Practical AI in Unity
summary
Shows working Unity code for HFSM, behavior trees and utility AI with a downloadable project and an Asset Store middleware called Behave. Implements an enum→delegate dictionary (reflection-backed) and coroutine-based state nodes with optional explicit transition objects, demonstrates a parallel node for sniff+walk behavior, and a utility panic value using an AnimationCurve utility scaled by 10 (panic threshold ~0.5). Examples run in Unity and include node data for interruption and reset handling.
AI-written summary · about
chapters (7)
- 0:00Introduction to AI in Unity
- 2:27Hierarchical state machines
- 7:24State machine code patterns
- 16:35Understanding behavior trees
- 26:43Behavior tree implementation
- 30:21Practical utility AI
- 36:13Q&A and closing
related talks
01h 01mThe Forgotten AI of Video Games
59mGame AI 4N00bz
35mHero AI – Gameplay Abilities Meet Behavior Trees
39mEmbarrassing Mistakes: a short story about AI
59mWriting, Rewriting and Re-Rewriting Armello's AI System
20mStudio Speaks: The Reality of AI Adoption in Games
46mMind your NPCs and Q’s: what’s next for Game AI?
01h 03mUnity 101 for C# Developers