On Game AI In The Uncanny Valley

An anonymous reader writes "Normally, the Uncanny Valley theory is used to critique graphical realism in games, but it also applies to AI. Therefore, designer David Hayward examines AI's Uncanny Valley over at Gamasutra, citing games from Valve's Half-Life 2 to the interactive drama Façade." From the article: 'There's a small minority of people who are consistently strange in particular ways... I don't mean to pick on them as a group; nearly all of us dip into such behavior sometimes, perhaps when we're upset, out of sorts, or drunk. Relative and variable as our social skills are, AI is nowhere near such a sophisticated level of interactive ability. It is, however, robotic. Monstrous and sometimes unintentionally comedic; the intersection of broken AI and spooky people is coming.'"

Comments

Interesting article

[nEoN nOoDlE]

I suspect that consultation with and evaluation by psychology departments may become relevant to game AI in the coming years, given that they're the most comprehensive resource in existence on human behavior

I disagree with this. I think in the future, game programmers won't have to go as far as the psychology departments of their nearest schools. They'll just have to walk over to the nearest cubicle and talk to the animators working on the game. As game models have become more and more complex, companies are using more and more motion capture to capture action sequences, but animators (especially good ones) are trained to make a non-living 3d model imitate human behavior. There's over 50 years of research done for animation by animators on how to bring life to drawings and 3d models in motion - which is something that can be directly transferred over into programming terms as opposed to a research paper on a psychological disorder. An animator can tell you when to make a character blink in order for it to appear more realistic; a psychologist, not so much.

btw, IAAA (I am an animator) so I'm slightly biased :)

Re:Interesting article

[dj_tla]

I'm really surprised that your comment was moderated so highly... It may be interesting, but it is incredibly off-topic. Let's not confuse the issue here: the article is about Game AI. Do animators play a big part in creating realistic games? I would argue no. It's easy to get immersed in a well written book, and yet a crappy wooden romantic comedy doesn't pull me in at all. But aren't actors people, providing the most human-like interaction you could hope to achieve through animation? A poorly written script, where characters get in wacky situations and manage to crack a joke at least once a minute just isn't engaging to me because people don't act that way. Game AI could give two shits how nice its graphical representations look, the point (at least for the AI that is discussed in the article) is to make characters behave in a realistic fashion. If I shoot my gloriously animated team-mate in the crotch in "Excellent New FPS Game 3," I want them to turn on me! If they stand there and take it, then I lose that sense of immersion, and any tension I've built up from the realistic ambiance is lost.

So, in response to the quote (I suspect that consultation with and evaluation by psychology departments may become relevant to game AI in the coming years, given that they're the most comprehensive resource in existence on human behavior), yes, psychology will play a large role as we are able to dedicate more computing resources to AI. This isn't conjecture; I and many other researchers are already consulting with psychologists in designing games.

Re:Interesting article

[grumbel]

### Animators know what makes dead 2-D filled shapes feel "human" and likable; if they applied their skills to real people, however, they would make them look dumb, hacked, and repulsive.

A real animator knows what makes a human human-like and given enough time will be able to fix any issues that arise. The issue isn't with animators, its with automated systems like motion capture, since no matter how many reflective dots you glue on an actor, they will always be off by a little bit and that is what gives you uncanny results. When you don't have anybody to fix up the arising problem, its no surprise that they stay unfixed, its really as simple as that.

Re:Uncanny valley... adaptive levels?

[grumbel]

And the most important part about the uncanny valley is that its a myth and not a scientifically verified barrier for technological progress. When animation or 3D models looks uncanny, they look so because nobody who understood their craft fixed them up. Motion capture is a nice thing, but it can't replace an animator and a 3d scanner can't replace a skilled modeler, which is why the 3D scanned Tiger Woods looks creepy and the hand modeled guys in Gears of War look fine.

And btw: There have been studies comparing computer generated faces with real ones, the computer generated ones always won. Those faces have been generated by morphing multiple real faces together, so it can be considered a bit of cheating, it however shows that just because something is generated doesn't mean it looks uncanny, even if it gets extremely close to the real thing.

Procedural animation

[PIPBoy3000]

The catch, of course, is that all this animation comes at a pretty huge cost in time. It takes teams of animators countless hours to generate all that animation.

I keep thinking that procedural animation is going to be the next big thing. Instead of rigid animations, we'll see rules governing the position of each limb and how they interact with the world and other characters. It's expensive in terms of CPU processing power, but it allows for a far more natural interaction with the environment. There's a movie of the new Indiana Jones game that shows this off nicely.

My dream, as a hobbyist game developer, is to have animation and text to voice systems get to the point where I can do a lot of the work myself. As it is, coordinating voice actors and model animation takes a huge chunk of time.

Re:I still call bull

[fractoid]

There is no one-dimension axis measuring likeness to human. It almost certainly differs from person to person, and we may not be able to define it yet in words or symbols, but there must be such an axis for the simple reason that we can define one, and experimentally determine subjects' positions on said axis. A simple test asking a large, random sample of people to rate a number of subjects on a scale of 'lifeless cube'=0 to 'pure believable human'=100 should give you enough data points to get a rough 'normalized humanness' axis. Ask them to crossrate how much they like, or are disturbed by, subjects and you have yourself a scale. Obviously it's affected by ethnicity and cultural background, but for a given domain it is a measurable value.

Oblivion for example was a lot easier to swallow than either, although detail-level-wise it's between [FF:Spirits Within and EQ2]. Detail level does not equate with believable humanity. Spirits Within and EQ2 both had detailed avatars that behaved inhumanly - I haven't seen Oblivion's avatars but I would presume that they were better animated. By the way, your 'reductio ad absurdum' depends in this case on the law of excluded middle, on which topic is noted: In rhetoric, the law of excluded middle is readily misapplied, leading to the formal fallacy of the excluded middle, also known as a false dilemma. [Wikipedia]

You can't take the average and use it as the X axis for an uncanny valley graph, because even if the average is 99% right (hence the whole should be on the right side of the valley), one single detail (e.g., "omg, they're zombies") which can be disturbing on its own. Zombies are disturbing because they look like humans but act inhuman. Mainly, though, they're disturbing because they're frikkin' zombies.

The Undead in WoW are the most disturbing visually, the characters in Spirits Within are uncanny valley too, so something in between should be in the Uncanny Valley too. Yet the Wow humans and elves are considered the races that look good. Undead are generally unattractive, but human females, in particular, weird me out, it's the way they stare. Oddly they're the only race I've played that have defined irises and pupils. Speaking of which, it's damn creepy the way dead humanoid mobs continue to blink occasionally. :S

Anyway this got long and it's hometime. I'll check back. :P

Have you ever BEEN Eliza?

[Moraelin]

I for one can say that Eliza actually improved my social life a lot. You just need to realize that you can do just that in a conversation too.

Are you stuck in a conversation with a zealot ranting about how BSD is better than Linux, or why Gentoo sucks compared to the Gay Penguin distro? Have to listen to someone ranting about what subtle differences make Manowar the greatest band ever, and Metalica just a bunch of soulless sell-outs? Have to nod through as your GF goes on at great lengths as to what should some soap-opera character do, or such? Stuck with a co-worker ranting every single day, for two years straight, about doing the same things in the same fucking CounterStrike map you've never heard of?

Well, ok, so there's the easy "if you don't talk to me ever again, I will refrain from breaking both your legs, cutting your balls with a rusty saw, and shoving them so far up your ass you'll gag" way out, but bear with me anyway ;)

The other way is to realize that you too can go through a whole conversation by just rephrasing what they've said.

Is that guy going on about how "emerge" sucks compared to the "bend-over-and-take-it" script in his favourite Gay Penguin distro? Never fear, just wait for the right moment to feed that bit right back at him. Sooner or later he'll give you some excuse to say, "Yeah, well, that's why emerge sucks compared to bend-over-and-take-it" or "well, duh, with bend-over-and-take-it it would have went much better" right back at him. Do it right, and he'll think he's found the perfect guy, who shares all his opinions to the letter.

Do remember though Eliza has the problem that it does it (A) immediately, and (B) quite unskilled at getting it to be a grammatically-correct sentence, much less one that makes sense. You can do better. For starters, don't feed them their own stuff back immediately. Throw a little delay in the feedback loop. Especially make sure that 10 seconds have elapsed. The short term memory buffer on most humans is 8 seconds, and it's good to have a bit of a margin, just in case.