Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Evolutionary Algorithms for Optimizing Emergency Exit Placement in Indoor Environments

Carlos Cotta, José E. Gallardo

TL;DR

This work tackles optimizing indoor emergency exit placement to enable rapid, orderly evacuations. It couples a cellular automaton (CA) model of pedestrian flow with two optimization methods: a greedy constructive heuristic and a real-valued Evolutionary Algorithm (EA), including an island-based variant (iEA). The objective $f(\sigma({\cal A},S))$ encodes a hierarchical evacuation goal that prioritizes minimizing $|\xi^-|$ before time $t_i$ or distance $d_i$, with normalization by the diagonal $D=\sqrt{w^2+h^2}$; exits are placed along the perimeter with a fixed width $\omega$ to minimize averaged evacuation performance across multiple scenarios. Experimental results indicate that the island-based EA generally yields the best solutions and outperforms the greedy method, although training data size influences overfitting and generalization to unseen cases. The study demonstrates the viability of global optimization for design decisions in safety-critical evacuations and highlights avenues for scalable, parallel simulations and surrogate-assisted methods.

Abstract

The problem of finding the optimal placement of emergency exits in an indoor environment to facilitate the rapid and orderly evacuation of crowds is addressed in this work. A cellular-automaton model is used to simulate the behavior of pedestrians in such scenarios, taking into account factors such as the environment, the pedestrians themselves, and the interactions among them. A metric is proposed to determine how successful or satisfactory an evacuation was. Subsequently, two metaheuristic algorithms, namely an iterated greedy heuristic and an evolutionary algorithm (EA) are proposed to solve the optimization problem. A comparative analysis shows that the proposed EA is able to find effective solutions for different scenarios, and that an island-based version of it outperforms the other two algorithms in terms of solution quality.

Evolutionary Algorithms for Optimizing Emergency Exit Placement in Indoor Environments

TL;DR

This work tackles optimizing indoor emergency exit placement to enable rapid, orderly evacuations. It couples a cellular automaton (CA) model of pedestrian flow with two optimization methods: a greedy constructive heuristic and a real-valued Evolutionary Algorithm (EA), including an island-based variant (iEA). The objective encodes a hierarchical evacuation goal that prioritizes minimizing before time or distance , with normalization by the diagonal ; exits are placed along the perimeter with a fixed width to minimize averaged evacuation performance across multiple scenarios. Experimental results indicate that the island-based EA generally yields the best solutions and outperforms the greedy method, although training data size influences overfitting and generalization to unseen cases. The study demonstrates the viability of global optimization for design decisions in safety-critical evacuations and highlights avenues for scalable, parallel simulations and surrogate-assisted methods.

Abstract

The problem of finding the optimal placement of emergency exits in an indoor environment to facilitate the rapid and orderly evacuation of crowds is addressed in this work. A cellular-automaton model is used to simulate the behavior of pedestrians in such scenarios, taking into account factors such as the environment, the pedestrians themselves, and the interactions among them. A metric is proposed to determine how successful or satisfactory an evacuation was. Subsequently, two metaheuristic algorithms, namely an iterated greedy heuristic and an evolutionary algorithm (EA) are proposed to solve the optimization problem. A comparative analysis shows that the proposed EA is able to find effective solutions for different scenarios, and that an island-based version of it outperforms the other two algorithms in terms of solution quality.
Paper Structure (11 sections, 9 equations, 2 figures, 2 tables, 2 algorithms)

This paper contains 11 sections, 9 equations, 2 figures, 2 tables, 2 algorithms.

Table of Contents

  1. Introduction
  2. Problem Statement
  3. A CA for modeling pedestrian evacuation
  4. State of the CA
  5. Update Procedure
  6. Transition Function
  7. Algorithms for Emergency Exit Optimization
  8. Experimental Results
  9. Experimental Setup
  10. Results
  11. Conclusions

Figures (2)

  • Figure 1: \ref{['subfig:rank:training']} Rank distribution of the different algorithms on the training set. \ref{['subfig:rank:test']} Rank distribution of the best solution of each algorithm on the test set.
  • Figure 2: Evolution of fitness in three of the instances. \ref{['fig:fitness:low']} low-density \ref{['fig:fitness:mid']} mid-density \ref{['fig:fitness:high']} high-density