Latest Articles

Synchronizing characters over the network is a difficult challenge. For player avatars, it requires a very responsive approach that . However, this approach isn't very suited to non-player characters as it consumes unnecessary bandwidth and can result in low-quality animation. RESISTANCE 2 in particular uses a different approach to synchronize the AI decisions over a network.

In this masterclass with Ross McIntosh, you'll hear about Insomniac Games' solution to synchronizing game state on multiple machines, and in particular how that affects the bots. Which things need to be payed particular attention to (e.g. animations, goals, behaviors) so they don't break the gameplay experience? What are common mistakes when networking AI systems and how can you address those?

Why not celebrate Valentine this year by inviting your spouse or partner to Paris in June? You'll attend the Game/AI Conference on Thusday 23rd and Friday 24th, then meet up on Saturday and Sunday for some tourism and romantic dinners in one of the most beautiful cities in the world? It's the perfect time of year for that!

Not to mention the fact you'll get the chance to attend the best event worldwide about artificial intelligence in games. (No seriously, don't mention it... Just say: “I'll meet you in Paris for the weekend!”) Last year the event brought together almost 300 developers from around the world, with keynotes from Ken Perlin on procedural animation and from DICE about the AI in the BATTLEFIELD: BAD COMPANY series.

Real-time Tactics (RTT) games are a sub-genre of strategy games where you're assigned a set of units and some reinforcements, and wage war on a battlefield against an enemy. How do you build AI for such games when the emphasis is entirely on unit deployment and maneuvering? What changes when you don't need to worry about base-building or resource gathering?

In this interview with Johan Pfannenstill, Lead Gameplay Programmer at Massive Entertainment, you'll learn everything about the AI in Ubisoft's WORLD IN CONFLICT, the most famous game in the Real-time Tactics genre. You'll find out how the opponent AI is implemented in skirmish mode, what tricks the game engine use to handle efficient line-of-sight and pathfinding calculations, and which approach the AI uses to make its decisions.

When building a racing game, the immersion of the player and the entertainment value of the gameplay is heavily influenced by the believability of the opponent drivers. But how is the AI built to cope with physically-accurate simulated vehicles? Milestone, an Italian developer specializing in racing, is famous among fans for delivering a hyper realistic driving simulations, both in racing cars and superbikes.

In this presentation from the Paris Game/AI Conference 2010, you'll hear Senior Programmer Paolo Maninetti explain the basics of racing AI, in particular the low-level details like steering control and maneuvers such as overtaking and avoidance. You'll also learn how to build automated algorithms that help analyse the track in order to build racing controllers to deal with any racing circuit.

With 2010 starting to fade away in the rear view mirror, there's no better time to announce the winners of this year's AiGameDev.com Awards for Game AI. The games are still fresh in everyone's minds, the votes are in, and everything is set for another year of innovative and fun game AI.

This year's voting was much more predictable than last year, and in fact things went very smoothly. We changed the voting a bit so people don't have to vote against games they haven't played... Most of the winners this year were by a clear margin. Also included is the Editor's Pick that we introduced last year, since it helps shine the spotlight on other games that deserve it.

The first generation of BT editors resembled built-in tree widgets with their attached property editors. Now much richer widgets are used in practice, making it easier for developers and designers to edit behavior trees.

In this masterclass, you'll discover AngryAnt Behave: a behavior tree tool and runtime for the popular Unity platform. Emil Johansen will explain the details behind the implementation, including the integration with the agent API and code generation. You'll also see the editor in action, and find out what nodes and design patterns are most commonly used.

Character animation has been around for almost a century, with applications ranging from short features to full films. Over the decades, animators have developed significant insights into the process... As an AI programmer, this can help you not only improve the quality of your NPCs behaviors and make your gameplay easier to understand too.

In this this masterclass with Steve Gargolinksi, AI Engineer who worked on the ZOO TYCOON series and WORLD OF ZOO, you'll learn about the the concept of "anticipation" in practice. You'll hear about adding an extra level of anticipation in the behavior, and how that affects the design of your high-level AI. Steve will also talk about toolchains and the importance of working with animators, sharing tips on how this can be done best.

Every year, I write an analysis of the past year's trends and break down predictions from 12 months ago to see how accurate they were. Without fail people ask me whether much has happened during the last 12 months in game AI. But after spending a few weeks going through news and events, I always come to the conclusion there's way more than meets the eye! Last year was quite an incredible year for artificial intelligence in games, and this year is living up to those high standards.

As for the predictions themselves, there's always been a certain self-fulfilling aspect to these posts, because we obviously remain very active working on all of these topics at AiGameDev.com throughout the year. However, until recently I under-estimated the influence of the blog and its reach, which turns my thoughtful rambling analyses into occasional points of reference for the community. Rest assured though, I won't let the pressure get to me and I promise to be just as controversial this time around!

Whether you're just getting started with the implementation of your own navigation system, or you're beginning pre-production of a pathfinding heavy title for the first time, you're no doubt blissfully unaware of the precision monsters lucking under your bed obstacle. You may try to convince yourself that floating point (or double) precision will help address the bugs that result from processing your navigation geometry, but chances are those problems will come back to bite you at the worst possible time — unless you have a team of developers that eat floating point precision bugs for breakfast.

The other solution is to use fixed point math! It may seem old school, but when you hear advice from veteran developers still using it regularly in practice should make you think twice at least. At the Paris Game/AI Conference 2010, Thomas Young gave a micro-talk entitled "Detail Issues in Robust Pathfinding" where he digged into the solutions and tricks that PathEngine uses in practice.

NOTE: This in-depth article was made possible thanks to Thomas Young and PathEngine's sponsorship of AiGameDev.com and the Paris Game/AI Conference 2010. Thomas is an active participant in the forums too, so if you have any tricky questions don't hesitate to ask, or consider digging into the PathEngine demo available on the official site.

It's very common to look at animation from the character's requirements, but when you flip the problem around and see it from the perspective of the environment, things change completely. How do you make sure animations line up perfectly with the world? How do you handle transitions in a responsive yet smooth fashion? How do these environmental animations fit into a traditional animation graph?

In this masterclass with Laurent Ancessi, 20-year industry veteran from Electronic Arts, Radical and Naughty Dog, you'll learn how to create great looking animations specifically built for interacting with the world. This includes for example parkour behaviors where the character runs along walls, hangs from a ledge, flips off a ladder, etc. You'll hear about the concept of an Interactive Cinematic Scene and how it integrates with modern animation systems, in order to bring your characters to life in complex environments.

While many established high-level AI middleware companies are apparently focusing on finite state machines, the rest of the industry seems to have converged towards behavior trees. I'm sure you're wondering, why hasn't anyone shifted their focus to BTs or why haven't any new companies taken up the challenge? As of today, that's all changed...

There's now a new startup dedicated to behavior trees, GameBrains, and they've been hard at work on their new middleware product. GameBrains currently has (limited) spaces for a beta program and is interested in partnerships with games companies.

Editor's Note: This feature was sponsored by GameBrains, and the rest of this article was written by the team. You'll find an overview of their system, an introductory video, as well as the CTO's reply to my most challenging questions on the topic!

You may be surprised to hear that not all studios reuse their AI code from one game to another. Low-level systems are increasingly being reused, but when it comes to decision making and game-specific logic, that often gets thrown out. One way to approach this strategically is to update the AI post-release with the next game in mind...

In this 1h30 interview with Mike Robbins, Gameplay Engineer at Gas Powered games, you'll hear about the AI of SUPREME COMMANDER 2 and its many updates since release. As well as learning about all the different systems of the RTS AI, you'll hear how Mike took into account players' feedback, and polished the strategy of the opponents. You'll also discover about the new neural networks that make the decisions for the game's units!