Emerging AI-driven smart and sustainable mobility

Övrig text i vetenskaplig tidskrift, 2025

The integration of artificial intelligence (AI) into urban mobility systems is transforming the landscape of smart and sustainable
transportation. As AI-driven technologies become embedded in urban infrastructures, connected and automated vehicles (CAVs), and
logistics systems, they unlock unprecedented opportunities to optimize vehicle operations, enhance safety, and reduce environmental
impact. AI-powered innovations, such as intelligent connected vehicles that improve traffic coordination, adaptive smart buses that
dynamically respond to passenger demand, and collaborative drone logistics for efficient last-mile deliveries, are re-shaping urban
transportation. However, the management of AI-driven mobility ecosystems presents a set of multifaceted challenges. Ensuring safety
in CAV systems and driver behavior, enhancing vehicle trajectory planning and control, improving traffic efficiency and energy
management, and increasing system resilience are just a few of the many issues that require innovative solutions. Addressing these
challenges necessitates collaboration across disciplines, bringing together experts in AI, transportation engineering, logistics, and
urban planning to create future-ready mobility systems that meet the growing demands of urban populations.
This Special Issue responds to the growing need for cutting-edge research and practical solutions in the domain of AI-driven smart
and sustainable mobility but also an opportunity to explore the interplay of technological, operational, and strategic factors shaping
the future of urban transportation systems. The fifteen articles selected for inclusion fill critical gaps in the existing literature by offering
a multifaceted exploration of AI applications in smart mobility. The contributions span a range of topics, from ensuring CAV
safety and risk assessment through neural network modeling and driver behavior prediction, and advancing vehicle trajectory
planning and control using predictive control and data-driven reconstruction, to improving traffic management and energy efficiency
in ride-hailing, logistics, and EV fleets, and strengthening system resilience through anomaly detection frameworks and robust control
of vehicle platoons. This editorial synthesizes key findings from the selected articles, highlighting their novelty, the problems they
address, and their individual and collective contributions to advancing knowledge and practice in AI-driven mobility systems.