Road accidents are a major cause of death in urban areas. As many as 22,800 people were killed in road accidents in the EU in 2019, with 47.5% involving vulnerable road users, such as riders, bikers, and pedestrians. This fraction increases to 75% when considering accidents on urban roads.

The PMDI project aims to radically improve the safety of urban mobility by extending STEP, an automotive data management and analytics platform, to support real-time and near-real-time use cases, particularly focusing on dangerous crossings at urban intersections. These capabilities will be achieved by deploying STEP on Multi-access Edge Computing hardware modules and integrating fast AI-based video and image analytics, as well as danger detection algorithms, into the platform. These algorithms will take as input V2X messages from a variety of sources, including (virtual) on-board units and infrastructural sensors.

To ensure that dangerous conditions are accurately learned by the AI algorithms, digital twins of the road sections under analysis will be built, leveraging domain-specific language technologies designed to ease integration.

Politecnico di Milano participates in PMDI through the HEAPLab at the Dpartiment of Electronics, Information and Bioengineering, in close collaboration with Vodafone Automotive (the project coordinator), the University of La Sapienza (Rome), and the start-up Smart-I. Politecnico’s focus is on the modeling and simulation of different scenarios, considering both the creation of digital twins and the connection to network simulators."