Towards crowd-aware indoor path planning

Indoor venues accommodate many people who collectively form crowds. Such crowds in turn influence people's routing choices, e.g., may prefer to avoid crowded rooms when walking from A B. This paper studies two types of crowd-aware indoor path planning queries. The Crowd-Aware Fastest Path Query (FPQ) finds a with the shortest travel time presence crowds, whereas Least Crowded (LCPQ) encountering least objects en route. To process queries, we design unified framework three major components. First, an crowd model organizes topology and captures object flows between rooms. Second, time-evolving population estimator derives room populations for future timestamp support cost computations query processing. Third, exact approximate processing algorithms each type query. All are based on graph traversal over use same search different strategies updating during process. proposals evaluated experimentally synthetic real data. experimental results demonstrate efficiency scalability our algorithms.