Paris Game AI Conference 2010

Game AI Conference 2010









El pasado 23 y 24 de Junio de 2010 tuvo lugar la Paris Game AI Conference, el mayor evento sobre Inteligencia Artificial y videojuegos del mundo, reuniendo a mas de 300 programadores, desarrolladores,  diseñadores y productores de videojuegos.

El programa (detallado abajo) contó con la asistencia de eminencias del sector tales como Noah Falstein, Bruce Blumberg, Paulo Maninetti o Ken Perlin.

June 23rd 2010

9:30 -This year in Game AI

Take a journey through the past 12 months in the games industry, and find out where artificial intelligence in becoming a key technology for modern games.

Phil Carlisle (Indie developer at MindFlock Ltd. and veteran programmer on the WORMS franchise) and Alex Champandard.

10:00 – Tales from the Design Trenches

Listen to veteran developers share war stories, their experiences of how design has changed over the years, and horror stories of working with programers.

Stephane Bura (Designer and writer consultant, previously Creative Director at IOTacle Belgium), Noah Falstein (Freelance designer and producer at The Inspirancy, and LucasArts veteran), and Jurie Horneman (Creative Director at mi’pu’mi, formerly designer/producer at Rocktar and Kalisto).

11:15 – Intimate Conversations with Interactive Animated Characters

Find out about the secret recipe that makes the wide variety of animals in WORLD OF ZOO so compelling to watch and interact with.

Bruce Blumberg (Lead Character Engineer at Blue Fang, Associate Professor at MIT)

12:15 – Middleware Megamix

Stay on top of the most recent developements from the leading artificial intelligence companies, and find out what’s coming down the line.

Autodesk, Havok, MASA Group, PathEngine and Spir.Ops.

14:30 – Navigation Loop:Avoid Turning in Circles with Local Navigation

How do you handle obstacle avoidance locally for single characters, as well as local multi-agent coordination? Find out what works and what works and what doesn’t…

Mikko Mononen (Designer/Programmer specializing in AI, previously Lead AI on CRYSIS at Crytek).

15:15 – Crowds and Pedestrians without Bumper Car Syndrome

Creating believable groups and crowds is both an art and science bridging the gap of character animation, pathfinding and behavior. Listen totips and tricks to help bring you up-to speed with recent games and its technology.

Mikko Mononen, Ken Perlin and Jean-Charles Perrier (Lead Programmer at Quantic Dream, developer on HEAVY RAIN and INDIGO PROPHECY).

16:30 Inside Your Player’s Mind

Do you know what your players think about your AI? Hear about an experiment to figure out exactly how people perceive in-game behaviors

Baylor Wetzel (Developer at Shikigami Games, researcher at the University of Minnesota).

17:00 Psychology Profiling in SILENT HILL: SHATTERED MEMORIES

Player modeling is becoming increasingly popular these days. Find out how games can serve different content based monitoring gameplay.

Gwaredd Mountain (Technical Director at Climax Studios, who also worked on the OVERLORD sequels)

17:40 Metrics, Experience Management and AI Directors

As games become more dynamic, keeping statistics about players is increasingly important. Find out how both offline and online games can benefit.

Jurie Horneman, Stephane Bura, and Gwaredd Mountain.

June 24th 2010

9:00 -Physics-based Racing AI in SUPERBIKE 2010 and SUPERSTARS V8

Finding a balance between physics simulation and AI control is alwais difficult. Learn how it’s done in realistic racing games with racing cars and bikes alike.

Paulo Maninetti (Senior Programer at Milestone, previously Game Programer at Ubisoft).

10:45 -The Evolution of BATTLEFIELD: BAD COMPANI’s AI

Discover wath choices helped DICE improve the AI/gameplay from good to great in their most recent franchise.

Mikael Hedberg (Software Engineer at DICE (Electronic Arts), working on the BATTLEFIELD franchise).

11:45- Building Virtual Toys that Don’t Break

Sandbox-style games and non-linear gameplay are becoming increasingly common. But making AI for such games in much harder. What’s the secret?

Bruce Blumberg and Ulf Johansen (Developer at IO Inreractive in Denmark, who worked on HITMAN: BLOOD MONEY).

14:00 – AI Sandbox Multi-threading

Concurrency. Parrallelism. Multi-thhreading. Regardless of what you call it in practice it’s a pain to deal with! You are not alone…

Alex Champandard (Contractor on KILLZONE 2, previously Senior AI Programer at Rockstar, now Technical Director at

14:45 – EVE Online Characters

Social Interactions in games remains a vastly under-explored area. Fid out how the space stations of CCP’s next expansion are going to be populated.

Claudio Pedica (Researcher at Reykjavík University, currently collaborating with CCP Games).

16: 00 – Modern Procedural Animation

As the cost of hand animation and motion capture increase, more developers are turning to procedural techniques to augment their animation systems.

Ken Perlin (Professor at New York University, Chief Tecnology Advisor at ActorMachine).

17:00 – Take Away and Looking Forward

Higlights from the most interesting topics during the conference and an open discusion about what to look out for over the coming months!

Phil Carlisle, Mikko Mononen and William van der Sterren (Consultant at CGF/AI and contractor on SHELLSHOCK:NAM ’67 and KILLZONE I).

Desafortunadamente la organización del congreso nos permitió grabar las conferencias, ya que quieren tener la exclusiva de la documentación del evento en el area PREMIUM (es decir, de pago), de la pagina web oficial del congreso, donde se pueden consultar también los videos de años anteriores.

Computational Creativity Group (CCG)


En el Computational Creativity Group (CCG) of the Department of Computing, Imperial College London, UK.tienen lugar una vez por semana los Computational Bioinformatics Group Seminars. Los dos ultimos que se impartieron estaban directamente relacionados con vidoejuegos.

El 2 de Junio Eurídice Cabañes, presento su proyecto:

Synesthetic computational creativity: A Philosophical Research

We consider that synesthesia can be a good model for computational creativity, first, because if creativity consists of establishing new relationships between old ideas or works, by using synesthesia we can extend these possible relationships. This allows them to be established in different perceptual and conceptual worlds, and thus are not completely random because they follow a pattern and can be modalized. Secondly, if we understand that part of the social validation of an artistic work is related to the feelings that this work produces in the viewer, using synesthesia we can find the relationships between colours, notes, rhythm, forms, etc. and feelings, and for this reason, generate computational creativity systems able to generate specific feelings.
We propose generate a synesthetic creativity program using computer games to harness the synesthetic and aesthetic human potential to make the machine training process a task easier and – why not – more fun.

Y el 9 de Junio, Daniel Ramirez presento:

Player Classification Using a Meta-Clustering Approach

Player classification has recently become a key aspect of game design in areas such as adaptive game systems, player behaviour prediction, player tutoring and non-player character design. Past research has focused on the design of hierarchical, preference-based and probabilistic models aimed at modelling players’ behaviour. We propose a meta-classification approach that breaks the clustering of gameplay mixed data into three levels of analysis. The first level uses dimensionality reduction and partitional clustering of aggregate game data in an action/skill-based classification. The second level applies similarity-based clustering of action sequences to group players according to their preferences. For this we propose a new approach which uses Rubner’s Earth Mover’s Distance (EMD) as a similarity metric to compare histograms of players’ game world explorations. The third level applies a combination of social network analysis metrics, such as shortest path length, to social data to find clusters in the players’ social network. We test our approach in a gameplay dataset from a freely available first-person social hunting game.

Una conferencia basada en el paper escrito por Daniel Ramirez-Cano, Simon Colton y Robin Baumgarten que fue presentado por este ultimo en la CGAT Conference 2010, April 6–7, 2010, Singapore.

La version en pdf
Y el audio.