Book Overview & Buying
Table Of Contents
Feedback & Rating

Unity Artificial Intelligence Programming

By : Dr. Davide Aversa , Aung Sithu Kyaw, Peters

4.3 (3)

Buy this Book

Unity Artificial Intelligence Programming

4.3 (3)

By: Dr. Davide Aversa , Aung Sithu Kyaw, Peters

Buy this Book

Overview of this book

Developing Artificial Intelligence (AI) for game characters in Unity 2018 has never been easier. Unity provides game and app developers with a variety of tools to implement AI, from the basic techniques to cutting-edge machine learning-powered agents. Leveraging these tools via Unity's API or built-in features allows limitless possibilities when it comes to creating your game's worlds and characters. This fourth edition with Unity will help you break down AI into simple concepts to give you a fundamental understanding of the topic to build upon. Using a variety of examples, the book then takes those concepts and walks you through actual implementations designed to highlight key concepts and features related to game AI in Unity. Further on, you'll learn how to distinguish the state machine pattern and implement one of your own. This is followed by learning how to implement a basic sensory system for your AI agent and coupling it with a Finite State Machine (FSM). Next, you'll learn how to use Unity's built-in NavMesh feature and implement your own A* pathfinding system. You'll then learn how to implement simple ?ocks and crowd dynamics, which are key AI concepts in Unity. Moving on, you'll learn how to implement a behavior tree through a game-focused example. Lastly, you'll apply all the concepts in the book to build a popular game.

Preface

Who this book is for

What this book covers

To get the most out of this book

Get in touch

Free Chapter

Introduction to AI

Artificial Intelligence (AI)

AI in games

AI techniques

Summary

Finite State Machines

The player's tank

The Bullet class

Setting up waypoints

The abstract FSM class

The enemy tank AI

Using an FSM framework

Summary

Randomness and Probability

Randomness in games

Definitions of probability

Character personalities

FSM with probability

Dynamic AI

Demo slot machine

Summary

Further reading

Implementing Sensors

Basic sensory systems

Scene setup

The player's tank and the aspect class

AI characters

Testing

Summary

Flocking

Basic flocking behavior

Alternative implementation

Summary

Path-Following and Steering Behaviors

Following a path

Avoiding obstacles

Summary

A* Pathfinding

Revisiting the A* algorithm

Implementing the A* algorithm

Setting up the scene

Testing the pathfinder

Summary

Navigation Mesh

Setting up the map

Scene with slope

Navigation areas

Off Mesh Links

Summary

Behavior Trees

Introduction to Behavior Trees

Implementing a BT in Unity with Behavior Bricks

Summary

External Resources

Machine Learning in Unity

The Unity Machine Learning Agents Toolkit

How to install the ML-Agents Toolkit

Using the ML-Agents Toolkit – a basic example

Summary

Navigation Mesh

As we have seen in the previous chapter, the most important thing in pathfinding is the scene representation; the AI agents need to know where the obstacles are, especially static obstacles. Previously, we created our custom representation by dividing the map into a 2D grid, and then we implemented our custom pathfinding algorithm by implementing A* on that representation. Would it not be awesome if Unity could do all, that for us?

Fortunately, Unity can do this using NavMeshes. While in our 2D representation we divided the world into perfect squares, with NavMeshes, we divide the world using convex polygons. This representation has two interesting advantages: first, every polygon can be different from the other, and therefore we can use few a polygons for wide open areas and many smaller polygons for very crowded spaces; second, the agent is not locked on a grid...