Crowd evacuation simulation method and system combining cultural algorithm and particle swarm optimization algorithm

Abstract

The invention discloses a cultural algorithm and particle swarm algorithm combination-based crowd evacuation simulation method and system. The method comprises the steps of building a three-dimensional model of an evacuation scene and searching for all exits of the evacuation scene; storing a to-be-evacuated crowd in a population space, performing grouping, screening out an individual closest to the position of a corresponding exit in each group as a leading individual of each group, and storing the individual in a belief space; establishing navigation used for associating the belief space with the population space by utilizing a cultural algorithm; transmitting the current position of the leading individual to the navigation, planning a shortest path of reaching the corresponding exit from the current position of the leading individual by the navigation, calculating a next position of the leading individual, and transmitting the next position to the leading individual; and taking the next position given by the navigation as a target, executing a particle swarm algorithm used for following the leading individual, and feeding back the position of the moved leading individual to the navigation: if the leading individual reaches the corresponding exit, re-screening out the leading individual of each group and storing the leading individual in the belief space until no individual exists in each group.

Description

technical field [0001] The invention belongs to the field of crowd evacuation calculation simulation, and in particular relates to a crowd evacuation simulation method and system combining a cultural algorithm and a particle swarm algorithm. Background technique [0002] In recent years, with the rapid development of social economy, various large-scale public activities that gather a large number of people have been increasing, and the safety issues have attracted more and more attention. Crowd evacuation in emergencies is a very complicated process. Organizing personnel to carry out evacuation experiments is highly targeted and obtains a large amount of information, but the cost of experiments and personnel safety issues are unavoidable. Therefore, computer simulation has become the most important method for studying crowd evacuation under emergencies. [0003] Cultural algorithm is a new evolutionary computing framework proposed by Reynolds in 1994. It consists of two par...

AI Technical Summary

Problems solved by technology

[0009] Commonly used crowd evacuation simulation models include macro model and micro model. The macro model treats the evacuated crowd as a whole, and the evacuation speed is fast, but it cannot truly simulate the crowd evacuation movement.

The micro-model needs to do global motion planning for each evacuated individual, and the calculation cost is too large. Due to the large number of evacuated people, the calculation path of each individual is too slow. This kind of micro-model can only be used to deal with small-scale group, and it is difficult to apply in real-time computing environment

Images