Download Creating Knowledge-rich Interactive 3D Worlds for Better Game AI

Survey
yes no Was this document useful for you?
   Thank you for your participation!

* Your assessment is very important for improving the workof artificial intelligence, which forms the content of this project

Document related concepts

Computer Go wikipedia , lookup

The Talos Principle wikipedia , lookup

Artificial intelligence in video games wikipedia , lookup

Transcript
Creating Knowledge-rich Interactive
3D Worlds for Better Game AI
G. Michael Youngblood, Ph.D.
Assistant Professor of Computer Science
Game Intelligence Group, Games + Learning Lab
UNC Charlotte Game Design & Development Program “The Playground”
ABSTRACT
Current game worlds are visually rich but information poor—particularly poor from the artificial
intelligence (AI) point of view. Where the player sees a rich visual representation of 3D objects,
internally these are just very sparsely described collections of points in space usually defined by
a few basic variables and at best a small state model. Tools for advanced world creation,
character modeling, animation, and advancements in computer graphics have brought us into the
age of near photo-realistic interaction; however, these interactions are still very limited in
comparison to the real world and the information is presented overwhelmingly for the player
packaged for the GPU (Graphics Processing Unit) with little reflection or structure suitable for
use by AI systems. This problem of a lack of rich information suitable for consumption by the
game AI often limits the true potential for deeper levels of interaction that are becoming more indemand by game players.
This talk will present a number of tools and techniques developed by the UNC Charlotte Game
Intelligence Group, which are being used to improve the embedded knowledge contained in
immersive game worlds. Advanced spatial decomposition (DEACCON tool), symbolic
annotation of the environmental elements (KAT tool), calculating the information value of the
surfaces in an interactive environment (HIIVVE tool), and geometric standardization and
analysis (SARGE tool) form the core tools and knowledge generators of our CGUL (Common
Games Understanding and Learning, pronounced “seagull”) Toolkit.
Using these tools to incorporate “knowledge painting” into the game design and development
process can help create knowledge-rich interactive worlds. AI developers can work with these
environmental knowledge elements to improve NPC (Non-Player Character) interactions both
with the player and the environment, enhancing interaction, and leading to new possibilities such
as meaningful in-game learning and agent portability.
SPEAKER BIO
G. Michael Youngblood, Ph.D. is an Assistant Professor in the Department of Computer Science
at The University of North Carolina at Charlotte, Co-director of the Games + Learning Lab, and
head of the Games Intelligence Group. His work studies how artificial agents and real people
interact in virtual environments including computer games and high-fidelity simulations in order
to understand the elements and patterns of learning for the development of better artificial
agents. His research interests are in interactive artificial intelligence, game knowledge and
information structures, and machine and human learning in games.