AI-Driven Scenarios for Urban Mobility: Quantifying the Role of ODE Models and Scenario Planning in Reducing Traffic Congestion
Katsiaryna Bahamazava
TL;DR
This work tackles urban congestion by integrating foresight driven scenario planning with an ODE based model of AI adoption and traffic dynamics. It introduces a two axis framework (AI adoption rate and regulatory support) to generate four plausible futures and develops a coupled system where congestion $C(t)$ decreases as AI adoption $A(t)$ rises, subject to regulatory and societal conditions. Through scenario-specific parameterization and Python-based simulations, the paper derives adoption thresholds (notably around $60\%$ under favorable regulation and $75\%$ without) and discusses policy levers, potential unintended consequences, and empirical validation paths. The approach provides a structured, quantitative, and actionable toolkit for policymakers to steer urban mobility toward sustainable and equitable outcomes as AI technologies mature.
Abstract
Urbanization and technological advancements are reshaping urban mobility, presenting both challenges and opportunities. This paper investigates how Artificial Intelligence (AI)-driven technologies can impact traffic congestion dynamics and explores their potential to enhance transportation systems' efficiency. Specifically, we assess the role of AI innovations, such as autonomous vehicles and intelligent traffic management, in mitigating congestion under varying regulatory frameworks. Autonomous vehicles reduce congestion through optimized traffic flow, real-time route adjustments, and decreased human errors. The study employs Ordinary Differential Equations (ODEs) to model the dynamic relationship between AI adoption rates and traffic congestion, capturing systemic feedback loops. Quantitative outputs include threshold levels of AI adoption needed to achieve significant congestion reduction, while qualitative insights stem from scenario planning exploring regulatory and societal conditions. This dual-method approach offers actionable strategies for policymakers to create efficient, sustainable, and equitable urban transportation systems. While safety implications of AI are acknowledged, this study primarily focuses on congestion reduction dynamics.