the traveler information domain to develop an Agent Information Server dynamically parameterized by its users.

An Agent-Based Community to Manage Urban Parking

In the context of road urban traffic management, the problem of parking spots search is a major issue because of its serious economic and ecological fallout. In this paper, we propose a multi-agent system that aims to decrease, for private vehicles drivers, the parking spots search time. In the system that we propose, a community of drivers shares information about spots availability. Our solution has been tested following different configurations. The first results show a decrease in parking spots search time.

Auto-organisation spatio-temporelle pour le VRPTW dynamique

Resume : Les problemes de tournees de vehicules sont des problemes de grande complexite pour lesquels differentes techniques d’intelligence artificielle ont ete utilisees. Dans ce papier, nous proposons un modele d’auto-organisation oriente-agent pour la version dynamique du probleme de tournees de vehicules avec fenetres temporelles. Notre proposition est fondee sur une representation spatio-temporelles des zones d’action des agents, capable de maintenir une bonne repartition des vehicules sur l’environnement. Cette repartition repond a l’objectif du probleme dynamique, puisqu’elle permet aux agents de prendre leurs decisions tout en anticipant les eventuels changements futurs des parametres du systeme. Mots-cles : Auto-organisation, Systemes multi-agents, Applications, Planification, Ordonnancement.

Impact of Travelers Information Level on Disturbed Transit Networks: A Multiagent Simulation

With the generalization of real-time traveler information, the behavior of modern transport networks becomes harder to analyze and to predict. It is now critical to develop simulation tools for mobility policies makers, taking into account this new information environment. Information is now individualized, and the interaction of a population of individually guided travelers have to be taken into account in the simulations. Multiagent simulation is proving to be a powerful model for analyzing transport activities. Indeed, autonomous agents provide an appropriate basis for modeling heterogeneous systems and environment-based systems. In this paper, we present a multiagent simulation model to measure the impact of information provision on the quality of passengers travels. This impact is measured by simulating different scenarios in function of the percentage of connected travelers, represented as agents. These simulated scenarios are analyzed following their impact on the average travel times of the travelers. Results show that the number of connected travelers has a positive impact on overall travel times up until a certain threshold before becoming negative.

A Data-Oriented Coordination Language for Distributed Transportation Applications

Data-oriented coordination languages rely on a shared space in which agents add, read and retrieve data. They are intuitively well suited for distributed transportation applications, where different actors evolve in a highly dynamic and very constrained environment. However, existing coordination languages can hardly be used for transportation applications, because they cannot express agents complex interaction needs. Indeed, in transportation applications, the interaction needs of the agents are driven by their current context and by ambient conditions, expressed in the form of constraints on the values taken by variables. In this paper, we propose Lacios , a new data-oriented coordination language for designing and implementing distributed transportation applications, and we illustrate our proposal with two examples: a traveler information system and a demand-responsive transport system. Lacios allows agents to express complex interaction needs, including agents states, system objects values, operators and functions, and is grounded on a model where the multi-agent system design is centered on the environment.

Towards a distributed multiagent travel simulation

With the generalization of real-time traveler information, the behavior of modern transport networks becomes harder to analyze and to predict. It is now critical to develop simulation tools for mobility policies makers, taking into account this new information environment. Information is now individualized, and the interaction of a huge population of individually guided travelers have to be taken into account in the simulations. However, existing mobility multiagent and micro-simulations can only consider a sample of the real volumes of travelers, especially for big regions. With distributed simulations, it would be easier to analyze and predict the status of nowadays and future networks, with informed and connected travelers. In this paper, we propose a comparison between two methods for distributing multiagent travelers mobility simulations, allowing for the consideration of realistic travelers flows and wide geographical regions.