Game AI Roundup Week #50 2007: 1 Demo, 1 Video, 9 Stories, 1 Job

Alex J. Champandard on December 15, 2007

This Saturday in the build-up to the festive shopping season, there’s an avalanche of interesting Smart Links about game development and artificial intelligence! Feel free to contact me if you have any news or tips for next week.

Remember there’s a mini-blog (RSS) which gets updated with game AI news from the web as it happens!

Quake 2 Bots Lined-Up

Bacteria Inspires Unit AI

Ethan Kennerly has some interesting thoughts about biologically-inspired unit behaviors:

“Imagine tactical artificial intelligence in which independent agents send signals to nearby allies about the presence of an outsider. And they send signals to all agents. These signals offer a proposed group cooperative activity, and the agents seek a quorum, a sufficient agreement among the agents to take a costly behavior that would help the group. The induced behavior might be to gas a massive enemy or bond together into an ad hoc defense barrier.”

A* Pathfinding in a Flash Applet

Claus Topholt has posted a cool demo showing an A* pathfinder written in Flex, Adobe’s programming language for developing Flash applications.

Flex A* (star) Path-finding

Lip Synching Challenge

Gerard Bailly wrote in to announce a challenge in lip synchronization open to game developers:

“LIPS 2008 is the first visual speech synthesis challenge. It will be held as a special session at INTERSPEECH 2008 in Brisbane, Australia. The aim of this challenge is to stimulate discussion about subjective quality assessment of synthesised visual speech with a view to developing standardised evaluation procedures.”

State Machine Hell

Jamie Fristrom points out how traditional low-level languages like C++ aren’t terribly suited to expressing FSMs, or application-level logic in general:

“To me, these state machines are spaghetti code: even less readable than a function laced with gotos. Taking each state and making it a class makes it even worse — now I have to go digging through half a dozen source files to figure out what the code does. I’ve done both many times, of course, and always been mystified by my code later.”

What do you think the solution is? How do you approach the problem?

Turok Lead Level Designer Discusses AI

Not too many technical details, but it’s a well produced video nonetheless!

Military-Level Game AI

A field grade officer notices the progress in commercial game AI for squad and soldier behaviors:

“The off-the-shelf technology and AI [artificial intelligence] behaviors are probably commensurate with what we thought were high-end Army training tools 10 years ago. We were able to train with them just great. Are games perfect? Do they have all of the fidelity in things like logistics? No. But these tools allow us to get to the blocking and tackling in this business.”

Industry/Academic Collaboration

Adam Russel wrote a blog post, from a the industry’s perspective, about the first AI Games Network meeting (posted in last week’s roundup). Julian Togelius wrote a reply from a bit more academic perspective. It’s certainly a useful debate for the community to have, so we’ll focus on it a bit more in next week’s developer discussion.

Reflecting on the AI in Portal & Assassins Creed

Nik discusses the AI in recent AAA hit games:

“Because apart from the chibi turrets, [Portal] does not have ‘traditional’ AI. Instead, what it does have is some great voice acting, simple computerized voice alterations, and writings on the wall. But you still get the sense of agency and livelihood both from the voice and the mysterious, nonexistent other character who leaves behind hints and warnings.”

Junior/Intermediate AI & Gameplay Programmer at Radical Entertainment

I noticed that Radical Entertainment is looking for recent graduates or intermediate programmers in the game industry interested in creating AI & gameplay elements for our next-gen action game. The job has the usual requirements:

  1. From beginning to end, shape gameplay and implement enemy and ambient AI.

  2. Work closely with designers and other gameplay programmers to analyze, design, and implement gameplay systems.

  3. Create AI behaviors that make the game world come alive.

  4. Develop tools and interfaces that allow designers and mission scripters to control and tune gameplay.

If you think you have what it takes, and are willing to move to Vancouver, why not apply?

XNA Game Studio 2.0: Time to Dream-Build-Play Again

Microsoft has got the PR machine running at full steam with the release of their XNA Game Studio 2.0:

“Artificial intelligence is so important to the games we make at Lionhead Studios, and we are very excited to see what the community can come up with in this Warm-Up Challenge to Dream-Build-Play 2008,” said Peter Molyneux, managing director at Lionhead Studios.

Anyone tried it yet?

Student’s AI breakthrough to Revolutionize Game Production?

When mainstream press writes for the masses, it can make any technology sound revolutionary. Here’s the latest such case in game development with AI:

“Cora developed the foundation of a system that would automatically learn to do things like selecting the best animation to play in response to certain player movements. Think of a hockey goalie responding to an approaching player with a different angle for each shot. To achieve this effect, he took some advanced AI algorithms and experimented with ways of attaching them to existing game code so that they could automatically control a wide array of behavioral parameters.”

It’s be interesting to see more details about the research itself…

BattleCode 2008

MIT is running the 2008 BattleCode competition, a challenge in software engineering and artificial intelligence. The objective is to write the best player program for the computer game BattleCode, a real-time strategy game developed for the 6.370 course. It works like this:

  1. Two teams of robots roam the screen managing resources and attacking each other with different kinds of weapons.

  2. However, in BattleCode each robot functions autonomously.

  3. Under the hood it runs a Java virtual machine loaded up with its team’s player program.

  4. Robots in the game communicate by radio and must work together to accomplish their goals.

However, it’s only open to a few universities in the U.S. apparently.

Stay tuned next Saturday for more Smart Links from around the web.

Discussion 0 Comments

If you'd like to add a comment or question on this page, simply log-in to the site. You can create an account from the sign-up page if necessary... It takes less than a minute!