CrowdMixer: Multiple Agent Types in Situation-Based Crowd Simulations

Shannon Blyth and Howard J. Hamilton

This paper presents a scalable approach to crowd simulation that can generate complex and varied simulations by using multiple types of individuals in a crowd. Efficiency is attained by using a situation-based approach where an individual agent adopts behaviors according to its situation, which corresponds to a subspace of the universe.


This page is copyrighted by AAAI. All rights reserved. Your use of this site constitutes acceptance of all of AAAI's terms and conditions and privacy policy.