Real-Time Public Transport Delay Prediction for Situation-Aware Routing

Situation-aware route planning gathers increasing interest. The proliferation of various sensor technologies in smart cities allows the incorporation of real-time data and its predictions in the trip planning process. We present a system for individual multi-modal trip planning that incorporates predictions of future public transport delays in routing. Future delay times are computed by a Spatio-Temporal-Random-Field based on a stream of current vehicle positions. The conditioning of spatial regression on intermediate predictions of a discrete probabilistic graphical model allows to incorporate historical data, streamed online data and a rich dependency structure at the same time. We demonstrate the system with a real-world use-case at Warsaw city, Poland.