English-Video.net comment policy

The comment field is common to all languages

Let's write in your language and use "Google Translate" together

Please refer to informative community guidelines on TED.com

TEDxStanford

Chris Gerdes: The future race car -- 150mph, and no driver

Filmed
Views 738,087

Autonomous cars are coming -- and they're going to drive better than you. Chris Gerdes reveals how he and his team are developing robotic race cars that can drive at 150 mph while avoiding every possible accident. And yet, in studying the brainwaves of professional racing drivers, Gerdes says he has gained a new appreciation for the instincts of professional drivers

- Mechanical engineer
An autonomous car may seem like a thing of the distant future, but mechanical engineer Chris Gerdes is racing to make it a reality today. Full bio

So, how many of you have ever
00:16
gotten behind the wheel of a car
00:17
when you really shouldn't have been driving?
00:19
Maybe you're out on the road for a long day,
00:25
and you just wanted to get home.
00:27
You were tired, but you felt you could drive a few more miles.
00:28
Maybe you thought,
00:31
I've had less to drink than everybody else,
00:32
I should be the one to go home.
00:34
Or maybe your mind was just entirely elsewhere.
00:36
Does this sound familiar to you?
00:40
Now, in those situations, wouldn't it be great
00:42
if there was a button on your dashboard
00:45
that you could push, and the car would get you home safely?
00:46
Now, that's been the promise of the self-driving car,
00:53
the autonomous vehicle, and it's been the dream
00:55
since at least 1939, when General Motors showcased
00:57
this idea at their Futurama booth at the World's Fair.
01:01
Now, it's been one of those dreams
01:04
that's always seemed about 20 years in the future.
01:06
Now, two weeks ago, that dream took a step forward,
01:10
when the state of Nevada granted Google's self-driving car
01:13
the very first license for an autonomous vehicle,
01:16
clearly establishing that it's legal for them
01:20
to test it on the roads in Nevada.
01:22
Now, California's considering similar legislation,
01:24
and this would make sure that the autonomous car
01:27
is not one of those things that has to stay in Vegas.
01:30
(Laughter)
01:33
Now, in my lab at Stanford, we've been working on
01:35
autonomous cars too, but with a slightly different spin
01:39
on things. You see, we've been developing robotic race cars,
01:42
cars that can actually push themselves to the very limits
01:46
of physical performance.
01:51
Now, why would we want to do such a thing?
01:53
Well, there's two really good reasons for this.
01:55
First, we believe that before people turn over control
01:58
to an autonomous car, that autonomous car should be
02:02
at least as good as the very best human drivers.
02:04
Now, if you're like me, and the other 70 percent of the population
02:08
who know that we are above-average drivers,
02:11
you understand that's a very high bar.
02:13
There's another reason as well.
02:16
Just like race car drivers can use all of the friction
02:19
between the tire and the road,
02:22
all of the car's capabilities to go as fast as possible,
02:24
we want to use all of those capabilities to avoid
02:27
any accident we can.
02:30
Now, you may push the car to the limits
02:32
not because you're driving too fast,
02:34
but because you've hit an icy patch of road,
02:36
conditions have changed.
02:38
In those situations, we want a car
02:40
that is capable enough to avoid any accident
02:42
that can physically be avoided.
02:46
I must confess, there's kind of a third motivation as well.
02:49
You see, I have a passion for racing.
02:53
In the past, I've been a race car owner,
02:55
a crew chief and a driving coach,
02:58
although maybe not at the level that you're currently expecting.
03:01
One of the things that we've developed in the lab --
03:04
we've developed several vehicles --
03:07
is what we believe is the world's first
03:09
autonomously drifting car.
03:11
It's another one of those categories
03:13
where maybe there's not a lot of competition.
03:16
(Laughter)
03:18
But this is P1. It's an entirely student-built electric vehicle,
03:20
which through using its rear-wheel drive
03:24
and front-wheel steer-by-wire
03:26
can drift around corners.
03:27
It can get sideways like a rally car driver,
03:29
always able to take the tightest curve,
03:31
even on slippery, changing surfaces,
03:33
never spinning out.
03:36
We've also worked with Volkswagen Oracle,
03:38
on Shelley, an autonomous race car that has raced
03:40
at 150 miles an hour through the Bonneville Salt Flats,
03:44
gone around Thunderhill Raceway Park in the sun,
03:47
the wind and the rain,
03:51
and navigated the 153 turns and 12.4 miles
03:54
of the Pikes Peak Hill Climb route
03:59
in Colorado with nobody at the wheel.
04:01
(Laughter)
04:04
(Applause)
04:06
I guess it goes without saying that we've had a lot of fun
04:11
doing this.
04:14
But in fact, there's something else that we've developed
04:16
in the process of developing these autonomous cars.
04:19
We have developed a tremendous appreciation
04:22
for the capabilities of human race car drivers.
04:26
As we've looked at the question of how well do these cars perform,
04:30
we wanted to compare them to our human counterparts.
04:34
And we discovered their human counterparts are amazing.
04:38
Now, we can take a map of a race track,
04:43
we can take a mathematical model of a car,
04:47
and with some iteration, we can actually find
04:50
the fastest way around that track.
04:53
We line that up with data that we record
04:54
from a professional driver,
04:57
and the resemblance is absolutely remarkable.
04:58
Yes, there are subtle differences here,
05:02
but the human race car driver is able to go out
05:06
and drive an amazingly fast line,
05:09
without the benefit of an algorithm that compares
05:11
the trade-off between going as fast as possible
05:13
in this corner, and shaving a little bit of time
05:16
off of the straight over here.
05:18
Not only that, they're able to do it lap
05:20
after lap after lap.
05:23
They're able to go out and consistently do this,
05:26
pushing the car to the limits every single time.
05:29
It's extraordinary to watch.
05:33
You put them in a new car,
05:36
and after a few laps, they've found the fastest line in that car,
05:38
and they're off to the races.
05:42
It really makes you think,
05:46
we'd love to know what's going on inside their brain.
05:47
So as researchers, that's what we decided to find out.
05:52
We decided to instrument not only the car,
05:56
but also the race car driver,
05:58
to try to get a glimpse into what was going on
06:01
in their head as they were doing this.
06:03
Now, this is Dr. Lene Harbott applying electrodes
06:06
to the head of John Morton.
06:10
John Morton is a former Can-Am and IMSA driver,
06:11
who's also a class champion at Le Mans.
06:14
Fantastic driver, and very willing to put up with graduate students
06:16
and this sort of research.
06:19
She's putting electrodes on his head
06:21
so that we can monitor the electrical activity
06:24
in John's brain as he races around the track.
06:26
Now, clearly we're not going to put a couple of electrodes on his head
06:29
and understand exactly what all of his thoughts are on the track.
06:32
However, neuroscientists have identified certain patterns
06:35
that let us tease out some very important aspects of this.
06:38
For instance, the resting brain
06:42
tends to generate a lot of alpha waves.
06:44
In contrast, theta waves are associated with
06:46
a lot of cognitive activity, like visual processing,
06:50
things where the driver is thinking quite a bit.
06:53
Now, we can measure this,
06:56
and we can look at the relative power
06:58
between the theta waves and the alpha waves.
07:00
This gives us a measure of mental workload,
07:02
how much the driver is actually challenged cognitively
07:05
at any point along the track.
07:08
Now, we wanted to see if we could actually record this
07:10
on the track, so we headed down south to Laguna Seca.
07:13
Laguna Seca is a legendary raceway
07:16
about halfway between Salinas and Monterey.
07:18
It has a curve there called the Corkscrew.
07:20
Now, the Corkscrew is a chicane, followed by a quick
07:22
right-handed turn as the road drops three stories.
07:25
Now, the strategy for driving this as explained to me was,
07:28
you aim for the bush in the distance,
07:31
and as the road falls away, you realize it was actually the top of a tree.
07:34
All right, so thanks to the Revs Program at Stanford,
07:37
we were able to take John there
07:40
and put him behind the wheel
07:41
of a 1960 Porsche Abarth Carrera.
07:42
Life is way too short for boring cars.
07:45
So, here you see John on the track,
07:48
he's going up the hill -- Oh! Somebody liked that --
07:50
and you can see, actually, his mental workload
07:52
-- measuring here in the red bar --
07:55
you can see his actions as he approaches.
07:57
Now watch, he has to downshift.
07:59
And then he has to turn left.
08:03
Look for the tree, and down.
08:03
Not surprisingly, you can see this is a pretty challenging task.
08:07
You can see his mental workload spike as he goes through this,
08:10
as you would expect with something that requires
08:13
this level of complexity.
08:15
But what's really interesting is to look at areas of the track
08:18
where his mental workload doesn't increase.
08:21
I'm going to take you around now
08:24
to the other side of the track.
08:26
Turn three. And John's going to go into that corner
08:27
and the rear end of the car is going to begin to slide out.
08:29
He's going to have to correct for that with steering.
08:32
So watch as John does this here.
08:34
Watch the mental workload, and watch the steering.
08:36
The car begins to slide out, dramatic maneuver to correct it,
08:38
and no change whatsoever in the mental workload.
08:42
Not a challenging task.
08:45
In fact, entirely reflexive.
08:48
Now, our data processing on this is still preliminary,
08:52
but it really seems that these phenomenal feats
08:55
that the race car drivers are performing
08:58
are instinctive.
08:59
They are things that they have simply learned to do.
09:01
It requires very little mental workload
09:05
for them to perform these amazing feats.
09:07
And their actions are fantastic.
09:10
This is exactly what you want to do on the steering wheel
09:13
to catch the car in this situation.
09:16
Now, this has given us tremendous insight
09:19
and inspiration for our own autonomous vehicles.
09:22
We've started to ask the question:
09:25
Can we make them a little less algorithmic
09:27
and a little more intuitive?
09:30
Can we take this reflexive action
09:32
that we see from the very best race car drivers,
09:34
introduce it to our cars,
09:37
and maybe even into a system that could
09:38
get onto your car in the future?
09:40
That would take us a long step
09:42
along the road to autonomous vehicles
09:44
that drive as well as the best humans.
09:46
But it's made us think a little bit more deeply as well.
09:48
Do we want something more from our car
09:52
than to simply be a chauffeur?
09:55
Do we want our car to perhaps be a partner, a coach,
09:57
someone that can use their understanding of the situation
10:01
to help us reach our potential?
10:04
Can, in fact, the technology not simply replace humans,
10:08
but allow us to reach the level of reflex and intuition
10:10
that we're all capable of?
10:15
So, as we move forward into this technological future,
10:18
I want you to just pause and think of that for a moment.
10:20
What is the ideal balance of human and machine?
10:23
And as we think about that,
10:27
let's take inspiration
10:29
from the absolutely amazing capabilities
10:30
of the human body and the human mind.
10:34
Thank you.
10:37
(Applause)
10:38
Translated by Morton Bast
Reviewed by Thu-Huong Ha

▲Back to top

About the speaker:

Chris Gerdes - Mechanical engineer
An autonomous car may seem like a thing of the distant future, but mechanical engineer Chris Gerdes is racing to make it a reality today.

Why you should listen

Imagine a car that can drive itself -- that with the push of a button can get you home safely when you’re too tired to drive or have had a night of one too many drinks. Dr. Chris Gerdes , the Director of the Center for Automotive Research at Stanford (conveniently acronymed CARS), and his team are developing a robotic race car, capable of driving at outrageous speeds while avoiding every possible accident. Gerdes’ research focuses on the development of driver assistance systems for collision avoidance, as well as on new combustion processes for engines.

Prior to teaching at Stanford, Gerdes was the project leader for vehicle dynamics at the Vehicle Systems Technology Center of Daimler-Benz Research and Technology North America. His work at Daimler focused on safety analysis.

More profile about the speaker
Chris Gerdes | Speaker | TED.com