UCT CS Research Document Archive

Controlling Crowd Simulations using Neuro-Evolution

Wang, Sunrise, James Gain and Geoff Nitschke (2015) Controlling Crowd Simulations using Neuro-Evolution. In Proceedings Genetic and Evolutionary Computation Conference (GECCO 2015), pages 353-360, Madrid, Spain.

Full text available as:
PDF - Requires Adobe Acrobat Reader or other PDF viewer.

Abstract

Crowd simulations have become increasingly popular in films over the last decade, appearing in large crowd shots of many big name block-buster films. An important requirement for crowd simulations in films is that they should be directable both at a high and low level. As agent-based techniques allow for low-level directability and more believable crowds, they are typically used in this field. However, due to the bottom-up nature of these techniques, to achieve high level directability, agent-level parameters must be adjusted until the desired crowd behavior emerges. As manually adjusting parameters is a time consuming and tedious process, this paper investigates a method for automating this, using Neuro-Evolution. To this end, the Conventional Neuro-Evolution (CNE), Covariance Matrix Adaptation Evolutionary Strategy (CMA-ES), Neuro-Evolution of Augmenting Topologies (NEAT), and Enforced Sub Populations (ESP) algorithms are compared across a variety of representative crowd simulation scenarios. Overall, it was found that CMA-ES generally performs the best across the selected simulations.

EPrint Type:Conference Paper
Subjects:I Computing Methodologies: I.2 ARTIFICIAL INTELLIGENCE
ID Code:1200
Deposited By:Nitschke, Geoff
Deposited On:23 November 2017