I was catching up on the activity on this blog not long ago, and I read through the awesome thread that Adam started on Industry/Academic collaboration, and it occurred to me that I’ve never seen discussed here one of our industry’s biggest recent trends: the rise of the game schools – the Digipens, the Full Sails, the DeVrys. Even many of the standard 4-year schools are now offering full Game Design and Game Development degrees, or at the very least courses in these areas. Bungie had a recruiting booth at GDC this year – first time we’ve done it – and I think we were all surprised by the number of students coming out of such programs.
I was particularly surprised by the number of visitors we had who cited AI as their main focus of interest. The point was driven home at the AI programmers dinner when one of the Full Sail guys said something to me like “… and of course, everyone wants to do graphics or AI, those are the sexy fields…” Wow, really? When did THAT happen?
Well that’s pretty cool, and I think there are a lot of signs that point to the growing maturity of this academic niche.
I just have one worry: I talked to a lot of students at GDC who cited A*, steering behavior, neural nets, etc. as proof of their AI expertise, but I’m concerned this might point to a case of academic over-fitting. Those things are well and good, but they’re also relatively straightforward, in and of themselves, and very SPECIFIC. If I had to choose between someone with experience with those particular tools of the trade and someone else with a generally stronger math and CS background, I would always choose the latter. Of course no one says you can’t have both, and I’m sure that’s what the game schools are aiming for. And clearly, in the spirit of Adam’s thread, it’s also incumbent on us in the industry to continue to prod the game schools to teach what we need learned.
I would be interested in hearing about other peoples’ more direct relationships to this topic, whether grads who moved from a Game AI-oriented curriculum into the industry (do you think it prepared you appropriately?), industry people who’ve worked with some of those grads (do you see holes in the education they’re getting?), or maybe industry people who are now teaching. Steve Rabin, are you out there?
Post-script: my HIGHLY UNINFORMED IMPRESSION is that animation engineering is an area that is sadly neglected by the game curriculae right now (isn’t good AI is at least 75% good animation, after all?). Does anybody else get that feeling?
We finally got the slides for my GDC talk up on-line in a format other than the ultra-elitist powerpoint 2007:
http://www.bungie.net/images/Inside/publications/presentations/betterbattle.zip
That ZIP file contains a .ppt and .pdf, so take your pick. Unfortunately you get EITHER the correct fonts (pdf) or the correct animations (.ppt) but not both!
In the meantime, I thought I would take this opportunity to give a little more background on the development of the Objectives System.
First of all, the story of Objectives really begins back at GDC 2005, when a couple members of the Bungie design team saw my talk on (among other things) Behavior Trees. Shortly after we had gotten back to Seattle, we started discussing what the replacement for Halo 2 “Orders” (the FSM-based “Imperative” approach described in the talk) would be. I believe the first person to explicitly suggest an adaptation of the Behavior Tree structure was Jaime Griesemer (he tends to be the forgotten half of the classic “Illusion of Intelligence” presentation at GDC 2002 – everyone remembers the Chris Butcher half, but the presentation was by Butcher AND Griesemer!) – he argued that tasks could be decomposed and sequenced in much the same way that behaviors were, and furthermore the tree structure seemed an intuitive representation to him. As no one had any objections, we went ahead with some UI mock-ups, and soon after that, some prototypes (including the “3 Generators” encounter described in the paper, though it unfortunately never made it into the final game).
Let’s be clear about one thing: I didn’t think it would work. Or to be more specific, it was clear that it could be MADE to work from an algorithmic point of view, I just thought the interface as a whole was going to be too complicated for designers to work with. I didn’t think they’d find it an intuitive way to break down the narrative of an encounter, nor did I think it would be particularly easy to inspect what was going on and diagnose problems. Finally, I never thought they would be willing to “abdicate their decision-making authority,” a process that the system more or less demands.
Thankfully I was wrong, and I guess I mention it in order to try to convince you, in case you’re thinking “no way, my designers would never go for that”, that I said the same thing, and maybe your designers WOULD go for it. Granted, that one of the advantages we have at Bungie is a design team that is VERY technically-oriented (we count ex-mechanical engineers and ex-aeronautical engineers among them. Jaime himself is an ex-physicist). Nonetheless, if your designers can learn a scripting language like Lua or Python, they can certainly learn to efficiently use Objectives.
Why DID Objectives work? Certainly some of it comes down to common sense production stuff: we aggressively front-loaded the system schedule-wise, and we invested some real time in the development and refinement of the UI (if you can believe it, the “Orders” system of Halo 2 had NO dedicated UI work done on it – this system was built on top of our generic “tags” interface, akin to a glorified XML viewer). The fact that the system and UI came on-line so early meant we had LOTS of time for iteration, for training designers, and for developing encounters from prototype to ship.
I happen to think that there’s more to it than that. An interface paradigm is generally not going to be very good unless it matches to some degree or another the mental representations inside the user’s brain, so if the designers in the end found the Objectives system useful, it may be because the system matches to some extent the way they already think about structuring coordinated action like a battle. I think, again, you can contrast it with the UNstructured FSM (“imperative”) approach, which is a headache and a mental hurdle once you get above a certain complexity – the lack of structure very quickly starts to work against you.
And certainly, the encounters built by the various designers on our team LOOKED different, Objectively speaking (heh heh). Some of the designers, like Paul Bertone, who built the space in the video shown at the talk, tend to script the AI rather tightly, while others use Objectives as looser guidelines for how the AI should move about a space. Once again, I think it speaks to the expressivity of the system that it allowed various users to adopt their own very different individual styles.
Most of all, I think Objectives are a reasonably elegant example of “transparent decision-making.” The technique is very simple, and yet it is quite expressive AND it never takes more than a few seconds of inspection to answer the question “why are my guys doing THAT?” That’s going to have to be true of ANY AI system which you put into the hands of your designers.
AIIDE'08: The Fourth Conference on Artificial Intelligence
and Interactive Digital Entertainment
October 22-24, 2008
Stanford University, Palo Alto, CA, USA
Submissions deadlines:
Papers and Industry Track abstracts due April 22, 2008
Extended abstracts for demonstrations due May 6, 2008
AIIDE'08 - the Fourth Conference on Artificial Intelligence and Interactive Digital Entertainment - is intended to be the definitive point of interaction between entertainment software developers interested in AI and academic and industrial AI researchers. AIIDE'08 will include invited speakers, research and industry presentations, project demonstrations, and product exhibits. While traditionally emphasizing commercial computer and video games, we invite researchers and developers to share their insights and cutting-edge results on all topics at the interface of entertainment and artificial intelligence, including serious games, entertainment robotics, and beyond. AIIDE'08 is sponsored by the Association for the Advancement of Artificial Intelligence (AAAI).
(more below...)
PAPERS
Because AIIDE'08 crosses disciplinary boundaries, submissions will be evaluated based on their accessibility to both commercial game developers and researchers in addition to their technical merit.
Research Track
Research Track papers describe AI research results that make advances towards solving known game AI problems or enabling a new form of interactive digital entertainment. The novel technique should be validated in a game prototype or test-bed, but need not be validated in a commercial game. Research Track papers are evaluated by the highest standards of academic rigor. The highest rated papers will be presented in short lecture format. We hope to offer the next highest rated group of papers the opportunity to present their work in a poster session. Applicants submit a paper of no more than 6 pages in the AAAI format for blind review (i.e. authors names and affiliations are omitted). All papers will be allocated 6 pages in the proceedings regardless of presentation format.
Industry Track
Individuals that have game development experience but lack the time or need for publishing rigorous academic papers can alternatively apply to the Industry Track. This track will include presentations of AI techniques, issues, or case studies from the perspective of implementing a product in the current commercial environment. Presentation proposals will be evaluated on their potential for conveying clearly elaborated ideas that have not been previously described to an adequate degree. Industry Track applicants submit an extended abstract describing the content of the proposed talk that also includes one paragraph describing their game industry experience. An extended abstract of two pages is sufficient, although any length up to that of a full paper (6 pages) is acceptable. Abstracts will be published in the conference proceedings.
Example Topics (List is Suggestive Only)
- Novel Solutions for Traditional AI Problems (Path planning, animation/camera control, tactical/strategic decision making, terrain analysis, user modeling)
- AI Supporting Novel Game Concepts or Gameplay Elements (Interactive drama, narrative/character development, NPC coordination, NPC belief/attitude/emotion modeling)
- AI Architectures for Games (Automata, scripting, planning, level of detail)
- AI Support for Game Production (Game design, content creation, testing)
- Other Entertainment Applications of AI Technologies (Robotics, natural language processing, reinforcement learning, neural networks, Bayesian networks, genetic algorithms, logic, rule based systems)
- Commercial AI Implementations (Case studies, implementation analysis, comparative evaluations)
Submissions
Electronic submission of papers and extended abstracts is required. All submissions must be in PDF format, no longer than 6 pages including references, and formatted in AAAI two-column, camera-ready style (see the author instructions page at http://www.aaai.org/Publications/Author/author.php). Full submission instructions will be available at the AIIDE web site (www.aiide.org) after March 15, 2008. Research Track papers and Industry Track extended abstracts must be submitted by April 22, 2008. All accepted papers and extended abstracts will be published in the conference proceedings. At least one author must register for the conference by the deadline for camera-ready copy submission. As AIIDE is an academic conference, all attendees including presenters pay a registration fee. AIIDE'08 will not accept any paper that, at the time of submission, is under review for or has already been published or accepted for publication in another journal or conference.
DEMONSTRATIONS
We invite researchers and practitioners to share insights and cutting-edge results from a wide range of topics and encourage the demonstration of a) research systems in the context of existing commercial games, b) new games authored by researchers, c) contributions demonstrating the adoption and/or extension of AI research results published games, and d) completely new forms of interactive digital entertainment made possible by AI research. An electronic submission of a 2-page abstract and demonstration materials is required. Demonstration materials can take the form of a recorded demonstration session, an executable version of the demonstration with written instructions, or a detailed description of the demonstration heavily illustrated with screenshots. Please note that these materials are for review only; it is hoped that all demonstrations will be conducted live at AIIDE'08. Demonstration materials can be submitted electronically by email or FTP up-load. Demonstration authors should submit abstracts and materials by May 6, 2008. Submissions will be judged on technical merit, accessibility to developers and researchers, originality, presentation, and significance. Demonstration abstracts will be published in the conference proceedings.
EXHIBITS
AIIDE'08 will have exhibit space available. Companies, publishers and other groups are encouraged to consider purchasing either a table top display or an exhibit booth. Exhibit space is limited and will be allocated on a first come, first serve basis. Please contact AAAI at aiide08@aaai.org for more information.
IMPORTANT DATES
- March-April: Authors register on the AIIDE web site
- April 22, 2008: Electronic submission of Research/Industry Track papers/abstracts
- May 6, 2008: Electronic submission of extended abstract for a demonstration
- June 11, 2008: Notification of acceptance decision
PUBLICATION
All accepted papers and abstracts will be allocated six (6) pages in the conference proceedings. Up to two (2) additional pages may be used at a cost to the authors of US$ 275 per page. Authors will be required to transfer copyright of their paper to AAAI.
CONFERENCE CHAIR
Michael Mateas
University of California, Santa Cruz
PROGRAM CHAIR
Chris Darken
Naval Postgraduate School
ORGANIZATIONAL COMMITTEE MEMBERS
Ruth Aylett (Heriot-Watt University, UK), Kevin Dill (Mad Doc Software), Richard Evans (Maxis), Ana Paiva (Technical University of Lisbon, Portugal), Michael Youngblood (University of North Carolina, Charlotte), Robert Zubek (Three Rings Design)
For additional information, please see www.aiide.org or email the conference organizers at aiide08@aaai.org .
Hi all,
Just wanted to post an announcement about an upcoming game AI conference. Hope to see you there!
Rob
AIIDE '07 - Artificial Intelligence and Interactive Digital Entertainment
June 6-8, 2007, Stanford University
www.aiide.org
The Third Artificial Intelligence and Interactive Digital Entertainment Conference will be held June 6–8, 2007 at Stanford University, Stanford, California. AIIDE is the premier conference on artificial intelligence in computer games and interactive entertainment. It brings together technical leaders to examine how computer games can be improved using AI technologies, and to promote new approaches and commercial developments.
This year's program includes invited talks from acclaimed game developers and researchers, and numerous presentations about emerging developments in entertainment AI.
Invited Talks:
- Bruce Blumberg - Blue Fang Games
- Wolff Dobson and John Funge - AiLive
- Quinn Dunki - Pandemic Studios
- Richard Evans - Maxis / Electronic Arts
- Chris Hecker - Maxis / Electronic Arts
- Soren Johnson - Firaxis Games
- Peter Molyneux - Lionhead Studios
- Ken Perlin - New York University
- Neil Young - Electronic Arts Los Angeles
- and Chris Bateman - International Hobo
There will also be a full conference technical program with two paper tracks -- Research and Published Games, a workshop on Optimizing Player Satisfaction, and a lively poster/demonstration session.
For more information please consult the following pages:
Announcement page: http://www.aaai.org/Conferences/AIIDE/aiide07.php
Conference program: https://www.aaai.org/Library/AIIDE/aiide07contents.php
Preliminary schedule: http://www.aaai.org/Conferences/AIIDE/2007/aiide07schedule.php
Registration: https://www.aaai.org/Forms/aiide-registration-form.html
Over on GTxA, Andrew Stern writes about the process of creating a new interactive storytelling title called The Party, following their success with Facade. They draw interesting lessons from both the successes and failure modes of the previous title - check it out in this article on the Grand Text Auto blog.
I just got a heads-up from Craig Reynolds about the Sandbox Symposium that's happening this year along with Siggraph 06 in Boston this year. Check it out, people: http://sandboxsymposium.org/.
Heh heh ... sorry if old, but congratulations to Jeff. Looks like Gamespot liked the FEAR AI
Quadruply cool given that all your super-innovative planning stuff is going on in the background! Awesome!
The end of the year upon us, it’s natural for us to look back on the past 12 months and search our souls for an answer to the questions “What was the best game AI of the year?” “What does the trajectory set by 2005 tell us about 2006?” “What titles most influenced the way you think about AI?”
Certainly, it was an interesting year for characters. I can think of two games that had, in one way or another, a novel character technology at the heart of their gameplay experience: God of War (in which character-on-character interaction was made the central mechanic, and which reminded us all how fun vidding a single button can really be) and Shadow of the Colossus. I’m always excited when games explore new character interaction design space, because the AI-space is always correspondingly extended. When we first implemented boarding for Halo2, the next and most logical step was “Now the AI should be able to board you BACK!” And very little (ironically) makes AI look smarter than a canned animation played back at a particularly appropriate time.
Anybody else have any thoughts on this? What AI or character work struck you in 2005?
Now that I'm rolling off of The Suffering: Ties That Bind and have my AIGPW3 article out the door, I figure it's time to make an intro post with obligatory bio:
Before getting into the game industry, I got my MS in CS at the University of Utah, where I once had the pleasure of flipping through Gouraud's and Phong's original dissertations in the library. I was then involved in a financially unsuccessful start-up that resulted in a nonetheless fun shareware game, StixWorld. That led me to Surreal Software where I've been for almost as many years as Duke Nukem Forever has been in development, developing AI for Drakan:OOTF, Drakan:TAG, LOTR:FOTR, The Suffering, and The Suffering: TTB. I presented a paper (slides) on the AI architecture used in FOTR and both Suffering games at the Challenges in Game AI workshop last year.
Now that I have time to start looking towards AI for next-gen consoles, I'm thinking that one of the biggest impacts will be the ability to have so many more characters on screen. On the PS2 and XBox, rendering and animation were enough of a bottleneck that we were limited to a small number of NPCs. But increasing the numbers of NPCs is more than just a quantitative change. As crowd density increases, navigation becomes a fundamentally different problem and any N^2 algorithms we've been using will fall apart. These changes will have effects rippling up into the AI decision making--it will be much less reasonable for an NPC to pick an "unoccupied" position, find a path, and then use simple steering behaviors to get to that exact spot, ignoring any possible crowd movements that might happen in the mean time.
That will keep us busy adapting for next-gen consoles and maybe another generation or two after that, but according to the crowd panic researchers, we're shooting for the fixed target maximum density of 10 people per m^2. Ouch.
I wonder how many scripters Carmack will have to hire then?
hola AImigos,
Thanks for the blog-vitation Damian! I guess my life as a game AI guy has come ironically full circle. Years ago I started reading publications from the Synthetic Characters group at the Media Lab, which influenced how we architected our AI systems for NOLF2, and to a greater degree FEAR. Now I find myself writing for naimad's blog, and heading to the Media Lab myself.
I have a habit of putting my foot in my mouth when someone hands me a microphone, so I can only imagine where blogging will get me. There are already a bunch of interesting threads here that I would like to respond to, but I'm preoccupied at the moment wrapping up work on FEAR, and preparing to move from one end of I-90 to the other (Seattle to Boston). For now I'll just post the obligatory bio.
I've been developing AI systems for games since 1996; most recently at Monolith Productions, where I've had the privilege of working with the team behind NOLF2 and FEAR. My work has focused on developing re-usable, modular architectures to support goal-oriented behavior. My colleague at Monolith, Brian Legge, has made countless improvements to these architectures, and reused them on other games. Lately I've been excited about planning. Inspired by our adventures with chaotic goal-oriented behavior on NOLF2, and some interesting discussions in the Goal Oriented Action Planning (GOAP) group of the AIISC, I decided to take the plunge and implement FEAR's AI with a GOAP system. We hope game players will find that this approach to AI provides a noticeably more dynamic, over the top combat experience. Time will tell...
My decision to head back into academia does not indicate any lack of interest in games. I'd just like to dive into research for a while, and explore solutions to the problems I found most interesting (and challenging) while working on FEAR; communication and coordination within groups of autonomous agents. I'll be joining the Cognitive Machines research group, which aims to create machines that can communicate on human terms.
Meanwhile, I'm glad to see the future of FPS AI tech in the capable hands of smart dudes like Damian, Paul, Brian, and Greg.
Here are the slides for my aiide05 presentation on spatial competence.