John Funge

Game AI Researcher 

Recent Activities

My YouTube debut featured the first in-depth look at the Wii MotionPlus
working with AiLive's LiveMove 2 software.  AiLive co-created the Wii MotionPlus accessory. The video has been watched over half a million times (a quarter of a million in the first week), it was the YouTube featured gaming video and generated widespread media coverage.  You can even watch a Japanese version!

LiveMove
LiveMove 2 is the latest in the LiveMove series of products.  LiveMove 2 fully supports the Nintendo Wii MotionPlus accessory to do motion tracking and recognition. AiLive, the company I co-founded, co-created the Wii MotionPlus hardware and is offering LiveMove 2 to help game developers take full advantage of its capabilities. LiveMove 2 incorporates all the great features of previous LiveMove products.  It is now even easier to create motion recognizers within minutes simply by showing examples of motions; no coding or scripting required.LiveMove 2
Ian Millington and John Funge. Artificial Intelligence for Games (Second Edition). Morgan Kaufmann, August 2009.

Buy it from Amazon.
cover image
CMPS 146 - Game AI is a course I proposed, designed, developed and taught in my spare time at the University of California Santa Cruz in Spring 2006, Spring 2007 and Fall 2008.
ucsc logo

Contact Information

Netflix                                        
100 Winchester Cir
Los Gatos, CA 95032
USA
Tel: (650) 000-0000
Fax: (650) 000-0000
jfunge at gmail dot com

Biography

jdf imageJohn Funge recently joined Netflix to start and lead the new Game Platforms group.  Previously, John co-founded AiLive (formerly iKuni) and spent nearly ten years helping to create a successful company that is now well known for its pioneering machine learning technology for games.  AiLive co-created the Wii MotionPlus hardware and has established its LiveMove products as the industry standard for automatic motion recognition.  At AiLive John also worked extensively on LiveAI, a real-time behavior capture product that is being used by the former lead game designer of Guitar Hero and Rock Band to create a new genre of game.  John is also an Assistant Adjunct Professor at the University of California, Santa Cruz (UCSC) where he teaches a Game AI course that he proposed, designed and developed.  John also spent time working at Sony Computer Entertainment America's (SCEA) research lab and,  before that, at Intel's Microcomputer Research Lab (MRL).  He received a B.Sc. in Mathematics and Computer Science at King's College London, an M.Sc. in Computation from Oxford University, and a Ph.D. in Computer Science from the University of Toronto.  He holds several patents, is the author of numerous technical papers, and has written three books on Game AI.  Those books most recently include the Second Edition of Artificial Intelligence for Games that John co-authored with Ian Millington.

Past Activities


John Funge. Artificial Intelligence for Computer Games: An Introduction. A K Peters, July 2004.

Buy it from Barnes & Noble or Amazon.
cover image

John Funge.
AI for Games and Animation: A Cognitive Modeling Approach.  A K Peters, 1999 (buy it!).
cover image

John Funge.
Chinese translation of AI for Games and Animation: A Cognitive Modeling Approach. Tsinghua University Press, May 2004.
cover image

John Funge.
Making Them Behave: Cognitive Models for Computer Animation. Ph.D. Thesis, University of Toronto, 1998 (screen optimized PDF, print optimized PDF).
cover image

John Funge.
Representing Knowledge within the Situation Calculus using
Interval-valued Epitemic Fluents
. Journal of Reliable Computing, Kluwer, issue 1, volume 5, 1999 (PDF).
cover image

John Funge, Xiaoyuan Tu, and Demetri Terzopoulos.
Cognitive Modeling: Knowledge, Reasoning and Planning for Intelligent Characters. SIGGRAPH 99, Los Angeles, CA, August 11-13, 1999 (PDF).
cover image

NOTE: The source code for the CML compiler is no longer available as it's pretty old now and I'm not sure how useful it is, or even if it still works. You might have better luck with Golog, which is based on the same ideas but is being actively maintained and updated by the Cognitive Robotics Group.