Integrating multiagent systems for land use and transport with artificial city generation

• Grant number: 22/02113-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2022
• End date: April 30, 2023
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: André Carlos Ponce de Leon Ferreira de Carvalho
• Grantee: Luiz Fernando Silva Eugênio dos Santos
• Host Institution: Instituto de Ciências Matemáticas e de Computação (ICMC). Universidade de São Paulo (USP). São Carlos , SP, Brazil
• Company: Universidade de São Paulo (USP). Instituto de Ciências Matemáticas e de Computação (ICMC)
• Associated research grant: 20/09835-1 - IARA - Artificial Intelligence in the Remaking of Urban Environments, AP.PCPE

Abstract

The generation of highly realistic urban environments and artificial cities is of great interest to the entertainment industry as well as for the creation of true-to-life simulation sceneries on the lack of real-world data. Being based on a set of features found in real cities, the methods for the said purpose more often than not show the capability of replicating properties such as zoning, street network development, and population distribution. This aspect can be said to characterize an intersection with the domain of Land Use/Transport Interaction (LUTI) models, a class of methods that seeks to describe the dynamics of the use of urban spaces and transportation within it. It is known to exist in a wide variety of approaches to this type of modeling, those based on agents especially standing out for allowing the construction and evaluation of the model with a higher level of detail when compared to those solely based on spatial statistics, while also granting a greater interaction with the model in runtime and real-time responses. This work consists of a collaboration between the project Inteligência Artificial Recriando Ambientes (IARA) and the University of Tsukuba, its proposal being to use the knowledge built with the modeling of agents for urban simulation in LUTI models for the generation of artificial cities, providing the foundations for defining the components that make up the urban environment as well as a tool for creating the objective functions for the agents, favoring its use in urban planning and development by enabling interaction with the environment as well as with predefined city maps.(AU)