Methodologies, Platforms, Ontologies and Techniques for a Multi-Agent Architecture for Simulation of Traffic with Communications

Inter-vehicle communications, in the context of Intelligent Transportation Systems, will probably bring a significant improvement in both traffic safety and efficiency. In order to evaluate in what measure this is true, traffic simulations that take into account the communications between vehicles are needed. Several approaches are being pursued to this end, many of them working on the integration of existing traffic simulators and network simulators. However, this integration is, in most cases, done offline, not allowing real-time operation. Another line of research proposes traffic simulation with the use of agents, allowing the development of more adaptive systems. However, these proposals don't consider implicit vehicle communications and its integrated simulation. In this paper, we propose a novel agent-based architecture, in which the simulation and management of the inter-vehicle communications are integrated in simulated agent-based vehicles and infrastructure, in a hierarchical multi-agent environment. In this architecture, each simulated vehicle is in itself a multi-agent system, with specialized agents to manage driving maneuvers, vehicle data, localization, communication filtering and interface. Intervehicle communications are managed by an agent-based module that simulates real wireless communications between vehicles, using the appropriate standards. To allow interoperability, the platform supporting the development of the proposed multi-agent system complies with FIPA specifications. Moreover, since the approach to a multi-agent system involve multiple choices about the appropriated methodologies, platforms, ontologies, communication standards, among others, a resumed roadmap is also presented.