We present a Decision Support System (DSS) for co-modal transportation. The DSS answers multiple route planning requests in a co-modal setting with vehicle preference and conflicting criteria, e.g., costs, time, and gas emissions minimization. The DSS architecture is based on the inherently distributed multi-agent systems framework that allows the decomposition of the route planning problem into multiple simpler tasks. A genetic algorithm is employed to obtain the optimal user-vehicle-route combinations according to the users preferences. The DSS is tested simulating itinerary requests with conflicting preferences in Nord Pas de Calais (France).

This paper addresses the problem of optimization in a distributed co-modal transport system. Transport systems are usually geographically distributed in dynamic changing environments. Such a system has to reach various sources in order to produce the necessary co-modal information for assisting the transport users and satisfying their requests. In this context, agent based technology might be very efficient. In this paper, we propose a combination of an evolutionary method and a multi-agent coalition in order to satisfy and optimize transport user itineraries demands in terms of total cost, total travelling time and total greenhouse gas emission. The presented co-modal transport system takes into account all possible means of transport, including carpooling, free use vehicles and public transport.

The co-modality is a new notion introduced by the European commission in 2006. It consists on developing infrastructures and taking measures and actions that will ensure optimum combination of individual transport modes enabling them to be combined effectively in terms of economic, environmental, service and financial efficiency, etc. Including different transport services in one system means that this one must cope with different distributed transport information stored in different location. For these reasons, we propose in this paper a distributed architecture that aims to satisfy transport users by providing them an optimized co-modal itineraries taking in account their constraints and preferences.

The co-modality is a new notion introduced by the European commission in 2006. It consists on developing infrastructures and taking measures and actions that will ensure optimum combination of individual transport modes enabling them to be combined effectively in terms of economic, environmental, service and financial efficiency, etc. Including different transport services in one system means that this one must cope with different distributed transport information stored in different location. For these reasons, we propose in this paper a distributed architecture that aims to satisfy transport users by providing them an optimized co-modal itineraries taking in account their constraints and preferences.

The paper presents a new approach based on a special distributed graphs in order to solve co-modal transport problems. The co-modal transport system consists on combining different transport modes effectively in terms of economic, environmental, service and financial efficiency, etc. However, the problem is that these systems must deal with different distributed information sources stored in different locations and provided by different public and private companies. In order to resolve the co-modal transport problems, we propose a distributed co-modal approach based on special distributed graphs that adapts to the distributed nature of real world transport information.

Nowadays, in transport sector, more researches are established in order to find solutions for the existing problems such as the future shortage of oil, the global warming… Most of these researches are turning to innovative alternative of private car like carsharing and carpooling. These means of transport represent a promising answer for economic and environment problems. In fact, total cost and gas emission quantities are considerably reduced if they are divided by the number of passengers. In this paper, we propose an evolutionary optimization method based on multi-agent approach which takes into account all possible means of transport, including carsharing, carpooling and multimodal common transport in order to satisfy transport user itineraries demands, respecting environment state. Our work is financed by the ademe (Agence de l'Environnement et de la Maitrise de l'Energie) and the regional council NPdC.

De nos jours, l’interet porte a la preservation de l’environnement a travers la reduction des emissions de gaz a effet de serre prend de plus en plus d’ampleur. Depuis 2006,la politique multimodale a evolue vers une politique co-modale qui n’oppose plus la voiture au transport public mais encourage une combinaison de tous les modes de transport sans favorisation dans le but d’une optimisation du service. Places dans ce cadre, le but de cette these est de mettre en œuvre un systeme de gestion de vehicules partages qui recouvre tous les services de transports existants tel que le transport public, le covoiturage, les vehicules en libre service et qui capable de satisfaire les demandes des utilisateurs en leur fournissant des itineraires co-modaux optimises en terme de temps, cout et emission des gaz a effet de serre tout en respectant leurs preferences et priorites. En recevant plusieurs requetes simultanees en un court laps de temps, le systeme doit etre capable a la fois de decomposer les solutions en troncons que nous appelons Routes, en respectant toutes les similarites entre les differentes demandes et de regrouper les informations de maniere coherente pour determiner les combinaisons de Routes possibles. Vu l’aspect dynamique et distribue du probleme, une strategie de resolution efficace mettant a profit une mixture de concepts ; a savoir les systemes multi-agents et l’optimisation a ete mise en place. Les resultats experimentaux presentes dans cette these justifient l’importance de la co-modalite et la necessite de mettre a profit la complementarite entre les vehicules partages et les autres moyens de transport a travers un systeme intelligent et global