Use case

CLASS incorporates a very challenging smart city use case upon which the capabilities of the CLASS software architecture will be evaluated.

Concretely, the CLASS smart city use case is being developed on top of the CLASS software architecture and includes four advanced mobility applications: digital traffic sign, smart parking, air pollution estimation and obstacle detection. The use case is deployed at the Modena Automotive Smart Area (MASA), a real environment within the city of Modena in Italy. This area is equipped with the necessary infrastructure (e.g., sensors and cameras for the recognition of obstacles) for the experimentation of connected driving technologies. Moreover, three connected prototype vehicles, incorporating sensing, communication and computation infrastructure, are available to develop and test the CLASS use-case.

MASA area, Modena, Italy

Through the smart city use case, CLASS aims to efficiently process multiple and heterogeneous streams of data to extract valuable information, create a common Data Knowledge Base (DKB) for the city, and improve the quality of citizenship in terms of sustainability, services and safe mobility.

Below there is a description of the four smart city use case applications:

  • The digital traffic sign application offers the opportunity to experiment, on a simulated environment, the impact of dynamically changing the traffic conditions based on real-time information collected from the distributed sensor infrastructure of the MASA (the use of a simulated environment is motivated due to the legal regulations of the City of Modena that forbids to actuate over actual traffic signs). In case of accidents, the traffic signals will advise the “best path to follow”, reducing the induced traffic impact and improving the driver experience. For emergency vehicles (e.g., ambulances, firefighters and police vehicles) it will dynamically create "green routes" by adjusting the frequency of the traffic lights to reduce the time of intervention. Key benefits are:

    • an improved driving experience, reducing the time it takes to circumvent blocked traffic situations related to congestion, accidents, road works, etc.
    • reduced CO2 emissions in central urban areas
    • improved safety of Vulnerable Road Users (VRU), like pedestrians, cyclists, etc.

    Traffic sign application from the CLASS connected car

     

  • The smart parking application collects real-time information about the available parking places in the monitored area. The detection of free parking lots will be based on the real-time elaboration of the video streams from existing and newly installed connected cameras, and also on the parking slots sensors.

    Edge nodes will send the pre-elaborated information to cloud city nodes which will elaborate a consistent representation of the available parking slots. A car searching for a free parking place will then send a request to the cloud of the city which will be able to inform the car about the available places in real-time.

    CLASS vehicle detecting parking space

  • The air pollution simulation application uses the data coming from the distributed sensor infrastructure of the MASA to estimate the pollution emissions of current traffic conditions in real-time. Emissions are computed using the PHEMLight + COPERT V emission model, a simplified version of Passenger car and Heavy duty Emission Model (PHEM), which generates instantaneous fuel consumption and emission factors based on the vehicle engine power. The model contains an internal database with more than 1000 measures of vehicles for different drive cycles in both laboratory and on-road tests from the ERMES group (European Research for Mobile Emission Sources).

    The emissions are then interpolated from emission curves containing the normalized engine’s power output and vehicle data to obtain the emission and fuel consumption values. The emission and fuel consumption files contain data for the whole range of normalized power demands, combining several vehicles and emission behaviours into one average vehicle per PHEMlight emission class.The output obtained estimates vehicle fuel consumption and emissions of NOx, PM, CO, HC and NO at a time resolution of 1Hz, for each vehicle, or road segment.

    CLASS car in motion in main road

  • The obstacle detection application develops the required services for warning a driver about general objects and vulnerable road users that may cross the driving path. Exploiting the MASA infrastructure, city cameras and sensors, and data collected from other connected vehicles, the information will be elaborated in real-time to detect the critical situations that may endanger the safety of the drivers and Vulnerable Road Users (VRU).

    The identification of potentially hazardous situations will be enforced at the different levels of the compute continuum, from edge to cloud, with a different precision and latency. The implementation of such a distributed awareness protocol in the monitored area will then enable the communication of potential risks, accidents, obstacles to the drivers, improving driving safety, especially in case of blind spots such as intersections and parking lots.

    CLASS vehicle detecting obstacles in real time