Assessing São Paulo’s public transport efficiency and coverage through data-driven modeling of autonomous vehicle and vehicle-as-a-service integration

Abstract

Abstract São Paulo, the largest Brazilian metropolis, faces complex challenges in urban mobility, exacerbated by growing population demands and the unequal distribution of public transport infrastructure. This study analyzed the efficiency of the city’s public transportation system using geospatial visualization techniques and data analysis. Significant disparities were identified between central areas, which exhibit higher density and connectivity, and peripheral neighbourhoods, which experience lower vehicle frequency and longer waiting times. To address these challenges, the study explored the potential of emerging technologies, such as autonomous vehicles and the Vehicle-as-a-Service (VaaS) model, to expand coverage and enhance public transportation efficiency. Autonomous vehicles can help reduce accidents caused by human error and alleviate traffic congestion, while the VaaS model offers an intelligent integration of vehicles and urban infrastructure, fostering a more flexible and scalable mobility system. Despite the promising prospects of these innovations, their implementation faces several challenges, including the need for specific regulations, robust technological infrastructure, and public acceptance. This study concludes that adopting analytical technologies and emerging solutions is crucial to transforming urban mobility in São Paulo, fostering a more efficient, inclusive, and sustainable public transportation system.