Evolving Better Rerouting Surrogate Travel Costs with Grammar-Guided Genetic Programming
Takfarinas Saber, Shen Wang · 2020
The number of drivers using on-board systems to navigate through urban areas is increasing. Drivers get real time information regarding traffic conditions and change their routes accordingly. Adapting a route clearly enables drivers to avoid closed roads or circumvent major hotspots. However, given the non-linearity of the traffic dynamics in urban environments, choosing a route based only on current traffic load or current average vehicle speed is not a guaranty of a lower overall travel time. In this work, we design an evolutionary system to search for better surrogate travel cost that drivers could optimise in their rerouting to achieve better overall travel times. Our system uses the Grammar-Guided Genetic Programming algorithm to evolve surrogate travel cost expressions and evaluate their performances on a micro traffic simulator. Our system is able to evolve different expressions that meet characteristics of specific urban environments instead of a one size fits all expression. We have seen in our experimental study on a traffic scenario representing Dublin city centre that our system is able to evolve surrogate travel cost expressions with ~34% and ~10% improvements in average travel time over the no rerouting and the average travel speed based rerouting algorithms.