Road Traffic Management
Based on Ant System and Regulation Model
Cyrille Bertelle, Antoine Dutot, Sylvain Lerebourg and Damien Olivier
Laboratoire d'Informatique du Havre,
25 rue Philippe Lebon, BP 540
76058 Le Havre Cedex - FRANCE
E-mail : {Cyrille.Bertelle, Antoine.Dutot, Sylvain.Lerebourg, Damien.Olivier}@univlehavre.fr
ABSTRACT:
Decision support system for road traffic management can be used for freight transport, people transport but also for site evacuation. We deal with two aspects of the decision support system in a same global architecture: one for road users to choose the shortest path in time between two points and the other for road traffic management to regulate the traffic and to avoid jam. These two aspects interact. The cartography is represented by a weighted digraph. The weights evolve according to the traffic and the graph is therefore dynamic. The search of the shortest path is based on an ant algorithm because it is well suited for dynamic environment. The regulation system is based on a neural network.
KEYWORDS:
Transport, distribution, road traffic, ant algorithm, multiagent systems, neural networks.
Back to MAS2003 Home Page