Pedestrian Flow Optimization to Reduce the Risk of Crowd Disasters Through Human–Robot Interaction

Pedestrian flow in densely populated or congested areas usually presents irregular or turbulent motion state due to competitive behaviors of individual pedestrians, which reduces flow efficiency and raises the risk of crowd accidents. Effective pedestrian flow regulation strategies are highly valuable for flow optimization. Existing studies seek for optimal design of indoor architectural features and spatial placement of pedestrian facilities for the purpose of flow optimization. However, once placed, the stationary facilities are not adaptive to real-time flow changes. In this paper, we investigate the problem of regulating two merging pedestrian flows in a bottleneck area using a mobile robot moving among the pedestrian flows. The pedestrian flows are regulated through dynamic human-robot interaction (HRI) during their collective motion. We adopt an adaptive dynamic programming (ADP) method to learn the optimal motion parameters of the robot in real time, and the resulting outflow through the bottleneck is maximized with the crowd pressure reduced to avoid potential crowd disasters. The proposed algorithm is a data-driven approach that only uses camera observation of pedestrian flows without explicit models of pedestrian dynamics and HRI. Extensive simulation studies are performed in both MATLAB and a robotic simulator to verify the proposed approach and evaluate the performances.

I. Introduction

Modeling and control of pedestrian collective motion behavior have received considerable research interest due to the increasing demand of effective pedestrian flow regulation and evacuation in public areas such as stadiums, shopping malls, and train stations. Without appropriate guidance and regulation, crowd disorder such as blocking [1], and irregular and turbulent pedestrian flow [2], [3] arises when pedestrians aggregate gradually. Particularly, crowd disorder may evolve into crowd accident such as stampedes under emergency circumstances due to competitive behavior of individual pedestrians. Therefore, investigations on pedestrian flow regulation strategies are of great importance for public crowd safety. The focuses of the existing work are primarily on either optimal evacuation planning [1], [4] or optimal architecture design and spatial placement of facilities [5]–[9] based on self-organization behavior of pedestrian collective motion. For instance, the study in [5] suggested that properly placing obstacles in front of an exit could mitigate crowd congestion and thus improves outflow efficiency. However, the optimal design of stationary facilities’ geometry parameters vary with the changes of pedestrian flows [10]. As a result, stationary facilities are not adaptive to real-time changes of pedestrian flows as they may not be easily reconfigurable once being placed.