Artificial Intelligence in Game Development (Photocopy Edition)

Author: David M. Bourg (USA), Glenn Seemann (USA)
Publisher:
Publish Date: 2005-06-01
Features: Does your game have characters that cannot move freely? Do characters walk into obstacles? Do non-player characters fail to move as a team? Now you can master advanced artificial intelligence (AI) techniques to solve these problems. Whether you are a programming beginner or an experienced game programmer just looking to quickly learn AI, you will find "Artificial Intelligence for Game Developers" to be an excellent introductory book for understanding and applying AI to your games. This book is specifically designed to provide you with advanced and useful AI techniques in game development. If you have ever tried to use AI to extend the lifecycle of your games, make them more challenging, and most importantly, more fun, this book is for you. David M. Bourg (author of the best-selling "Physics for Game Developers") and Glenn Seemann will introduce you to techniques such as finite state machines, fuzzy logic, and neural networks in a very intuitive and easy-to-understand language, with source code (written in C and C++) illustrating these techniques throughout the book. From basic game behaviors like chasing, dodging, pattern-based movement, and grouping to predicting player behavior, this book teaches you how to apply AI to provide believable intelligence for your game characters. These techniques include a mix of deterministic (traditional) and nondeterministic (more recent) AI techniques suitable for beginner AI developers. Other topics include:
Using a single technique based on potential functions to handle problems like chasing, dodging, grouping, and obstacle avoidance.
Solving pathfinding problems using waypoints and the classic A algorithm.
Expanding the functionality of the AI engine with AI scripting to better design and play games.
Giving your game characters rule-based AI reasoning capabilities, including fuzzy logic and finite state machines.
Using probabilistic analysis and advanced techniques like Bayesian reasoning to handle uncertainty problems.