Living Lab: cooperative, predictive and resilient AI-driven infrastructure

Urban mobility systems continued to be strained due to traffic disturbances, including congestion, accidents, and emissions, resulting in significant financial, economic, and safety losses. Especially for stochastic disruptions or unforeseen events, such as traffic anomalies caused by various traffic disturbances, accidents and severe weather conditions, traditional traffic management systems and signal controls struggle to cope. To overcome these limitations, the transport ecosystem should transform the infrastructure to involve more intelligent, predictive, and cooperative participants. This work highlights several research efforts and complementary modules developed at TH Aschaffenburg over the past few years. An explainable and accident-aware congestion prediction framework is designed using a Bayesian network, followed by a multi-class fog modelling for weather-aware, robust perception. Moreover, ongoing research on the development and integration of reinforcement learning-based adaptive traffic signal control for traffic optimisation under uncertainty, a vehicle-to-everything-ready architecture for cooperative vehicle-infrastructure interaction, and the development of a digital twin framework for achieving a robust and reliable strategy through rigorous testing and validation is highlighted. Although these modules are studied individually, TH Aschaffenburg’s LiDAR-equipped City Mobility Living Lab facilitates the creation of an artificial intelligence-driven platform to unify, validate, and extend this research within real-world settings.