Towards a Centralized Route Management Solution for Autonomous Vehicles

Currently, one of the main challenges that large metropolitan areas have to face is traffic congestion. To address this problem it is necessary to implement an efficient solution to control traffic that generates benefits for citizens such as reducing vehicle journey times and, consequently, environmental pollution as well. By properly analyzing traffic demand it becomes possible to predict future traffic conditions, and use this information for the optimization of routes. Such an approach becomes especially effective if applied in the context of automated vehicles, which have a more predictable behavior, thus being capable of mitigating the effects of traffic congestion by improving the traffic flow of the city in a centralized manner. This paper performs an experimental study of traffic congestion in an area characterized by intense traffic in the city of Valencia, Spain. By comparing the traffic flow in a typical day with our proposed improved solution, we show that significant benefits are achieved. In particular, we have created an interface to connect an existing urban traffic simulator (SUMO), and a network simulator (OMNeT++), with a modified route server. The latter continually updates present and future traffic conditions to properly balance traffic throughout the city. Experimental results show that our proposed Traffic Prediction Equation, combined with frequent updating of traffic conditions on the route server, is able to achieve substantial improvements in terms of average travel speeds and travel times, both indicators of lower degrees of congestion and improved traffic fluidity.