Design and Implementation of an Agent-based Crowd Simulation Model for Evacuation of University Buildings Using Python

Guillermo Fernández. (2017). Design and Implementation of an Agent-based Crowd Simulation Model for Evacuation of University Buildings Using Python. Trabajo Fin de Titulación (TFG). ETSI Telecomunicación, Universidad Politécnica de Madrid.

Nowadays we see a lot of news about tragedies involving crowd evacuations, so it is very important study this topic and define effective evacuations protocols. In order to define effective evacuation protocols, understanding disasters and crowd emergency evacuation behaviour is essential. Many studies focus on analyzing different types of behaviors and defining rules to handle crowd in case of evacuation. Therefore we will use these rules and these behaviors to simulate it in real scenarios and make conclusions. To resolve this problem we use Agent-based Social Simulation (ABSS). ABSS consists of social simulations that are based on agent-based modeling, and implemented using artificial agent technologies. Agent-based social simulation is scientific discipline concerned with simulation of social phenomena, using computer-based multiagent models. In these simulations, persons or group of persons are represented by agents. ABSS models the different elements of the social systems using artificial agents, (varying on scale) and placing them in a computer simulated society to observe the behaviors of the agents. From this data it is possible to learn about the reactions of the artificial agents and translate them into the results of non-artificial agents and simulations. This project will consist of simulating a school building through the Mesa platform, with which we will have the most real possible plan of one of the ETSIT buildings. In addition to the use of Mesa, in the simulations the agents (people) will be modelled through Python. The plan created will be the work environment where agents can simulate the evacuation of the building causing agents to try to leave the building as soon as possible. Therefore this project will generate different reports according to the criteria that apply to the simulated scenarios. For example the simplest case would be in which these agents look for the nearest exit or the one that has the least affluence to escape in a satisfactory way. On the other hand also can be made other types of policies as it is that the agents look for to leave in groups, because they are family, team of work, etc... And look out of the building together. It will also take into account that in case of fire the fire is progressing so you will get reliable reports of the different scenarios that arise. These scenarios would be the most basic being possible to implement and analyze other more complex scenarios for further investigation and thus establish certain evacuation protocols to successfully achieve the exit of the building as soon as possible. The project´s objectives are: - Design scenarios and policies. - Implementation scenarios and policies which are previously designed. - Simulate and testing the differents situations we have studied. - Analyze the results of the simulation. - Technical report writing.