Smart Mobility: Pedestrian routes that minimize exposure to pollutants

AI-based solution that recommends healthier walking routes, reducing exposure to air pollutants such as NO₂ or PM2.5. The system integrates air quality data from multiple sources to improve real-time route planning and mobility decisions.

Market need: Cities face growing concerns about air quality and the adverse effects of pollution on pedestrians’ health (such as respiratory and cardiovascular diseases).Current pedestrian navigation systems prioritize the shortest route without considering exposure to air pollutants such as NO₂, PM2.5, or PM10. This limitation reduces potential benefits for municipalities, public health services, and urban mobility applications seeking to protect citizens and enhance urban sustainability.

Proposed solution: The proposed solution recommends “green” pedestrian routes, optimized to minimize exposure to atmospheric pollutants. The system models the city as a graph, where each segment has a weight associated with the estimated pollutant exposure. It applies graph algorithms combined with graph neural networks to interpolate both historical and real-time Air Quality Index (AQI) data. The system’s architecture has proven effective in real-world scenarios and can be integrated into mobility apps, smart-city platforms, or municipal services. Real-world tests using data from Barcelona demonstrated an average 7.82% reduction in NO₂ exposure with a minimal route increase of approximately 4%.

Competitive advantages

Advanced hybrid algorithm that improves the accuracy of route recommendations compared to conventional methods.
Transferable and scalable: adaptable design for other cities and urban contexts with available AQI data.
Health and sustainability focus: aligned with public health policies, smart-city strategies, and sustainable urban mobility initiatives, facilitating institutional adoption and public–private partnerships.