In this project, a digital map is being developed that captures and provides information on GNSS signal propagation – in particular multipath and NLOS errors – in urban environments. AI models are used to interpolate mapped multipath errors at user positions and to predict errors at locations without real training data. The map enables improved weighting of GNSS signals in the receiver, thereby enhancing the accuracy, integrity, and availability of the positioning solution for highly automated vehicles in urban traffic.
The project is being carried out in cooperation with Geo++ GmbH.
