People flow prediction by multi-agent simulator

In places where many people gather, such as large-scale event venues, it is important to prevent crowd ac-cidents from occurring. To that end, we must predict the flows of people and develop remedies before congestion creates a problem. Predicting the movement of a crowd is possible by using a multi-agent simulator, and highly ac-curate prediction can be achieved by reusing past event information to accurately estimate the simulation parameters. However, no such information is available for newly constructed event venues. Therefore, we propose here a method that improves estimation accuracy by utilizing the data measured on the current day. We introduce a people-flow prediction system that incorporates the proposed method. In this paper, we introduce results of an experiment on the developed system that used people flow data measured at an actual concert event. © 2020, Japanese Society for Artificial Intelligence. All rights reserved.