With the Dynamic Parking Prediction research project, BMW is demonstrating a solution that will in future be able to shorten the search for vacant on-street parking, particularly in cities. The company plans present a research prototype of this application at TU-Automotive Detroit. The system will be displayed in a BMW i3.
A significant element of the system is BMW’s connected navigation which already supports Real-Time Traffic Information (RTTI), a system created by INRIX that determines congestions and provides alternative routes to the drivers.
BMW has been researching solutions to take the stress out of parking and to reduce the time spent locating a vacant space since 2011. For the purposes of this project, up-to-date digital maps were produced showing all public parking spaces, while several thousand vehicles from a test fleet supplied movement data generated when using these spaces. Data was supplied by fleet vehicles both when leaving a parking space and also when searching for a space. Based on the digital map, the local prediction algorithm and the parking data from the fleet vehicles, the research application calculates current parking options in a given area, for example a particular part of town. This information is then presented on the dashboard display. The number of currently vacant parking spaces and the number of drivers looking for parking are both factored into the calculation. Even when the system is restricted to using data just from the fleet vehicles it achieves reliable results – and prediction accuracy increases in step with the number of vehicles supplying data. In this way Dynamic Parking Prediction will be able to help BMW drivers obtain the information they need to home in on parking areas where fewer other road users are simultaneously searching for parking. This will ease pressure on both drivers and local residents, BMW argues.