Swarm-based Traffic Simulation with Evolutionary Traffic Light Adaptation

J. Penner, R. Hoar, and C. Jacob (Canada)


evolutionary engineering, hybrid systems, intelligent agents


Traffic congestion has become a major concern for many cities throughout the world. Simulations provide useful tools for engineers to plan traffic systems. In this paper we discuss SuRJE, a swarm-based traffic simulation system. All interactions among individual drivers are implemented through the dropping and sniffing of pheromones on a 2-dimensional map. Furthermore, SuRJE is an interactive tool for testing and optimizing traffic light sequences through an evolutionary strategy.

Important Links:

Go Back