Shiva Ninjaz!

I have been asked to give a talk at tonight’s “Code Ninja” workshop. Code Ninja is a competition for Galway students involving mobile or web apps/games. So Shiva’s just perfect..

Anyway, here’s my presentation slides (pdf, 1MB).. I hope they’re useful to someone :-)

The talk is only 45 mins long, so there’s no way I’ll get everything covered that I want to, but I figured I might as well make a more complete presentation so it can be useful to people after the event too. I’ll likely have to skim over bits of it.

Pathfinding just like those clever humans..

This paper discusses the use of empirical cost-surfaces derived from substantial amounts of player-traced movements in Darkwind, for the purposes of improving A* pathfinding by AI vehicles. My core ideas are that (i) there are a number of subtle factors related to both effectiveness and aesthetic value, which define optimal routes around the terrains, and that (ii) it may not be feasible to deal with these factors algorithmically. I aim to achieve efficient, believable (‘human-like’) routes which navigate terrain features and surface types sensibly, are safe from collision damage and, where possible, enemy fire.

Since Darkwind is a well established online multiplayer game, it provides substantial amounts of empirical evidence about player-chosen routes. The basic premise is that we have thousands of player-controlled cars travelling around the maps every week, so why not let the computer learn the favourite routes taken by humans?

Draft Paper here (pdf, ~3.5MB)

This is all based on ‘votes’ that I have been gathering in the game for the past 12 months or so.

pheromone trails

Game-On

We’re going to be hosting the academic/industry crossover conference ‘Game On‘ here in Galway this year. My academic colleague Colm asked me to help out on the organising team, which I’m happy to do since I know he’ll run a tight ship and I’ll only need to row in behind him ;-)

It was only really last year that I learned that valid academic research can include computer games – this was somewhat a revelation to me, as it gives me a way to combine my two major interests into a ‘win-win’. Last year I was at a ‘Serious Games’ conference in Portugal, with a PhD student talking about our work with neural networks and image processing in the development of a ‘social agent’ for online communication tools; I also presented a paper at an AI conference in which I talked about the use of Genetic Algorithms in Darkwind to train the computer to drive races more competitively. You can download the research paper here.

This is a win-win I plan to continue with.. I’ll probably put something together about the collaborative ‘virtual whiteboard’ tools in VRCGroups, for the Game On conference itself.