Managing public transport and how to move safely during Phase 2 of the COVID-19 pandemic represents one of the most significant challenges for our country. algoWatt has developed a series of solutions to respond to the need to effectively manage upcoming mobility developments, in compliance with the regulations and directives that will be issued and the safety of citizens.
For the management of flows on urban public transport lines, starting from its eMaaS platform, algoWatt has put in place two different solutions that can be used individually or come together in a third powerful solution consisting of the integrated platform Hybrid Local Public Transport (H-LPT ).
Let’s see in detail what it is.
eMaaS – Urban Safe Bus
Access to collective transport services certainly constitutes one of the phases of the production cycle of the service that will be most affected by precautionary measures and health security control. The goal of this solution is to allow users informed and responsible travel choices, making it possible. for their movements, identification of the less crowded bus, thus contributing to compliance with collective safety parameters.
To this end, algoWatt offers an app intended for users, for:
- Pre-trip: know the flow rates for transport lines and plan the best times to take public transport throughout the day. Based on the choice of the color of the chosen time slot, the information functions relating to the occupation status of the vehicle are shown.
- On-trip: access information relating to the presence of travelers within the vehicles on the various lines and get a real-time overview of the available seats
The system collects and integrates the position and occupation (attendance) data of the vehicle at the previous stop, integrating the data of the passenger counter system for the balance of arrivals and departures. Through the app, it transmits data to the user at the stop which will thus be able to assess the capacity of the vehicles that will travel that route in the next half hour.
The app provides qualitative information on the availability of seats (red, orange, green light) while the passenger counter system allows you to precisely manage the number of seats occupied in real time.
The application uses Deep Learning algorithms to “train” to assess the degree of crowding at the stops and manage the lines of greatest turnout. The interaction is based on statistical data at the main “nodes” relating to ascents and descents from the vehicle in a time range. The algorithm self-learns on the basis of the data it gradually receives and learns to give an increasingly precise estimate.