基于GPU的大规模人群疏散模拟*

基于中央处理器(CPU)串行的人群疏散传统方法对于人群规模较少的场景,可以得到良好的疏散模拟效果,但在人群密度较高的场景中,难以达到实时模拟的要求。为了克服上述问题,实现了一种基于图形处理器(GPU)的人群疏散模拟的方法。该方法通过对个体寻径算法的优化,不仅能使个体快速准确地智能寻径,而且将个体寻径独立性与图形处理器高性能计算特性进行结合,充分利用了图形处理器强大的并行计算能力,从而大幅度提高了人群疏散模拟的人群规模,使人群疏散模拟的实时性得到增强。

Large scale crowd evacuation simulation based on GPU

Traditional crowd evacuation serial method which is based on the central processor unit can get a good crowd evacu-ation simulation results for scene with a small scale population. However,it is difficult to achieve real-time simulation require-ments in crowd scene. To solve the problem, this paper proposed a crowd evacuation simulation method based on GPU. Thismethod not only provided individual quickly and accurately intelligent pathfinding, but also combined the independence of indi-vidual pathfinding with high-performance computing of GPU to make full use of powerful parallel computing capability of GPU.Therefore,it could greatly improve the population scale and real-time feature of the crowd evacuation simulation.