Controlling Crowd Simulations using Neuro-Evolution

Wang, Sunrise and Gain, James and Nitschke, Geoff (2015) Controlling Crowd Simulations using Neuro-Evolution, Proceedings of Proceedings of the 2015 Annual Conference on Genetic and Evolutionary Computation, 11-15 July 2015, Madrid, Spain.

Full text not available from this repository. (Use alternate locations listed below)


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.

Item Type: Conference paper
Uncontrolled Keywords: Crowd Animation, Neural Networks
Date Deposited: 13 Sep 2016
Last Modified: 10 Oct 2019 15:32

Actions (login required)

View Item View Item