Game AI News

Digesting Duck: Off-Mesh links Progress

Mon, 11 Jan 2010 15:59:29 +0100

Digesting Duck: Off-Mesh links Progress:

I have worked a little towards off-mesh links (a.k.a jump-links). That is, extra annotation other than polygons which act as links in the navigation graph. My long term plan is to support point-to-point and segment-to-segment off-mesh links. The first iteration will only bring you the point-to-point links.

Phil Carlisle on AI in Overgrowth - Wolfire Games Blog

Tue, 05 Jan 2010 21:48:23 +0100

Phil Carlisle on AI in Overgrowth - Wolfire Games Blog:

This is a guest post from Phil Carlisle, best known for his work on the Worms series. He appears from time to time in Wolfire IRC and I finally coaxed him into writing a guest blog post! He will introduce himself below.

Digesting Duck: Stumbling Towards the Holidays

Thu, 24 Dec 2009 02:07:21 +0100

Digesting Duck: Stumbling Towards the Holidays:

After a small hiatus, I’ve been grinding off my to-do list. The first item was to finish the local navigation proto.

Design AI for Your Games: Part 2

Fri, 11 Dec 2009 13:17:59 +0100

Design AI for Your Games: Part 2:

Part 2: Perceptions and Path Finding

Perception equals reality. And in games, the more that can be perceived, the more realistic the experience is… both for the player and for the game entities.

This article discusses the challenges an AI faces in perceiving and navigating a complex environment, and how those challenges can be addressed. Included are examinations of using ray tracing to emulate sight, and how your AI can perceive temporary entities (such as bullet holes, pools of blood and footprints). It then discusses how your AI can navigate the environment, including the use of multi-threading for crashing, turning, and remembering. Includes code samples.

Design AI for Your Games: Part 1

Fri, 11 Dec 2009 13:16:29 +0100

Design AI for Your Games: Part 1:

Part 1: Design and Implementation

Raising the bar of software development has also raised consumers’ expectations. Gamers expect to see each new game become more complex and intelligent, challenging developers to push the envelope. Computer-controlled AI has evolved to accomplish this mammoth task.

In this article, get an architectural overview of the new API for the Intel Media SDK and how it can be used to incorporate AI into game design. Includes the various types of AI systems; the roles AI can play in games; and decision making in simple rules-based systems, finite state machines (FMS), and adaptive AI, which attempts to predict behavior and is key in fighting and strategy games.

Digesting Duck: Obstacle Avoidance Experiments

Mon, 30 Nov 2009 16:27:28 +0100

Digesting Duck: Obstacle Avoidance Experiments:

Today’s experiment was to solve of unfortunate side effect of the sampling method I chose—namely initial collision. If two agents are overlapping, the sampling will always return blocked and the two agent will get stuck. I previously side stepped this problem by just ignoring the initial collision.

ninjaxnagame

Fri, 20 Nov 2009 19:46:55 +0100

ninjaxnagame:

XNA game in C# for a Game AI course at PUC (Rio de Janeiro). A small clip of the game is at: http://www.youtube.com/watch?v=YZMxgLtnzvc. It’s a 2D game that uses simple the concept of Navigation Mesh with AStar for pathfinding. Steering behaviors were also implemented. The game is based on the starter kits and forum from the XNA’s Creator Club.

Start-up studio banks on Xaitment tools | News by Develop

Fri, 13 Nov 2009 16:08:29 +0100

Start-up studio banks on Xaitment tools | News by Develop:

Xaviant, the young development studio based in the US city of Atlanta, is using a number of tools from AI group Xaitment for its debut project.

Here’s a video of the previously discussed obstacle...

Mon, 09 Nov 2009 20:39:54 +0100

Here’s a video of the previously discussed obstacle avoidance scheme. (via Digesting Duck: Obstacle Avoidance Video)

Digesting Duck: Rediscovering Obstacle Avoidance

Mon, 09 Nov 2009 20:38:51 +0100

Digesting Duck: Rediscovering Obstacle Avoidance:

After fiddling around with the different methods to implement velocity obstacles (especially the directive circle style approaches), I noticed that there are two parameters which can be used to tune to get out of the cases where the agent is completely surrounded by the velocity obstacle. The parameters are: desired movement speed and time horizon. Time horizon means the latest potential collision we are interested in avoiding (or reversely, how early something should be avoided).

Digesting Duck: Hybrid Reciprocal Directive Circle

Sat, 07 Nov 2009 01:19:11 +0100

Digesting Duck: Hybrid Reciprocal Directive Circle:

Or HRDC for short. That is my homage to obstacle avoidance scene. The method is combining the good stuff from HRVO with easy of implementation of DC.

Digesting Duck: Making Velocity Selection More Stable

Thu, 05 Nov 2009 16:13:57 +0100

Digesting Duck: Making Velocity Selection More Stable:

I have done a couple of tests the get my velocity obstacle prototype to reduce the flicker in the velocity selection. Here’s a couple of things that seem to work well.

Digesting Duck: Velocity Obstacle Prototype I made a quick...

Fri, 30 Oct 2009 13:30:16 +0100

Digesting Duck: Velocity Obstacle Prototype

I made a quick velocity obstacle prototype last night. Above is video shows of some example scenarios.

Digesting Duck: Not Bumping Into Things

Tue, 27 Oct 2009 14:23:49 +0100

Digesting Duck: Not Bumping Into Things:

Usually when I do research to solve some problem, I get fond of some particular method, try it out, get disappointed because it did not quite solve all my cases, then I try to track back towards the root of the idea to try to figure out what might have been the original motivation behind the solution and try to find a better suiting method from there.

Digesting Duck: Blast from the Past pt. 2

Tue, 13 Oct 2009 22:06:53 +0200

Digesting Duck: Blast from the Past pt. 2:

I was browsing my old hard drive last night while trying to find some old material in preparation for a lecture in a local game dev school. I found a couple of good docs I’ve written in 2006, which I thought would be worth sharing. The grammar in the docs is the same awful you are used when reading this blog.

Digesting Duck: Blast from the Past

Tue, 13 Oct 2009 22:05:11 +0200

Digesting Duck: Blast from the Past:

I just found this nice repository of old from from International Joint Conference on Artificial Intelligence. Lots of good stuff all the way from 1969.

http://dli.iiit.ac.in/ijcai/

Digesting Duck: Status Update

Thu, 08 Oct 2009 03:10:14 +0200

Digesting Duck: Status Update:

I decided to put the area stuff on hold for a while. The update was becoming too heavy, and I need to revise my plan of attack, and probably just simplify few things too

Xaitment almost missed the market

Thu, 01 Oct 2009 20:49:34 +0200

Xaitment almost missed the market:

In a feature looking at the way xaitment is attempting to cater for high-level behaviours and learning with its modular middleware solution, the company’s co-founder has detailed the ups and downs of the German firm’s early history.

Finite State Machines « Game Development Blog

Tue, 22 Sep 2009 21:05:47 +0200

Finite State Machines « Game Development Blog:

I will explain the Finite State Machines concept and I will give an application example. My explanation is based on Chapter 2 of Programming AI By Example book. Thanks Math Buckland for your excellent book. You can download the source code and the executable from here.

NavMesh and Path Finding. There has still been quite a lot of...

Tue, 22 Sep 2009 19:39:10 +0200

NavMesh and Path Finding. There has still been quite a lot of progress on the NavMesh side of things, the editor now has many more features like merging points, splitting edges and nodes plus the big news is that we’ve integrated the Recast NavMesh Builder from Mikko Mononen into Torque, Mikko was Lead AI Programmer for Crysis so he knows a thing or two about AI and the results we’ve been getting from his Recast Library have been a huge bonus to editor we’ve been working on. (via Z-Day - Site, Sound and Errrr A.I. | Andy Rollins | Blogs | Community | GarageGames)