Autonomous Agent Behavior Through Hierarchical Behavior Trees: A Three.js Implementation of Emergent Survival Dynamics in Virtual Environments
Abstract
This project presents an AI-driven NPC survival simulation built with Three.js and vanilla JavaScript, where autonomous agents manage hunger, thirst, energy, and social needs in a dynamic 3D island environment. The system combines behavior trees, resource management, environmental dynamics, and performance optimizations to demonstrate emergent survival behavior in real time. Both the full scientific article and source code are provided to support reproducibility and further research.
Fields of Study & Subjects
Artificial Intelligence in Games
Psychiatry
Mental Health
Neuroscience
Digital Games and Media
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 28 January 2026
- Language
- EN