Special Issue: Advances in Intelligent Transportation Systems

Over the past decade, Intelligent Transportation Systems (ITSs) have evolved from conceptual frameworks into operationally deployed technologies. This Special Issue, “Advances in Intelligent Transportation Systems”, showcases significant progress in the integration of artificial intelligence, connected and automated vehicles (CAVs), and data-driven decision-support systems. The contributions published here demonstrate how advanced sensing, connectivity, and predictive modeling are reshaping the safety, efficiency, and sustainability of modern transportation networks.

For instance, Kim et al. [1] empirically examined the impact of vehicle-to-vehicle (V2V) warning information on driver behavior, showing that connected vehicle communication can effectively promote safer and more conservative driving patterns in real-world environments. Similarly, Kim H.K. [2] quantified the environmental benefits of automatic idling control in CAVs, finding that smart idling management could reduce CO₂ emissions by 23.6% and idling-related pollutants by over 90%. Beyond vehicle-level systems, Fathurrahman and Gautama [3] introduced spatial performance indicators for traffic flow prediction, illustrating how spatial clustering and node centrality provide new ways to evaluate model robustness beyond conventional accuracy metrics. Complementing these perspectives, Shi et al. [4] proposed a spatio-temporal deep learning model for metro flow prediction that accounts for external factors and periodicity, extending the scope of ITS applications to multimodal public transport systems.

Collectively, these works highlight the accelerating convergence of AI, sensing, and communication technologies in shaping the next generation of mobility systems. Yet, as noted by Zhao et al. [5], challenges remain in mixed-traffic conditions, where the coexistence of human-driven and automated vehicles can produce complex and sometimes counterintuitive safety and efficiency outcomes. Moreover, the institutional and technical infrastructures required for cross-sector data sharing and cooperative governance are still maturing.

Looking ahead, several directions for research and implementation emerge. As the transition toward mixed-traffic environments continues, the integration of legacy vehicles and CAVs must be carefully managed to ensure safety, efficiency, and public acceptance. Interactions among human drivers, automated systems, and infrastructure will shape how effectively new technologies perform under real-world conditions. At the same time, the development of cross-domain data-sharing architectures is becoming increasingly important. Vehicles, roadside infrastructure, and mobile systems generate vast amounts of heterogeneous data that, when integrated, can support real-time decision-making, proactive control, and adaptive traffic management. Furthermore, spatial–temporal performance indicators should play a central role in evaluating the operational reliability of predictive models. These indicators move beyond simple aggregate metrics by identifying localized vulnerabilities and resilience patterns within transportation networks. Finally, embedding sustainability and environmental objectives directly into ITS design and policy evaluation is essential. The incorporation of emissions reduction, energy efficiency, and ecological metrics—illustrated by [2]—will help ensure that technological innovation aligns with global goals for sustainable mobility.

In conclusion, the studies collected in this Special Issue reveal that ITS research is entering a phase of multidimensional innovation—linking technology, policy, and human behavior toward a more intelligent and sustainable mobility ecosystem. As connected and autonomous systems become increasingly integrated into daily life, fostering collaboration across academia, industry, and government will be essential to ensure that these technologies advance not only efficiency and safety but also equity and environmental stewardship.