Authors:
Fadratul Hafinaz Hassan
and
Allan Tucker
Affiliation:
Brunel University West London, United Kingdom
Keyword(s):
Genetic algorithm, Simulated annealing, Hill-climbing, Cellular automata, Pedestrian simulation, Spatial layout.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence
;
Computational Intelligence
;
Evolutionary Art and Design
;
Evolutionary Computing
;
Evolutionary Multiobjective Optimization
;
Genetic Algorithms
;
Informatics in Control, Automation and Robotics
;
Intelligent Control Systems and Optimization
;
Soft Computing
Abstract:
The ease of movement of people inside a public space is highly impacted by the public space layout itself. For example, the flow of a large number of people should be smooth in a well designed public space such as a stadium or hospital. In extreme cases, people might crush to death during emergency evacuations in poorly designed spaces. It is vital that design takes into account the smooth flow of pedestrians. In this paper we describe an initial exploration in using models of pedestrian flow combined with heuristic search to assist in the automatic design for spatial layout. A two-way pedestrian flow system is simulated and heuristic search techniques (genetic algorithm, simulated annealing and hill climbing) are used to find feasible spatial layouts based upon the generated statistics with promising results.