Grammar-Guided Genetic Programming for UAV-Based Mitigation of Urban Disaster Traffic Congestion

Created by W.Langdon from gp-bibliography.bib Revision:1.8344

@InProceedings{Wlodarczyk:2025:CCNC,

• author = "Damian Wlodarczyk and Takfarinas Saber",
• title = "Grammar-Guided Genetic Programming for {UAV-Based} Mitigation of Urban Disaster Traffic Congestion",
• booktitle = "2025 IEEE 22nd Consumer Communications \& Networking Conference (CCNC)",
• year = "2025",
• month = jan,
• keywords = "genetic algorithms, genetic programming, Disasters, Roads, Urban areas, Cost function, Autonomous aerial vehicles, Time measurement, Road traffic, Time factors, Traffic congestion, Urban Disaster, Unmanned Aerial Vehicles, Simulation of Urban MObility, Grammar-Guided Genetic Programming, G3P",
• ISSN = "2331-9860",
• DOI = "doi:10.1109/CCNC54725.2025.10975833",
• abstract = "As the global population grows and more people migrate to urban areas, road traffic becomes an increasingly critical problem. Minimizing and mitigating the effects of disaster traffic are crucial for reducing emissions, economic losses, and saving lives by enabling faster emergency response times. Existing works aim to optimise traffic and rerouting in disaster-struck scenarios, but different cost functions are effective under different circumstances and information levels. No single method consistently produces an optimal rerouting cost function regardless of the road segment affected or the information provided. This study aims to develop a method to generate a cost function that consistently produces optimal solutions and outperforms existing functions, regardless of the road segment affected or the amount of information available. We simulated five different disaster scenarios in Dublin City Centre, with each scenario involving a disaster-struck road segment. We considered the use of Unmanned Aerial Vehicles to capture data on road conditions, dividing it into five information levels, with each level adding data about roads farther from the disaster. Furthermore, we used Grammar-Guided Genetic Programming (G3P) to evolve efficient cost functions, which were then tested in the SUMO simulator using Dijkstra's algorithm to reroute traffic. The performance was measured by the Average Travel Time of vehicles. Our approach successfully generated efficient cost functions for each scenario and information level. In all but one case, the G3P-generated functions outperformed existing methods. In some scenarios, the G3P-generated functions achieved better average arrival times than those in non-disaster conditions. We observed a maximum improvement of 44.23percent in the Average Arrival Time compared to the no rerouting scenario and 14.99percent compared to the non-disaster scenario. The findings suggest that our proposed G3P-based rerouting approach could be beneficial even in regular non-disaster situations.",
• notes = "Also known as \cite{10975833}",

}

Genetic Programming entries for Damian Wlodarczyk Takfarinas Saber

Citations