Human crowd evacuation framework and analysis using look-ahead-based reinforcement learning algorithm. (2016)

• Record Type: Journal Article
• Authors: Lee, Hyunsoo
• Is Part Of: International journal of the digital human. Volume 1:Number 3(2016)
• Page Start: 248
• Page End: 262
• Publication Date: 2016
• Subjects: human evacuation -- reinforcement learning -- look-ahead estimation -- real-time control -- evacuation control -- crowd modelling -- crowd evacuation -- human crowds -- digital human modelling -- DHM -- exit paths -- emergency management -- emergency evacuation; Human mechanics -- Computer simulation -- Periodicals; Human engineering -- Computer simulation -- Periodicals; Human-computer interaction -- Periodicals; 620.820113
• Languages: English
• ISSNs: 2046-3375

Abstract

Human evacuation framework is one of representative applications using the digital human model. While the early human evacuation frameworks focused on the emergency modelling and evacuation simulation, contemporary evacuation models are evolved as control frameworks which can be used in real-time emergency situations. While many research studies propose several control methods for human evacuation, most of the models ignore the human crowdedness in the emergency situations, comparatively. As the ignorance of the evacuating crowdedness may lead to the more harmful situation, this paper proposes an effective method considering both objectives - the fastest evacuation routes and the crowd-less paths to the exit. In order to generate the shortest paths to the exit, a reinforcement learning approach is provided. The learning method generates candidate directions from current status, and then the less crowded directions are extracted using the proposed look-ahead crowded estimation method. The suggested method can be used as a real-time control algorithm for successful human crowd evacuations.