Abstract
The article examines a comprehensive approach to analyzing the urban transport system, based on the integration of experimental and computational methods with the use of smart technologies.To conduct the research, models simulating various vehicle movement scenarios were employed. This makes it possible to optimize traffic flow parameters through the transmission and processing of relevant information for traffic management.The prospects for the development of Geographic Information Systems (GIS) in the transport sector are discussed, including the integration of “smart”vehicles equipped with onboard navigation and autopilot information systems to create “smart”transport systems. “Smart”transport systems should possess a well-developed road infrastructure, including modern technical means for traffic organization.In “smart”transport systems, methods and algorithms of machine learning, such as quantile regression and neural networks, are applied to predict traffic congestion and optimize vehicle routes.Experimental studies are necessary for the practical testing of proposals to improve the efficiency of transport systems based on optimizing the route of transport and interaction with the road infrastructure on control sections of roads.The research results will have practical significance for optimizing urban mobility and enhancing the efficiency of transport systems.