Route planning represents a major challenge with a substantial impact on safety, economy, and even climate. An ever-growing urban population caused a significant increase in commuting times, therefore, stressing the prominence of e cient realtime route planning. In essence, the goal is to compute the fastest route to reach the target location in a realistic environment where tra c conditions are time-evolving. Consequently, a large volume of tra c data is potentially required and the route continuously updated. We thereby address the re-routing problem to answer questions such as when, how often, and where is re-routing worthwhile. We base our study on a real dataset, comprising the travel times of the road segments of New York, London, and Chicago, collected over three months. By exploiting this dataset, we implement an optimal algorithm, able to mimic ideal predictions of road segment speeds in the network. Thereby, allowing us to compute the lower bound of traveltime to serve as a reference against other routing techniques. Mainly, we quantify the achieved travel-time gain of a static, no re-routing, and continuous re-routing strategies. Surprisingly, we find that tra c conditions are su ciently stable for short time windows, and re-routing a vehicle is very seldom useful when exploiting accurate statistics at departure time. Typically, real-time re-routing should only be triggered during rush hours, for long routes, passing through well-identified road segments.

Many algorithms compute shortest-path queries in mere microseconds on continental-scale networks. Most solutions are, however, tailored to either road or public transit networks in isolation. To fully exploit the transportation infrastructure, multimodal algorithms are sought to compute shortest paths combining various modes of transportation. Nonetheless, current solutions still lack performance to efficiently handle interactive queries under realistic network conditions where traffic jams, public transit cancelations, or delays often occur. We present a multimodal separators–based algorithm (MUSE), a new multimodal algorithm based on graph separators to compute shortest travel time paths. It partitions the network into independent, smaller regions, enabling fast and scalable preprocessing. The partition is common to all modes and independent of traffic conditions so that the preprocessing is only executed once. MUSE relies on a state automaton that describes the sequence of modes to constrain the shortest path during the preprocessing and the online phase. The support of new sequences of mobility modes only requires the preprocessing of the cliques, independently for each partition. We also augment our algorithm with heuristics during the query phase to achieve further speedups with minimal effect on correctness. We provide experimental results on France’s multimodal network containing the pedestrian, road, bicycle, and public transit networks.