â Finalized
âš
The pilot focused on enhancing the use of data collected from loading and unloading zones across the Metropolitan Area of Barcelona. Through the RAPTOR Programme of EIT Urban Mobility, UTA member Kentyou deployed its AI-driven data platform âKentyou Eyeâ to support advanced data visualisation, predictive analytics and decision-support tools for improving city logistics management.
Key goal:
To transform raw operational data from loading/unloading zones into actionable intelligence that supports data-driven urban logistics policies, optimises parking demand management and improves traffic flow.
Urban freight and last-mile logistics place increasing pressure on metropolitan infrastructures. Barcelona collects large volumes of data through its dedicated application monitoring loading and unloading zones. However, the city faced challenges in extracting strategic value from this data for policy development and operational optimisation.
Within the RAPTOR framework, Kentyou collaborated with AMB to develop a digital twin-based mobility solution that integrates monitoring, predictive modelling and decision-support capabilities.
Kentyou Eye is an AI-powered data analytics platform designed to support integrated city data management and evidence-based mobility decision-making.
The pilot validated the operational deployment of a mobility digital twin focused on loading and unloading zones within a metropolitan environment. It confirmed the technical feasibility of integrating data collected through the cityâs dedicated loading and unloading zone application into the Kentyou Eye platform and combining real-time monitoring with predictive analytics.
In particular, the pilot demonstrated:
The Metropolitan Area of Barcelona significantly enhanced its capacity to extract strategic value from operational logistics data. Rather than relying solely on descriptive statistics, the city gained access to structured visual analytics and predictive insights.
This resulted in improved understanding of temporal demand patterns in loading zones, better identification of congestion hotspots, and clearer evidence for adjusting routing and traffic management strategies. The pilot shifted the data from passive monitoring towards active decision support.
The most immediate benefit was increased visibility over the utilisation of loading and unloading infrastructure. This transparency enables more efficient allocation of urban space and supports better coordination of freight flows.
At a strategic level, the solution strengthened evidence-based policymaking in urban logistics. By supporting demand forecasting and routing optimisation, the pilot contributed to the broader objectives of congestion reduction and more sustainable metropolitan mobility management.
Several structural insights emerged from the implementation. First, data quality and standardisation are critical preconditions for reliable predictive modelling. Second, close cooperation with city authorities is essential to ensure that dashboards and analytical outputs reflect real operational needs rather than purely technical possibilities. Finally, the data analytics and modelling approach proved particularly effective for testing policy scenarios in a controlled, low-risk environment prior to real-world implementation.
The RAPTOR framework enabled a focused and results-oriented collaboration within a relatively short timeframe. Despite its five-month duration, the pilot demonstrated how targeted AI-driven analytics can generate measurable operational improvements and create a scalable foundation for long-term metropolitan mobility digital transformation.
The experience provides a strong basis for replication in other European metropolitan areas facing similar logistics challenges. Future steps may include integration with additional mobility datasets, further enhancement of the data analytics and visualisation capabilities, and progressive scaling of predictive tools to support long-term logistics planning in the metropolitan area.
