Designing adaptive urban mobility: a digital twin-driven architecture for intelligent traffic systems

This study investigates the integration of Industry 4.0 technologies in urban traffic management, aiming to optimize traffic flow, improve safety and enhance sustainability. The research focuses on Computer Vision, Digital Twins and Cloud Computing in real-time traffic adaptation, moving beyond static signal control to a dynamic, data-driven system. The proposed framework leverages interconnected sensors, AI-driven analytics and predictive modeling to provide a holistic, adaptive and integrated traffic management system. Method. First, a comprehensive literature review was conducted using Scopus, analyzing key studies on Intelligent Transportation Systems and their technological advancements. Second, a conceptual framework was developed to integrate traffic monitoring technologies, cloud-based analytics and real-time control mechanisms. The study evaluates the flow of information from data collection (Computer Vision, sensors, IoT) to decision-making (PLC controllers, AI-driven analysis) and real-time system adjustments (adaptive traffic signals, variable message panels). Findings The results demonstrate that vision-based traffic monitoring, integrated with IoT and cloud computing, enables real-time data collection and predictive analytics. AI-driven models improve traffic flow optimization, reduce congestion and adapt to environmental variables. Digital Twins (DT) provide a dynamic simulation environment, allowing for scenario testing and initiative-taking decision-making. The integration of edge computing and cloud-based analytics ensures low-latency responses and scalable infrastructure management. Additionally, the intelligent system enhances safety by detecting incidents, optimizing emergency response times and reducing vehicle emissions. Conclusions The proposed Intelligent Transportation System framework overcomes the limitations of static signal control by introducing adaptive, data-driven decision-making. Challenges such as system interoperability, infrastructure costs and cybersecurity risks remain, requiring further research on AI-driven traffic modeling and multi-objective optimization. Future advancements should focus on enhanced sensor fusion, decentralized control architectures and real-time urban mobility simulations to further improve traffic efficiency, sustainability and resilience.