A master thesis from Aalborg University
Emergent flocking boid-based crowd behavior through generalization of the system rules in a 3D Reinforcement learning environment with predator satiation and foraging
Author(s)
Term
4. term
Education
Publication year
2020
Submitted on
2020-06-04
Pages
65 pages
Abstract
The purpose of this project was to create an emergent flocking boid-based crowd behavior, through generalization of the system rules, predatory threat and foraging for the virtual crowd. Extensive research was conducted on the topics of flocking boids, prey and predator behaviors in nature and emergent behaviors and self-organizing systems. 3D Reinforcement learning environment was implemented using Unity ML-agents. Finally, evaluation was conducted by comparing two different ML crowd implementations with a flocking boid control environment. The results showed a successful evolving of an emergent crowd behavior from one of the models, using a generalized set of system rules. Despite the suffered hardware limitations, the exhibited results satisfied the problem criteria, as well as providing interesting insights and findings regarding emergent behaviors.
Documents
Colophon: This page is part of the AAU Student Projects portal, which is run by Aalborg University. Here, you can find and download publicly available bachelor's theses and master's projects from across the university dating from 2008 onwards. Student projects from before 2008 are available in printed form at Aalborg University Library.
If you have any questions about AAU Student Projects or the research registration, dissemination and analysis at Aalborg University, please feel free to contact the VBN team. You can also find more information in the AAU Student Projects FAQs.