Roadway congestion leads to wasted time and money and environmental damage. One possible solution is adding more roadway capacity, but this can be impractical especially in urban environments and still may not make up for a poorly-calibrated traffic signal schedule. As such, it is becoming increasingly important to use existing road networks more efficiently. Recent research has focused on developing more efficient traffic signal control algorithms. To further reduce delays, in this work, we consider the synergistic idea of dynamic routing, or changing vehicles' routes through the network to minimize the current delay. We generate new routes by simulating the current traffic state forward at each vehicle decision point, based on knowledge of the current routes of other vehicles and the control algorithms governing the traffic signals, and returning the fastest routes according to this forward simulation.

We evaluated our algorithm using the SUMO microscopic traffic simulator on different road networks (both synthetic and real-world examples) using different traffic signal control algorithms (fixed-timing plans and schedule-driven intersection control). Experiments carried out on combinations of networks and traffic signal control algorithms show that our rerouting protocol generally reduces delay for both vehicles participating in route guidance (adopters) and those that do not (non-adopters) and that the reduction in delay increases as the proportion of adopters does. In addition, we are able to achieve real-time performance on the (relatively small) road networks we tested on by learning a neural net approximation of expensive signal control algorithms and extending our basic routing algorithm into an anytime version compatible with early stopping. In the future, our routing could even potentially be interleaved with a traditional graph-search-based routing algorithm, combining the speed and scale of traditional routing with detailed small-scale optimizations generated by simulating ahead.