Once again, the traditional AI rant session will be a part of the GDC AI Summit. The rants have historically been one of the highest-rated sessions in the Summit and we expect this year to be no exception!

From the GDC site description:

Sometimes things just need to be said. Saying them out loud in a room filled with (hopefully) like-minded people just makes it all the more interesting and cathartic. Seven AI developers – and one AI evangelist designer – from all corners of the industry will deliver quick, to-the-point, and often humorous, rants about what’s on their mind regarding game AI.

This year’s rants will feature Dave Mark (Intrinsic Algorithm), Michael Dawe (Big Huge/38 Studios), Kevin Dill (Lockheed Martin), Brian Schwab (Blizzard), David “Rez” Graham (EA/Maxis), Neil Kirby (Alcatel Lucent), Stéphane Bura (Storybricks), and Mike Treanor (UCSC).

In the 2011 AI Summit, we featured a panel of experienced AI developers discussing some of the non-technical issues that AI developers face. This year, the Summit will have a similarly non-technical panel discussing the “how”, “when”, and “why” of game AI rather than simply the “what”.

This 25-minute panel features four familiar AI veterans Chris Jurney (Double Fine), Dan Kline(Maxis), Kevin Dill (Lockheed Martin), and Rez Graham (EA: Sims Division) and will be moderated by Summit co-adviser, Steve Rabin (Nintendo of America).

From the GDC site description:

It’s easy for AI programmers to look at games and say, “I would have added this” or “they should have fixed that”. However, simply asserting that a game could have had better AI only addresses one issue. There are always other factors to consider. How much would it have cost? What were the schedule pressures? And frankly, where does AI fit in the overall vision for the game? Are there even some games that *gasp* don’t need better AI? This panel will explore these questions and provide some perspective into where AI fits in this vast universe of game development.

David “Rez” Graham, Software Engineer III, Electronic Arts (Sims Division)

Rez is an Artificial Intelligence programmer at Electronic Arts working on The Sims team where he most recently worked on The Sims Medieval and the Pirates & Nobles expansion.  He has worked in the games industry for over 6 years spending most of that time working on various kinds of AI, from platformer enemy AI to full simulation games.  He is the co-author of “Game Coding Complete, 4th Edition” and regularly speaks to colleges and high schools about working in the games industry.

Daniel Kline, Software Engineer, Maxis

Daniel Kline has been an AI and Game Programmer and Designer since 2001. He has shipped 5 titles and developed 10 titles, working with companies such as Activision, Electronic Arts, Blizzard, LucasArts, SquareSoft, and Midway. He was Head AI and Gameplay Engineer on Star Wars: Force Unleashed, AI programmer on Diablo 3, and the engineer and designer of the first two levels of Call of Duty: Finest Hour. He has spent over 5 years doing Interactive Storytelling research, design, programming, and pre-production for 3 different companies and AAA blockbuster titles. He is currently finishing Darkspore at Maxis.

Kevin Dill, Staff Software Engineer, Lockheed Martin Global Training & Logistics

Kevin Dill is a staff software engineer at the Lockheed Martin Advanced Simulation Center. He is a recognized expert on Game AI and a veteran of the game industry, with seven published titles under his belt. He was the technical editor for Introduction to Game AI and Behavioral Mathematics for Game AI, and a section editor for AI Game Programming Wisdom 4. He has taught classes on game development and game AI at Harvard University, Boston University, and Worcester Polytechnic Institute.

Chris Jurney, Lead Programmer, Double Fine Productions

Chris Jurney is a rock and roll experimental lead programmer at Double Fine Productions, with 12 years experience in games and simulation. He has shipped numerous titles in the games industry including Company of Heroes, Dawn of War 2, and Iron Brigade. Chris frequently speaks on the topic of game AI, having presented at GDC 5 times as well as at GDC China, Columbia University, the University of Pennsylvania, aigamedev.com, and various IGDA chapters. He has also written articles published in AI Game Programming Wisdom and frequently modifies his behaviors and routes to avoid the enemy psychics of Galactic Rear Admiral Thoothius Branx.

Steve Rabin, Principal Software Engineer, Nintendo of America

Steve is a principal software engineer at Nintendo of America, where he researches new techniques for Nintendo’s next generation systems, develops tools, and supports Nintendo developers. Before Nintendo, Steve worked primarily as an AI engineer at several Seattle start-ups including Gas Powered Games, WizBang Software Productions, and Surreal Software. He managed and edited the AI Game Programming Wisdom series of books, the book Introduction to Game Development, and has over a dozen articles published in the Game Programming Gems series. He’s spoken at the Game Developers Conference, moderated the AI roundtables, and founded the AI Game Programmers Guild. Steve teaches game AI at both the University of Washington Extension and at the DigiPen Institute of Technology. He earned a BS in computer engineering and an MS in computer science, both from the University of Washington.

This year’s AI Summit takes a look at online games and some of the special challenges that crafting AI for them entails. Two developers — one from the realm of social games and the other from the world of traditional MMOs — share their experiences and solutions.

From the GDC description:

Recently, MMOs and social games have begun pushing the envelope by adding rich AI agents to fill out their human-driven worlds. This movement exposed a new set of challenges. How do you create and manage thousands of simultaneous MMO agents that may interact with tens of thousands of users? And how do you do it in a manner that allows the fast-paced and often iterative release schedule of today’s online games? This lecture will outline the challenges unique to architecting AI for online games, and explain some of the solutions used by Zynga’s CityVille and ArenaNet’s upcoming Guild Wars 2.

Mike Lewis – Senior Server Programmer, ArenaNet Inc.

Mike has spent over a decade in the game development industry as a programmer, working on a diverse range of technical challenges, most often with an AI theme. He has shipped AI in three successful titles for Egosoft GmbH, and is currently a server architecture engineer working on ArenaNet’s upcoming MMORPG, Guild Wars 2. Mike has previously lectured at the GDC AI Summit, and volunteers as a forum moderator for one of the web’s largest game development communities.

Rob Zubek – Principal Software Engineer, Zynga

Dr. Robert Zubek is a principal software engineer at Zynga in San Francisco, developing games for social networks, where he forged new games such as CityVille and Roller Coaster Kingdom. Prior to Zynga, he was at Three Rings Design, and Electronic Arts / Maxis; even earlier, he did research in artificial intelligence and robotics. He holds a PhD in computer science from Northwestern University, where he also earned his other CS degrees.

In 2010, Kevin Dill and Dave Mark delivered a lecture on using utility theory in game AI. In this year’s session, “Embracing the Dark Art of Mathematical Modeling in AI” Kevin and Dave dig deeper into the nuts and bolts of how to use those concepts.

From the GDC session description:

Utility-based AI is a widely-used approach, particularly for games with deeper or more complex behavior. While new users may find utility functions complex and intimidating, experienced users see them as a natural and comfortable way to express behavior. In a follow-up of their 2010 lecture, Kevin Dill and Dave Mark will show how simple problems can be laid out quickly and easily using common design patterns. Additionally, they will show how complex situations can make use of utility functions to express more nuanced behavior. They will then walk through real-world examples, showing how they would be expressed in a utility-based architecture.

Kevin Dill - Staff Software Engineer, Lockheed Martin Global Training & Logistics

Kevin Dill is a staff software engineer at the Lockheed Martin Advanced Simulation Center. He is a recognized expert on Game AI and a veteran of the game industry, with seven published titles under his belt. He was the technical editor for “Introduction to Game AI“ and “Behavioral Mathematics for Game AI“, and a section editor for AI Game Programming Wisdom 4. He has taught classes on game development and game AI at Harvard University, Boston University, and Worcester Polytechnic Institute.

Dave Mark – President & Lead Designer, Intrinsic Algorithm

Dave is the President and Lead Designer of Intrinsic Algorithm, an independent game development studio and AI consulting company in Omaha, Nebraska. He is the author of the book “Behavioral Mathematics for Game AI” and is a contributor to the “AI Game Programming Wisdom” and “Game Programming Gems” book series from Charles River Media. Dave is also a founding member of the AI Game Programmers Guild and has spoken at numerous conferences including being a co-advisor for the previous AI Summits at GDC. He continues to further his education by attending the University of Life. He has no plans to graduate any time soon.

The 2011 AI Summit had Dave Mark and Brian Schwab teaming up for the highest rated lecture of year, “Using Randomness in AI: Both Sides of the Coin”. This year, Dave and Brian return with another joint lecture — this time on the application of human psychology to the craft of creating AI for game characters.

From the GDC description:

When dealing with game AI characters, psychology can’t help but come into play. Players process what they see and experience through a filter of expectations. We expect human-like game characters to exhibit human-like traits. A by-product of the quest to improve AI decisions, however, is that characters can begin to “feel” robotic and sterile. This session will begin by showing various psychological biases that we as game players bring to the experience. We will then show how characters can be imbued with simple affects to exploit these expectations in order to seem more “alive” and believable.

Brian Schwab – Senior AI/Gameplay Engineer II, Blizzard Entertainment

Brian, during his 18 years of industry captivity, has made AI systems for many disparate products including educational titles, war simulations, sports games, and everything in between. At last count, he has fixed just over 14,600 bugs so far. He has led teams of 2-15 people, done a ton of design work in addition to his coding, and also wrote the book AI Game Engine Programming, now in its second edition. He was also AI section editor for Game Programming Gems 6 & 7, and has served on the planning council for the AIIDE conference for a while now. He’s currently working at Blizzard Entertainment on an unannounced title.

Dave Mark – President & Lead Designer, Intrinsic Algorithm

Dave is the President and Lead Designer of Intrinsic Algorithm, an independent game development studio and AI consulting company in Omaha, Nebraska. He is the author of the book “Behavioral Mathematics for Game AI” and is a contributor to the “AI Game Programming Wisdom” and “Game Programming Gems” book series from Charles River Media. Dave is also a founding member of the AI Game Programmers Guild and has spoken at numerous conferences including being a co-advisor for the previous AI Summits at GDC. He continues to further his education by attending the University of Life. He has no plans to graduate any time soon.

This year’s GDC AI Summit features a collection of sessions that don’t fit into the “main stream” of game AI. As such, we figured it deserved its own session. Chris Jurney (Double Fine), Michael Robbins (Gas Powered Games) and Ben Sunshine-Hill each bring their own unique gem to the party!

From the GDC description:

In the game industry, AI is typically thought of as a collection of simple tools used to make characters “do things.” This lecture will show three different ways that people have leveraged more esoteric AI techniques in manners not traditionally seen in games. Michael Robbins will show how he successfully used neural networks for tactical decision-making in Supreme Commander 2, Chris Jurney will discuss computer vision tricks for Kinect in Double Fine’s Happy Action Theater, and Ben Sunshine-Hill will explain how to use AI techniques to dynamically adjust level of detail to match what a player is likely to perceive and remember.

Ben Sunshine-Hill, Software Engineer, Havok

Ben Sunshine-Hill is a software engineer at Havok, working on character pathfinding and local steering. Ben recently completed his PhD work at the University of Pennsylvania, designing ways for game characters to switch behavioral techniques in real-time, and for games to exploit players’ limited powers of memory and perception. His dissertation was ultimately titled “Perceptually Driven Simulation” after his original title, “Messing with the Player’s Head for Fun and Profit“, was rejected.

Michael Robbins, Gameplay Engineer, Gas Powered Games

Michael Robbins is a Gameplay Engineer with Gas Powered Games working on everything from UI to AI. He has been working in the industry for a little over two years after being a long time member of Gas Powered Games’ modding community. His most notable work is featured in Supreme Commander 2, released March 2010.

Chris Jurney, Lead Programmer, Double Fine Productions

Chris Jurney is a rock and roll experimental lead programmer at Double Fine Productions, with 12 years experience in games and simulation. He has shipped numerous titles in the games industry including Company of Heroes, Dawn of War 2, and Iron Brigade. Chris frequently speaks on the topic of game AI, having presented at GDC 5 times as well as at GDC China, Columbia University, the University of Pennsylvania, aigamedev.com, and various IGDA chapters. He has also written articles published in AI Game Programming Wisdom and frequently modifies his behaviors and routes to avoid the enemy psychics of Galactic Rear Admiral Thoothius Branx.