A real-life test bed for multi-agent monitoring of road network performance

This paper describes an approach to road network monitoring. The approach has the following components: a multi-agent hierarchical monitoring system in which the agents are network elements, such as crossings, road segments and routes, software engineering techniques to handle legacy sensors and to homogenize their heterogeneous data streams, distributed Kalman filtering to reduce sensor noise and a traffic simulation model to help in predicting future traffic states and to replace missing physical sensors. The approach has resulted in a real-life test bed for network performance monitoring in which various configurations of agents and various ways of distributed Kalman filtering can be tested. The current, still rather simple monitoring configuration is already in operational use for traffic management.