The Evolution of ARC Raiders EP3 - Building ARC Machines

Hello and welcome to the final video in our series on the development of Arc Raiders. In the previous two episodes,

Raiders. In the previous two episodes, we detailed how Arc Raiders changed from the fast-paced co-op giant machine hunting game to a more intimate and tactical PVPVE

extraction shooter. But the dream of

extraction shooter. But the dream of taking down large intelligent machines never died. In fact, it may be the

never died. In fact, it may be the defining technology pillar of this entire project. I say maybe because for

entire project. I say maybe because for years, Embark has been struggling to wrestle results out of this new tech.

You see, early in Arcador's development, the team at Embark decided to make a gamble on an emerging technology to make machines that would seem to move with intelligence. It's not AI in either the

intelligence. It's not AI in either the traditional gaming sense or in the new generative sense, but rather adopting breakthrough machine learning research in the field of realworld robotics. A

way to allow the machines in this game, both large and small, to move realistically, allowing them to cross complex terrain, to react, fall, and stumble when under enemy fire, to walk,

run, and jump even when one of their limbs has been blown off. I spend a lot of time talking to a lot of smart people to understand how exactly this technology works, the groundbreaking new

game design language it opens up, and frankly, how difficult it is to get any of this to work effectively. But before

we get to any of that, let's first quickly remind ourselves about the machines that populate this world, instruments of the game's antagonist, Ark. We filmed these interviews in 2024,

Ark. We filmed these interviews in 2024, around a year before the game's release date. So much of what the interviewees

date. So much of what the interviewees are talking about has itself changed in the 12 months since. What work is left to do? And how is Arc Raiders likely to

to do? And how is Arc Raiders likely to evolve before it's released?

Internally, we kind of broadly define uh the enemies into aerial enemies and ground enemies just because of how we have to build them and how they behave tends to most cleanly fall into those two categories. And then within those

two categories. And then within those categories, it tends to be like lighter enemies, fodder style enemies that if ignored, they'll hurt you but aren't a tremendous deal to take down up to uh

much heavier enemies that are significant threat to you and take a lot of effort. So on the low end of our

of effort. So on the low end of our aerial enemies, we have the Wasp, which is just a pretty light aerial drone that is somewhat erratic in its movement and has a light uh machine gun and it will pepper you with bullets. And then it

sort of big brother version is the hornet which has significant armor plating which necessitates the player to either use maybe a type of grenade to take it out. They need to flank around behind it and take out its thrusters

which are unarmored. So the rocketeer is an aerial enemy and it's kind of what it sounds like. It's just a very large

sounds like. It's just a very large aerial drone fairly heavily armored and will uh kind of saturate areas of threat with rockets from a distance. So it kind of flushes players out. If you want to just shoot for the center maybe it takes

a few more hits but it's easier to hit.

and each hit will kind of knock it back.

So if it was getting ready to shoot at you, you can kind of throw its aim off just by knocking it a little bit. And

that has always been the case. So

there's always this concept of like a popcorn enemy where it's like you get a lot of them and you kind of they don't take much damage to destroy, but it's like pop pop pop. It feels very satisfying.

>> And then our ground enemies are primarily our answer to uh interior spaces, which again in pile one weren't really a factor. It was a building you would run through at 50 km an hour cuz

our move speed was so high then it didn't matter. Whereas now you are

didn't matter. Whereas now you are slowed down and are interacting with containers and we need a way to present threats to players in interior spaces.

So we've gone through a lot of types uh in that area. But today we have what we just charmingly call the fireball which is basically this metallic sphere that can roll quite easily in interiors and

then it opens up and shoots fire at you.

the the initial need was to have an enemy that was really fast and that could really catch up to players, right?

Like we needed something that would be able to traverse our our world in the game is it's beautiful, but it has quite a lot of complex geometry and you know

there's all of this verticality and all of these slopes and it's it's quite difficult for many ground moving enemies to navigate. So, we were like, "Okay, we

to navigate. So, we were like, "Okay, we need something that can be on the ground, but that can really go after players when they're like swimming around and jumping and bolting and going

with their snap hooks and stuff." And

then we were like, "Oh, wait a second. A

ball.

>> You don't need legs. You don't need wheels. You don't need tracks. Just

wheels. You don't need tracks. Just

roll.

>> It just goes to where it needs to be."

Right.

>> So, we have another one called the tick, which is kind of a creepy little spiderish robot. uh and it can cling the

spiderish robot. uh and it can cling the walls and like hop off of them and it uh will summon other enemies if you get close to them.

So the loot from the AI are the ones that are nicer. So like you find the core from one of the enemies, it's a it's a grenade. There's an enemy that call other enemies, the piece of it does

the same. So you can trap another player

the same. So you can trap another player just like throw the thing and enemies will drop on them. So like we are trying to make you use of the loot that way.

The first step on the journey to realistic machines is creating a world in which physics are accurate. Most

games will animate their characters irrespective of the laws of physics. But

if Embark was going to create a world in which intelligent robots could walk around as they saw fit, they had to ensure that laws like mass and gravity were consistent. That the world of Arc

were consistent. That the world of Arc Raiders was capable of creating emergent moments between player, machine, and environment. Our enemies are fully

environment. Our enemies are fully physicalized. All parts, everything,

physicalized. All parts, everything, they use physics. Uh to an extent that sometimes it's even a challenge because if we really want a drone to do a barrel roll, uh it can't because of their their

weight and the thrusters, all of that is super realistic in the game, right? So,

it's not easy to justify it doing a barrel roll. Uh and all the parts of the

barrel roll. Uh and all the parts of the drones as well can be peeled off and and the drone will actually react to that.

that has a one thrusters left, it's going to try to shoot and that it's going to impact its uh trajectory and all of that.

>> I think it's a choice between control versus emergence really cuz like if you want to be able to say like look at a game like uh Dark Souls or something uh Bloodborne where they have these enemies

that have really specific patterns and it's like they want the player to learn, okay, after 3 seconds it's going to move to the left and then it does this move which takes X amount of time and then something else happens. If you want that

kind of control, you cannot use physics.

>> Cuz a lot of design philosophies, especially with enemy design, are really difficult to pull off when you have this type of systems cuz it's so much about pattern recognition, right? Like you

have an enemy moving in a certain way and like, oh, that's the opening for the attack. I can go in or you as a player

attack. I can go in or you as a player know that like if I do this, I'm going to get this reaction from it and that's going to happen every time. And that's

what games like Dark Souls, like Monster Hunter kind of rely upon. And we had this ambition to have boss fights in that same arena of like Dark Souls,

Monster Hunter, like having all of that compelling pattern recognition. But then

we also realized that well if you knock it in a certain way and the slope is a little bit angled and you know maybe someone else is standing somewhere else and the firing off a grenade then that

is not going to work. You're not going to have the pattern that you thought.

>> Like if you got a big enemy flying in the middle of a pack of smaller drones and you throw a grenade and it explodes and then maybe one of the engines flies off and hits this other one which then like crashes to the side. You get all of this stuff kind of these cinematic

moments that are really memorable and that's not something anyone's designed as such. It's just something that's

as such. It's just something that's happened naturally which is really cool and like we thought it was worth that >> versus having to struggle with okay maybe we don't get to do exactly what we

want all the time but we get these cool memorable moments that can just occur without anyone having planned them.

Getting physics to work for barrels or grenades is one thing. Getting physics

to work for drones with parts that can be blown off is a whole other challenge, but getting physics to work for machines the size of buildings is an entirely different story. This is due to the

different story. This is due to the nature of most game engines and physics simulations. Games are not used to

simulations. Games are not used to calculating mass at that scale, and having enemies weighing thousands of tons creates challenges in how they move and interact within the world. Because

sand in video games isn't sand. It's

geometry, texture, and shaders. Because

rock and dirt doesn't crumble under the weight of heavy things in most games.

>> Inside the simulation, there are just numbers at work here. So the the the the weights of things are there. So you set, you know, this leg weighs 6 tons or, you

know, the center of mass of this robot should be 10,000 kilos or something like that. But to get it to support its own

that. But to get it to support its own weight, you have to uh set um values on how much strength each limb has. And

when you start dealing with like very very insane numbers to try and support the thing, you get behaviors which are sort of uncanny, very very stiff legs that sort of like have a lot of energy,

but they do small little inputs like this against the ground and you get sort of like rigid bounciness happening. And

if you want to dial that down, then you get something that can't support itself and it starts to trip or fall over and this sort of thing. So there's this middle ground, which was really hard to

find to make it look natural, uh, but also give it the power to actually locomote.

>> It is a classic game issue that when you have physics, they are not penetrating each other, right? you have things and it's resting on top of something, you don't get it buried deep beneath, right?

And if we're talking about these big bosses, they would bury themselves into concrete or anything, right? Not just

sand. Um, but we can't really do that in games without a lot of smoke and mirrors.

>> Yeah, it really breaks the illusion when you want to see like an at foot kind of like come towards Luke's speeder and go and that doesn't happen. What happens is

it kind of goes, hey, like this and you're kind of like, huh, thought this thing was supposed to be huge and big, right? It just doesn't sell it. Early in

right? It just doesn't sell it. Early in

the development of Arc Raiders, the team at Embark decided to establish a team to explore the possibility of using groundbreaking research in the field of robotics to enable the enemies to

locomote independently of any preset animations. Decision-making would be

animations. Decision-making would be made using game logic. But how a machine got from A to B would be decided by a brain generated using machine learning.

You know those Boston Dynamics videos where they try and teach a bipeedal robot how to jump up on a box? That's

kind of like what Arc Raiders is trying to do, but instead their robots are way bigger and they have way more legs. And

crucially, they have to be able to do something that traditional games can't.

And that's when you blow off one of those legs, those robots have to be able to adapt. I think uh as I've been told

to adapt. I think uh as I've been told like their their objectives has been much closer to to the same objectives as Boston Dynamics has rather than game

design problems of like literally figuring out how how these machines will navigate with their own vision and like they they had to be physically accurate

also where you put the engines and the down wash and all that has to be accurately they have to be in accurate locations for it to work. What's

exciting and what's still exciting is the fact that using this technology for our locomotion system is the losing limbs

and still it wants to stand up. It it

just opens that door to to the imagination of what is self-preservance like and and how that speaks back to the players to us that when we saw that at

least that is an exciting prospect of a new type of experience that players uh haven't had before. I think they're literally playing against a machine.

>> The ML only did at that point locomotion. So they that was responsible

locomotion. So they that was responsible to make it go from point A to B and that's it. No ML in decision making

that's it. No ML in decision making whatsoever. So it depends a little bit

whatsoever. So it depends a little bit on the model. So some models consume a lot of memory. That is maybe the biggest consideration and some language models and such consume gigabytes of memory. Uh

but this uh locomotion does not consume that much. So I'd say the expensive part

that much. So I'd say the expensive part of ML is the what we call observations and that is uh actually not really ML per se. And that is just how the agents

per se. And that is just how the agents get information about the world. So they

don't see the world the way a player sees it. Of course, they have to if they

sees it. Of course, they have to if they want to see a wall, you have to sort of line trace or to shape cast to see it to detect it. And we need to do a lot of

detect it. And we need to do a lot of those, maybe thousands. Uh so they get a idea of what kind of environment they're in. At least this is the case for

in. At least this is the case for locomotion. The road to getting this

locomotion. The road to getting this locomotion system to work has been long and difficult and it involves several different stakeholders from within the team from animators to technical animators, artists and gameplay

engineers. It also required the studio

engineers. It also required the studio to look outside into the world of research.

>> I did my PhD in in mathematics uh and thought pure mathematics was a bit too dry. So then I found applications and

dry. So then I found applications and and the application I found was applying machine learning to biology. So I worked on on uh her hereditary diseases like u like diabetes and and uh Crohn's disease

and stuff like that and and tried to identify the target genes that were involved with that through machine learning like it's completely revolutionized the field. I think

there's a very soon we will see a Nobel Prize to deep mind Google deep mind for for their work on on biology applications of machine learning like that's the I'm certain of it. Yeah,

really early on we had there was a test where even though the gates so the way it walked was kind of meh, we threw boxes at it. So we were just throwing

these I think there were 100 kg boxes and it just reacted and you know that's when you see holy there's a magic here from an animation perspective I'm used to you know okay how would I break

this down into let's say a sequence of animations that can in this case it would be we can throw a box at this from any angle in any direction in any weight or whatever and I'm thinking of the

animation complexity of well how do I handle arbitrary complexity well then I need to have infinite amount of animations or blending and that it's just a a nightmare which is why you

often see things like you know if I punch you in the shoulder in a video game you just do this cave in animation or you know the can sequence >> and the funny thing with this take I

think is that it's kind of partially ruined animations in other games for me a little bit. So now when I look at other games, I'm like, wait, the the center of gravity is off here. Like this

this this doesn't feel right anymore and it really annoys me.

>> A connoisseur of animation, I hear.

>> But but everything else they do looks so good. Like when they when they walk like

good. Like when they when they walk like on a flat ground like that that's a an authored animation cycle that looks really good and an animator like I want to convey this sense of of weight, this sense of of of menace in this gate or

like this sense of of joy or whatever.

and we just take whatever the robots give us and it looks frequently kind of shitty in comparison to these like Disney walks, right?

>> But on the other hand, when you throw something at it or when it slips or when the ground is not even, our robots do the right stuff >> and their robots are not robots. They

don't do the right stuff. They just like apply some kind of one out of their 20 animations that they have and it doesn't fit.

>> The process of training these brains is complicated. It essentially requires

complicated. It essentially requires somebody to give the brain certain conditions, have it train using those conditions, and then testing the brain in a machine and seeing what it does

right and what it does wrong. An example

of a condition could be if an enemy is far away, run fast to get to them. Or if

a human enemy is firing at you, attempt to jump over them. The core problem with this work is that once one of the brains is baked, you can't simply tweak its behavior. you have to go back to the

behavior. you have to go back to the original conditions, retrain the entire brain, and then test to see if the new brain works better. And this causes a

problem because the solutions that a human might have can be very different to the solutions these robot brains come up with. We found some fun playing

up with. We found some fun playing against the big ML enemies, right? And

the problem was to replicate that fun was very difficult because it's not predictable. It's very hard to just say

predictable. It's very hard to just say do this, right? It doesn't. It It

doesn't follow orders that way. You have

to train it and teach it. And sometimes

it finds weird ways to get to to do things more efficiently, like removing all the legs but two from the ground because that's faster for it, but then it looks silly. It doesn't become an a

menacing enemy that we wanted, right? So

we always had that uh dilemma dealing with ML that is not the predictability part of it.

>> The damn agent learned that if I just shove my foot into the ground really hard faster than the server can keep up, I can use the the penetration to bounce myself. Right?

myself. Right?

>> A typical example was that we like we give it a cookie when it reaches a uh or when it when it moves towards a flag, right? And when it gets to the flag uh

right? And when it gets to the flag uh we move the flag to a new place, right?

At some point in time, it tried to train it like the closer it was to the flag, the bigger the reward it got, got like the better the cookie, right? And what

it learned, of course, was that it runs up to the flag and then stops like with this nose like this close to the damn thing. And it's like I know if I touch

thing. And it's like I know if I touch it, it goes away and stuff starts starts hurting. Like that's much much worse.

hurting. Like that's much much worse.

>> My god.

>> But you're touching something I think has been a huge problem, which is the interaction between game designers and and the ML loop. Like that that's been really hard >> for a long time. I felt like like the

game designers would ask us something and we like we think that's possible.

Let us get back to you. And then 3 months later we'd be like, "Yeah, now we have the storm attack request." And

they're like, "Oh, we worked around that." Now,

that." Now, >> the team at Embark has tackled these issues with a number of solutions. One

being training the brains on actual animation data to help guide their movement, almost like giving the brain a template to work from. And another has been instead of baking one brain for

each machine, giving them multiple brains that focus on specific tasks.

This in particular has proved helpful for both getting the machines to work properly and empowering developers in how they tweak machine behavior. And and

I think it's only fairly recently that we've like managed to get the the the the locomotion components we've been working on predictable and and and um and diverse enough that they get that they feel like they have building blocks

that they can use by themselves instead of like involving us in every every single step. They can be like, okay, I I

single step. They can be like, okay, I I know I have the the stop behavior, I have the patrol behavior, I have the assault behavior, and I have the melee behavior. Now, I can combine these as I

behavior. Now, I can combine these as I want to and and create good game design with it. As you've probably talked

with it. As you've probably talked about, it's very tricky to get ML to do things with extreme intent. And we've

tended to try to ask it to do jobs it's bad at, which is telegraph and attack with precision. So trying to work

with precision. So trying to work through those problems where we've got this thing that walks very competently across complex terrain. How do we turn that into a game that feels satisfying?

like our reinforcement learning and machine learning efforts into locomotion is something that is being used today to some extent maybe not to the full extent that we were hoping as we started um and

that proved to be far more difficult than we expected but we are using it today it's a part of the game and it makes the game feel very different than any other game and that technology will

evolve over time so we were just a little bit too too I think too early with it and and didn't maybe have enough resources and and knowledge to figure it out at the time.

>> I think we are getting to a point now where we are getting more and more comfortable with it. So that's why we want to keep it. Still an ambition.

That's why we always have at least one enemy in the game with it. But it is much more complicated. We just did a new prototype of one big enemy like those

without machine learning with procedural animation and it got the results. As I

said, like you can say just stop there, put the leg here, uh, and and do things like that. It it was much simpler to

like that. It it was much simpler to produce, but we had a couple animators full-time on it for 6 months.

>> So, that's the the the tradeoff there.

>> Arc Raiders is launching into one of the least predictable video game markets ever, where players demand exciting new experiences that they can play with their friends for days, weeks, and months at a time. But this reality

hasn't stopped Embark from taking bold risks when it comes to gameplay or technology. In both Arc Raiders and the

technology. In both Arc Raiders and the finals, it's clear to see how much of a thirst the studio has for evolving any given genre, even if it takes years of experimenting. And while I've been

experimenting. And while I've been embedded in the development of Arc Raiders, it's also been clear to me that they're not scared to tear up lukewarm ideas that don't reach their lofty goals. Time will tell what type of

goals. Time will tell what type of audience Arc Raiders ultimately receives. We produced these videos long

receives. We produced these videos long before the game's release, but one thing is for sure. No matter how Arc Raiders launches in Embark's hands, this game is going to continue to evolve, to take

risks, and to push technology and more importantly gameplay forward.