Biblio

Effective traffic light control algorithms are of central importance for reducing congestion. While the currently most effective algorithms rely on expensive infrastructure to obtain knowledge of the traffic state, within the COLOMBO project, low-cost adaptive traffic light controllers have been examined that rely on swarm intelligence principles and the exploitation of V2X data. The swarm-based traffic light controller exploits numerical values that are adapted by the principles of stigmergy and used to switch between lower-level traffic light control strategies. This algorithm has more than 100 parameters that determine its behavior. In our work, we have explored the automatic configuration of this traffic light controller. In fact, the possibility of automatically configuring the parameters of the swarm-based traffic light control algorithm in this case is instrumental for the development of such a method and the high performance reached by it.