ABOUT THE SPEAKER
Torsten Reil - Animating neurobiologist
By coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around.

Why you should listen
From modeling the mayhem of equine combat in Lord of the Rings: Return of the King to animating Liberty City gun battles in Grand Theft Auto IV, Torsten Reil's achievements are all over the map these days. Software that he helped create (with NaturalMotion, the imaging company he co-founded) has revolutionized computer animation of human and animal avatars, giving rise to some of the most breathtakingly real sequences in the virtual world of video games and movies- and along the way given valuable insight into the way human beings move their bodies.

Reil was a neural researcher working on his Masters at Oxford, developing computer simulations of nervous systems based on genetic algorithms-  programs that actually used natural selection to evolve their own means of locomotion. It didn't take long until he realized the commercial potential of these lifelike characters. In 2001 he capitalized on this lucrative adjunct to his research, and cofounded NaturalMotion. Since then the company has produced motion simulation programs like Euphoria and Morpheme, state of the art packages designed to drastically cut the time and expense of game development, and create animated worlds as real as the one outside your front door. Animation and special effects created with Endorphin (NaturalMotion's first animation toolkit) have lent explosive action to films such as Troy and Poseidon, and NaturalMotion's software is also being used by LucasArts in video games such as the hotly anticipated Indiana Jones.

But there are serious applications aside from the big screen and the XBox console: NaturalMotion has also worked under a grant from the British government to study the motion of a cerebral palsy patient, in hopes of finding therapies and surgeries that dovetail with the way her nervous system is functioning.
More profile about the speaker
Torsten Reil | Speaker | TED.com
TED2003

Torsten Reil: Animate characters by evolving them

Filmed:
335,954 views

Torsten Reil talks about how the study of biology can help make natural-looking animated people -- by building a human from the inside out, with bones, muscles and a nervous system. He spoke at TED in 2003; see his work now in GTA4.
- Animating neurobiologist
By coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around. Full bio

Double-click the English transcript below to play the video.

00:15
I'm going to talk about a technology that we're developing at Oxford now,
0
3000
4000
00:19
that we think is going to change the way that
1
7000
3000
00:22
computer games and Hollywood movies are being made.
2
10000
3000
00:26
That technology is simulating humans.
3
14000
3000
00:29
It's simulated humans with a simulated body
4
17000
3000
00:32
and a simulated nervous system to control that body.
5
20000
3000
00:36
Now, before I talk more about that technology,
6
24000
3000
00:39
let's have a quick look at what human characters look like
7
27000
3000
00:42
at the moment in computer games.
8
30000
3000
00:45
This is a clip from a game called "Grand Theft Auto 3."
9
33000
3000
00:48
We already saw that briefly yesterday.
10
36000
2000
00:50
And what you can see is -- it is actually a very good game.
11
38000
3000
00:53
It's one of the most successful games of all time.
12
41000
3000
00:56
But what you'll see is that all the animations in this game are very repetitive.
13
44000
4000
01:00
They pretty much look the same.
14
48000
2000
01:02
I've made him run into a wall here, over and over again.
15
50000
3000
01:05
And you can see he looks always the same.
16
53000
2000
01:07
The reason for that is that these characters
17
55000
3000
01:10
are actually not real characters.
18
58000
2000
01:12
They are a graphical visualization of a character.
19
60000
4000
01:16
To produce these animations, an animator at a studio has to anticipate
20
64000
5000
01:21
what's going to happen in the actual game,
21
69000
3000
01:24
and then has to animate that particular sequence.
22
72000
3000
01:27
So, he or she sits down, animates it, and tries to anticipate what's going to happen,
23
75000
4000
01:31
and then these particular animations are just played back
24
79000
3000
01:34
at appropriate times in the computer game.
25
82000
3000
01:37
Now, the result of that is that you can't have real interactivity.
26
85000
5000
01:42
All you have is animations that are played back
27
90000
3000
01:45
at more or less the appropriate times.
28
93000
2000
01:47
It also means that games aren't really going to be as surprising as they could be,
29
95000
5000
01:52
because you only get out of it, at least in terms of the character,
30
100000
3000
01:55
what you actually put into it.
31
103000
2000
01:57
There's no real emergence there.
32
105000
2000
01:59
And thirdly, as I said, most of the animations are very repetitive because of that.
33
107000
4000
02:03
Now, the only way to get around that
34
111000
2000
02:05
is to actually simulate the human body
35
113000
2000
02:07
and to simulate that bit of the nervous system of the brain that controls that body.
36
115000
5000
02:12
And maybe, if I could have you for a quick demonstration
37
120000
3000
02:15
to show what the difference is --
38
123000
2000
02:17
because, I mean, it's very, very trivial.
39
125000
4000
02:21
If I push Chris a bit, like this, for example, he'll react to it.
40
129000
3000
02:24
If I push him from a different angle, he'll react to it differently,
41
132000
3000
02:27
and that's because he has a physical body,
42
135000
2000
02:29
and because he has the motor skills to control that body.
43
137000
3000
02:32
It's a very trivial thing.
44
140000
2000
02:34
It's not something you get in computer games at the moment, at all.
45
142000
2000
02:36
Thank you very much. Chris Anderson: That's it?
46
144000
2000
02:38
Torsten Reil: That's it, yes.
47
146000
2000
02:40
So, that's what we're trying to simulate --
48
148000
1000
02:41
not Chris specifically, I should say, but humans in general.
49
149000
4000
02:46
Now, we started working on this a while ago at Oxford University,
50
154000
5000
02:51
and we tried to start very simply.
51
159000
2000
02:53
What we tried to do was teach a stick figure how to walk.
52
161000
3000
02:56
That stick figure is physically stimulated. You can see it here on the screen.
53
164000
3000
02:59
So, it's subject to gravity, has joints, etc.
54
167000
3000
03:02
If you just run the simulation, it will just collapse, like this.
55
170000
3000
03:05
The tricky bit is now to put an AI controller in it
56
173000
4000
03:09
that actually makes it work.
57
177000
2000
03:11
And for that, we use the neural network, which we based on
58
179000
3000
03:14
that part of the nervous system that we have in our spine
59
182000
2000
03:16
that controls walking in humans.
60
184000
2000
03:18
It's called the central pattern generator.
61
186000
2000
03:20
So, we simulated that as well, and then the really tricky bit
62
188000
3000
03:23
is to teach that network how to walk.
63
191000
2000
03:25
For that we used artificial evolution -- genetic algorithms.
64
193000
4000
03:29
We heard about those already yesterday,
65
197000
2000
03:31
and I suppose that most of you are familiar with that already.
66
199000
3000
03:34
But, just briefly, the concept is that
67
202000
2000
03:36
you create a large number of different individuals --
68
204000
3000
03:39
neural networks, in this case --
69
207000
2000
03:41
all of which are random at the beginning.
70
209000
2000
03:43
You hook these up -- in this case, to the virtual muscles
71
211000
2000
03:45
of that two-legged creature here --
72
213000
3000
03:48
and hope that it does something interesting.
73
216000
3000
03:51
At the beginning, they're all going to be very boring.
74
219000
2000
03:53
Most of them won't move at all,
75
221000
2000
03:55
but some of them might make a tiny step.
76
223000
2000
03:57
Those are then selected by the algorithm,
77
225000
2000
03:59
reproduced with mutation and recombinations to introduce sex as well.
78
227000
4000
04:03
And you repeat that process over and over again,
79
231000
2000
04:05
until you have something that walks --
80
233000
2000
04:07
in this case, in a straight line, like this.
81
235000
2000
04:09
So that was the idea behind this.
82
237000
2000
04:11
When we started this, I set up the simulation one evening.
83
239000
3000
04:14
It took about three to four hours to run the simulation.
84
242000
3000
04:17
I got up the next morning, went to the computer and looked at the results,
85
245000
4000
04:21
and was hoping for something that walked in a straight line,
86
249000
3000
04:24
like I've just demonstrated,
87
252000
2000
04:26
and this is what I got instead.
88
254000
2000
04:28
(Laughter)
89
256000
10000
04:38
So, it was back to the drawing board for us.
90
266000
3000
04:42
We did get it to work eventually,
91
270000
3000
04:45
after tweaking a bit here and there.
92
273000
2000
04:47
And this is an example of a successful evolutionary run.
93
275000
3000
04:50
So, what you'll see in a moment is a very simple biped
94
278000
3000
04:53
that's learning how to walk using artificial evolution.
95
281000
3000
04:56
At the beginning, it can't walk at all,
96
284000
2000
04:58
but it will get better and better over time.
97
286000
2000
05:02
So, this is the one that can't walk at all.
98
290000
3000
05:05
(Laughter)
99
293000
6000
05:11
Now, after five generations of applying evolutionary process,
100
299000
3000
05:14
the genetic algorithm is getting a tiny bit better.
101
302000
3000
05:17
(Laughter)
102
305000
8000
05:25
Generation 10 and it'll take a few steps more --
103
313000
2000
05:31
still not quite there.
104
319000
2000
05:34
But now, after generation 20, it actually walks in a straight line without falling over.
105
322000
5000
05:40
That was the real breakthrough for us.
106
328000
3000
05:43
It was, academically, quite a challenging project,
107
331000
3000
05:46
and once we had reached that stage, we were quite confident
108
334000
3000
05:49
that we could try and do other things as well with this approach --
109
337000
3000
05:52
actually simulating the body
110
340000
2000
05:54
and simulating that part of the nervous system that controls it.
111
342000
3000
05:57
Now, at this stage, it also became clear that this could be very exciting
112
345000
3000
06:00
for things like computer games or online worlds.
113
348000
3000
06:03
What you see here is the character standing there,
114
351000
2000
06:05
and there's an obstacle that we put in its way.
115
353000
2000
06:07
And what you see is, it's going to fall over the obstacle.
116
355000
5000
06:12
Now, the interesting bit is, if I move the obstacle a tiny bit to the right,
117
360000
3000
06:15
which is what I'm doing now, here,
118
363000
2000
06:17
it will fall over it in a completely different way.
119
365000
4000
06:24
And again, if you move the obstacle a tiny bit, it'll again fall differently.
120
372000
5000
06:29
(Laughter)
121
377000
2000
06:31
Now, what you see, by the way, at the top there,
122
379000
2000
06:33
are some of the neural activations being fed into the virtual muscles.
123
381000
3000
06:36
Okay. That's the video. Thanks.
124
384000
2000
06:38
Now, this might look kind of trivial, but it's actually very important
125
386000
3000
06:41
because this is not something you get at the moment
126
389000
2000
06:43
in any interactive or any virtual worlds.
127
391000
2000
06:48
Now, at this stage, we decided to start a company and move this further,
128
396000
3000
06:51
because obviously this was just a very simple, blocky biped.
129
399000
3000
06:54
What we really wanted was a full human body.
130
402000
2000
06:56
So we started the company.
131
404000
1000
06:57
We hired a team of physicists, software engineers and biologists
132
405000
5000
07:02
to work on this, and the first thing we had to work on
133
410000
3000
07:05
was to create the human body, basically.
134
413000
4000
07:09
It's got to be relatively fast, so you can run it on a normal machine,
135
417000
3000
07:12
but it's got to be accurate enough, so it looks good enough, basically.
136
420000
3000
07:15
So we put quite a bit of biomechanical knowledge into this thing,
137
423000
3000
07:18
and tried to make it as realistic as possible.
138
426000
4000
07:22
What you see here on the screen right now
139
430000
2000
07:24
is a very simple visualization of that body.
140
432000
2000
07:26
I should add that it's very simple to add things like hair, clothes, etc.,
141
434000
4000
07:30
but what we've done here is use a very simple visualization,
142
438000
3000
07:33
so you can concentrate on the movement.
143
441000
2000
07:35
Now, what I'm going to do right now, in a moment,
144
443000
3000
07:38
is just push this character a tiny bit and we'll see what happens.
145
446000
3000
07:46
Nothing really interesting, basically.
146
454000
2000
07:48
It falls over, but it falls over like a rag doll, basically.
147
456000
3000
07:51
The reason for that is that there's no intelligence in it.
148
459000
3000
07:54
It becomes interesting when you put artificial intelligence into it.
149
462000
4000
07:58
So, this character now has motor skills in the upper body --
150
466000
4000
08:02
nothing in the legs yet, in this particular one.
151
470000
2000
08:04
But what it will do -- I'm going to push it again.
152
472000
3000
08:07
It will realize autonomously that it's being pushed.
153
475000
2000
08:09
It's going to stick out its hands.
154
477000
2000
08:11
It's going to turn around into the fall, and try and catch the fall.
155
479000
3000
08:20
So that's what you see here.
156
488000
2000
08:22
Now, it gets really interesting
157
490000
2000
08:24
if you then add the AI for the lower part of the body as well.
158
492000
4000
08:28
So here, we've got the same character.
159
496000
2000
08:30
I'm going to push it a bit harder now,
160
498000
2000
08:32
harder than I just pushed Chris.
161
500000
2000
08:34
But what you'll see is -- it's going to receive a push now from the left.
162
502000
4000
08:41
What you see is it takes steps backwards,
163
509000
2000
08:43
it tries to counter-balance,
164
511000
2000
08:45
it tries to look at the place where it thinks it's going to land.
165
513000
4000
08:49
I'll show you this again.
166
517000
2000
08:51
And then, finally hits the floor.
167
519000
3000
08:55
Now, this becomes really exciting
168
523000
3000
08:58
when you push that character in different directions, again, just as I've done.
169
526000
5000
09:03
That's something that you cannot do right now.
170
531000
4000
09:07
At the moment, you only have empty computer graphics in games.
171
535000
3000
09:10
What this is now is a real simulation. That's what I want to show you now.
172
538000
3000
09:13
So, here's the same character with the same behavior I've just shown you,
173
541000
3000
09:16
but now I'm just going to push it from different directions.
174
544000
2000
09:18
First, starting with a push from the right.
175
546000
2000
09:23
This is all slow motion, by the way, so we can see what's going on.
176
551000
3000
09:26
Now, the angle will have changed a tiny bit,
177
554000
3000
09:29
so you can see that the reaction is different.
178
557000
4000
09:33
Again, a push, now this time from the front.
179
561000
3000
09:37
And you see it falls differently.
180
565000
2000
09:39
And now from the left --
181
567000
2000
09:43
and it falls differently.
182
571000
2000
09:45
That was really exciting for us to see that.
183
573000
2000
09:47
That was the first time we've seen that.
184
575000
2000
09:49
This is the first time the public sees this as well,
185
577000
2000
09:51
because we have been in stealth mode.
186
579000
2000
09:53
I haven't shown this to anybody yet.
187
581000
2000
09:55
Now, just a fun thing:
188
583000
2000
09:57
what happens if you put that character --
189
585000
2000
09:59
this is now a wooden version of it, but it's got the same AI in it --
190
587000
2000
10:01
but if you put that character on a slippery surface, like ice.
191
589000
2000
10:03
We just did that for a laugh, just to see what happens.
192
591000
3000
10:06
(Laughter)
193
594000
1000
10:07
And this is what happens.
194
595000
2000
10:09
(Laughter)
195
597000
3000
10:12
(Applause)
196
600000
3000
10:15
It's nothing we had to do about this.
197
603000
2000
10:17
We just took this character that I just talked about,
198
605000
2000
10:19
put it on a slippery surface, and this is what you get out of it.
199
607000
3000
10:22
And that's a really fascinating thing about this approach.
200
610000
3000
10:26
Now, when we went to film studios and games developers
201
614000
3000
10:29
and showed them that technology, we got a very good response.
202
617000
3000
10:32
And what they said was, the first thing they need immediately is virtual stuntmen.
203
620000
4000
10:36
Because stunts are obviously very dangerous, they're very expensive,
204
624000
4000
10:40
and there are a lot of stunt scenes that you cannot do, obviously,
205
628000
2000
10:42
because you can't really allow the stuntman to be seriously hurt.
206
630000
3000
10:45
So, they wanted to have a digital version of a stuntman
207
633000
3000
10:48
and that's what we've been working on for the past few months.
208
636000
2000
10:50
And that's our first product that we're going to release in a couple of weeks.
209
638000
5000
10:55
So, here are just a few very simple scenes of the guy just being kicked.
210
643000
5000
11:00
That's what people want. That's what we're giving them.
211
648000
2000
11:02
(Laughter)
212
650000
7000
11:09
You can see, it's always reacting.
213
657000
2000
11:11
This is not a dead body. This is a body who basically, in this particular case,
214
659000
4000
11:15
feels the force and tries to protect its head.
215
663000
2000
11:17
Only, I think it's quite a big blow again.
216
665000
2000
11:19
You feel kind of sorry for that thing,
217
667000
2000
11:21
and we've seen it so many times now that
218
669000
2000
11:23
we don't really care any more.
219
671000
2000
11:25
(Laughter)
220
673000
1000
11:26
There are much worse videos than this, by the way, which I have taken out, but ...
221
674000
4000
11:31
Now, here's another one.
222
679000
2000
11:33
What people wanted as a behavior was to have an explosion,
223
681000
4000
11:37
a strong force applied to the character,
224
685000
2000
11:39
and have the character react to it in midair.
225
687000
2000
11:41
So that you don't have a character that looks limp,
226
689000
2000
11:43
but actually a character that you can use in an action film straight away,
227
691000
3000
11:46
that looks kind of alive in midair as well.
228
694000
2000
11:48
So this character is going to be hit by a force,
229
696000
2000
11:50
it's going to realize it's in the air,
230
698000
2000
11:52
and it's going to try and, well,
231
700000
3000
11:55
stick out its arm in the direction where it's landing.
232
703000
2000
11:59
That's one angle; here's another angle.
233
707000
3000
12:02
We now think that the realism we're achieving with this
234
710000
2000
12:04
is good enough to be used in films.
235
712000
2000
12:06
And let's just have a look at a slightly different visualization.
236
714000
3000
12:09
This is something I just got last night
237
717000
2000
12:11
from an animation studio in London, who are using our software
238
719000
3000
12:14
and experimenting with it right now.
239
722000
2000
12:16
So this is exactly the same behavior that you saw,
240
724000
3000
12:19
but in a slightly better rendered version.
241
727000
4000
12:23
So if you look at the character carefully,
242
731000
3000
12:26
you see there are lots of body movements going on,
243
734000
2000
12:28
none of which you have to animate like in the old days.
244
736000
2000
12:30
Animators had to actually animate them.
245
738000
2000
12:32
This is all happening automatically in the simulation.
246
740000
2000
12:34
This is a slightly different angle,
247
742000
2000
12:39
and again a slow motion version of this.
248
747000
2000
12:41
This is incredibly quick. This is happening in real time.
249
749000
4000
12:45
You can run this simulation in real time, in front of your eyes,
250
753000
2000
12:47
change it, if you want to, and you get the animation straight out of it.
251
755000
3000
12:50
At the moment, doing something like this by hand
252
758000
2000
12:52
would take you probably a couple of days.
253
760000
2000
12:55
This is another behavior they requested.
254
763000
3000
12:58
I'm not quite sure why, but we've done it anyway.
255
766000
2000
13:00
It's a very simple behavior that shows you the power of this approach.
256
768000
2000
13:02
In this case, the character's hands
257
770000
2000
13:04
are fixed to a particular point in space,
258
772000
2000
13:06
and all we've told the character to do is to struggle.
259
774000
3000
13:09
And it looks organic. It looks realistic.
260
777000
3000
13:12
You feel kind of sorry for the guy.
261
780000
2000
13:14
It's even worse -- and that is another video I just got last night --
262
782000
3000
13:17
if you render that a bit more realistically.
263
785000
2000
13:23
Now, I'm showing this to you just to show you
264
791000
2000
13:25
how organic it actually can feel, how realistic it can look.
265
793000
2000
13:27
And this is all a physical simulation of the body,
266
795000
3000
13:30
using AI to drive virtual muscles in that body.
267
798000
3000
13:35
Now, one thing which we did for a laugh was
268
803000
3000
13:38
to create a slightly more complex stunt scene,
269
806000
2000
13:40
and one of the most famous stunts is the one where James Bond
270
808000
3000
13:43
jumps off a dam in Switzerland and then is caught by a bungee.
271
811000
4000
13:48
Got a very short clip here.
272
816000
2000
13:54
Yes, you can just about see it here.
273
822000
2000
13:56
In this case, they were using a real stunt man. It was a very dangerous stunt.
274
824000
3000
13:59
It was just voted, I think in the Sunday Times, as one of the most impressive stunts.
275
827000
3000
14:02
Now, we've just tried and -- looked at our character and asked ourselves,
276
830000
3000
14:05
"Can we do that ourselves as well?"
277
833000
2000
14:07
Can we use the physical simulation of the character,
278
835000
2000
14:09
use artificial intelligence,
279
837000
2000
14:11
put that artificial intelligence into the character,
280
839000
2000
14:13
drive virtual muscles, simulate the way he jumps off the dam,
281
841000
4000
14:17
and then skydive afterwards,
282
845000
2000
14:19
and have him caught by a bungee afterwards?
283
847000
2000
14:21
We did that. It took about altogether just two hours,
284
849000
3000
14:24
pretty much, to create the simulation.
285
852000
2000
14:26
And that's what it looks like, here.
286
854000
2000
14:37
Now, this could do with a bit more work. It's still very early stages,
287
865000
3000
14:40
and we pretty much just did this for a laugh,
288
868000
2000
14:42
just to see what we'd get out of it.
289
870000
2000
14:44
But what we found over the past few months
290
872000
2000
14:46
is that this approach -- that we're pretty much standard upon --
291
874000
3000
14:49
is incredibly powerful.
292
877000
2000
14:51
We are ourselves surprised what you actually get out of the simulations.
293
879000
4000
14:55
There's very often very surprising behavior that you didn't predict before.
294
883000
4000
14:59
There's so many things we can do with this right now.
295
887000
2000
15:01
The first thing, as I said, is going to be virtual stuntmen.
296
889000
3000
15:04
Several studios are using this software now to produce virtual stuntmen,
297
892000
4000
15:08
and they're going to hit the screen quite soon, actually,
298
896000
2000
15:10
for some major productions.
299
898000
2000
15:12
The second thing is video games.
300
900000
3000
15:15
With this technology, video games will look different and they will feel very different.
301
903000
4000
15:19
For the first time, you'll have actors that really feel very interactive,
302
907000
3000
15:22
that have real bodies that really react.
303
910000
2000
15:24
I think that's going to be incredibly exciting.
304
912000
3000
15:27
Probably starting with sports games,
305
915000
2000
15:29
which are going to become much more interactive.
306
917000
2000
15:31
But I particularly am really excited
307
919000
1000
15:32
about using this technology in online worlds,
308
920000
3000
15:35
like there, for example, that Tom Melcher has shown us.
309
923000
3000
15:38
The degree of interactivity you're going to get
310
926000
2000
15:40
is totally different, I think, from what you're getting right now.
311
928000
3000
15:44
A third thing we are looking at and very interested in is simulation.
312
932000
4000
15:49
We've been approached by several simulation companies,
313
937000
2000
15:51
but one project we're particularly excited about, which we're starting next month,
314
939000
3000
15:54
is to use our technology -- and in particular, the walking technology --
315
942000
4000
15:58
to help aid surgeons who work on children with cerebral palsy,
316
946000
4000
16:02
to predict the outcome of operations on these children.
317
950000
3000
16:05
As you probably know,
318
953000
2000
16:07
it's very difficult to predict what the outcome of an operation is
319
955000
3000
16:10
if you try and correct the gait.
320
958000
2000
16:12
The classic quote is, I think, it's unpredictable at best,
321
960000
3000
16:15
is what people think right now, is the outcome.
322
963000
3000
16:18
Now, what we want to do with our software is allow our surgeons to have a tool.
323
966000
4000
16:22
We're going to simulate the gait of a particular child
324
970000
3000
16:25
and the surgeon can then work on that simulation
325
973000
3000
16:28
and try out different ways to improve that gait,
326
976000
2000
16:30
before he actually commits to an actual surgery.
327
978000
3000
16:33
That's one project we're particularly excited about,
328
981000
2000
16:35
and that's going to start next month.
329
983000
2000
16:39
Just finally, this is only just the beginning.
330
987000
3000
16:42
We can only do several behaviors right now.
331
990000
2000
16:44
The AI isn't good enough to simulate a full human body.
332
992000
3000
16:47
The body yes, but not all the motor skills that we have.
333
995000
3000
16:50
And, I think, we're only there if we can have something like ballet dancing.
334
998000
3000
16:53
Right now, we don't have that
335
1001000
2000
16:55
but I'm very sure that we will be able to do that at some stage.
336
1003000
2000
16:57
We do have one unintentional dancer actually,
337
1005000
3000
17:00
the last thing I'm going to show you.
338
1008000
2000
17:02
This was an AI contour that was produced and evolved --
339
1010000
3000
17:05
half-evolved, I should say -- to produce balance, basically.
340
1013000
3000
17:08
So, you kick the guy and the guy's supposed to counter-balance.
341
1016000
3000
17:11
That's what we thought was going to come out of this.
342
1019000
3000
17:14
But this is what emerged out of it, in the end.
343
1022000
2000
17:17
(Music)
344
1025000
10000
17:27
Bizarrely, this thing doesn't have a head. I'm not quite sure why.
345
1035000
3000
17:31
So, this was not something we actually put in there.
346
1039000
2000
17:33
He just started to create that dance himself.
347
1041000
4000
17:37
He's actually a better dancer than I am, I have to say.
348
1045000
3000
17:41
And what you see after a while --
349
1049000
2000
17:43
I think he even goes into a climax right at the end.
350
1051000
2000
17:49
And I think -- there you go.
351
1057000
3000
17:52
(Laughter)
352
1060000
2000
17:54
So, that all happened automatically. We didn't put that in there.
353
1062000
2000
17:56
That's just the simulation creating this itself, basically.
354
1064000
3000
17:59
So it's just --
355
1067000
2000
18:01
(Applause)
356
1069000
1000
18:02
Thanks.
357
1070000
2000
18:05
Not quite John Travolta yet, but we're working on that as well,
358
1073000
3000
18:08
so thanks very much for your time.
359
1076000
2000
18:10
Thanks.
360
1078000
1000
18:11
(Applause)
361
1079000
1000
18:12
CA: Incredible. That was really incredible.
362
1080000
2000
18:14
TR: Thanks.
363
1082000
1000

▲Back to top

ABOUT THE SPEAKER
Torsten Reil - Animating neurobiologist
By coding computer simulations with biologically modeled nervous systems, Torsten Reil and his company NaturalMotion breathe life into the animated characters inhabiting the most eye-poppingly realistic games and movies around.

Why you should listen
From modeling the mayhem of equine combat in Lord of the Rings: Return of the King to animating Liberty City gun battles in Grand Theft Auto IV, Torsten Reil's achievements are all over the map these days. Software that he helped create (with NaturalMotion, the imaging company he co-founded) has revolutionized computer animation of human and animal avatars, giving rise to some of the most breathtakingly real sequences in the virtual world of video games and movies- and along the way given valuable insight into the way human beings move their bodies.

Reil was a neural researcher working on his Masters at Oxford, developing computer simulations of nervous systems based on genetic algorithms-  programs that actually used natural selection to evolve their own means of locomotion. It didn't take long until he realized the commercial potential of these lifelike characters. In 2001 he capitalized on this lucrative adjunct to his research, and cofounded NaturalMotion. Since then the company has produced motion simulation programs like Euphoria and Morpheme, state of the art packages designed to drastically cut the time and expense of game development, and create animated worlds as real as the one outside your front door. Animation and special effects created with Endorphin (NaturalMotion's first animation toolkit) have lent explosive action to films such as Troy and Poseidon, and NaturalMotion's software is also being used by LucasArts in video games such as the hotly anticipated Indiana Jones.

But there are serious applications aside from the big screen and the XBox console: NaturalMotion has also worked under a grant from the British government to study the motion of a cerebral palsy patient, in hopes of finding therapies and surgeries that dovetail with the way her nervous system is functioning.
More profile about the speaker
Torsten Reil | Speaker | TED.com