//

Thursday, July 18, 2019

T3chExpress

Self Driving car - How Close Are We to a Self-Driving World?

Self Driving car - How Close Are We to a Self-Driving World?

Watch this video and you can read the transcript below it
Self Driving car - How Close Are We to a Self-Driving World?
Self Driving car - How Close Are We to a Self-Driving World?






00:07
IMAGINE A WORLD WHERE YOU WAKE UP, GRAB YOUR CUP OF COFFEE, AND HOP IN YOUR CAR TO DRIVE
00:12
TO WORK…
00:13
EXCEPT YOU’RE NOT DOING THE DRIVING.
00:14
YOU HAVE MORE TIME TO SLEEP, READ A BOOK, OR EVEN GET A PHYSICAL.
00:19
THIS IS A WORLD WE ALL WANT TO LIVE IN. AND ALTHOUGH WE’RE NOT QUITE THERE YET, PEOPLE
00:24
ALL OVER THE WORLD ARE WORKING ON DEVELOPING, TESTING, AND PLANNING FOR A
00:29
FUTURE WITH AUTONOMOUS VEHICLES.
00:31
BECAUSE, WHO DOESN’T WANT THAT EXTRA HOUR OF SLEEP?
00:34
SO, HOW CLOSE ARE WE TO A SELF-DRIVING WORLD?
00:43
YOU MAY HAVE SEEN SELF-DRIVING CARS ON THE NEWS, SPLASHED ACROSS THE INTERNET, OR EVEN
00:48
TESTING AROUND YOUR CITY.
00:50
BUT MOST OF THOSE CARS STILL HAVE A HUMAN IN THE DRIVER’S SEAT.
00:53
AND THAT MEANS IT’S PROBABLY A LEVEL 2 OR 3 CAR, WHICH DEFINITELY MORE INDEPENDENT THAN
00:58
THE CAR YOU MIGHT DRIVE, WHICH IS PROBABLY A LEVEL 0 OR 1, BUT IT'S STILL A FAR CRY FROM
01:02
OUR DREAM RIDE, WHICH WOULD BE A LEVEL 5.
01:04
OR 4.
01:05
LET ME EXPLAIN.
01:06
SAE INTERNATIONAL HAS DIVIDED AUTONOMY INTO FIVE STAGES.
01:10
LEVEL ONE IS “DRIVER ASSISTANCE,” AND LEVEL TWO IS “PARTIAL AUTOMATION,”
01:13
WHICH YOU CAN ALREADY FIND IN CARS WE DRIVE TODAY.
01:16
HERE, THE CAR CAN DO SOME OF THE STEERING, BRAKING, AND ACCELERATING, BUT STILL NEEDS
01:21
A DRIVER WITH HANDS ON THE WHEEL, BECAUSE LEVELS 1 AND 2 ARE STILL JUST “DRIVER SUPPORT.”
01:26
So lane keeping, collision warning, even active interventions that will swerve the vehicle
01:32
if you're about to get into an accident.
01:35
LEVEL THREE IS “CONDITIONAL AUTOMATION,” WHICH MEANS THAT THE CAR IS PRETTY MUCH IN
01:40
CONTROL, BUT REQUIRES HUMAN INTERVENTION IN AN EMERGENCY,
01:43
OR WHEN PROMPTED BY THE SYSTEM.
01:45
REMEMBER LEVEL THREE, BECAUSE THIS IS WHERE IT CAN GET STICKY.
01:48
BUT THE ULTIMATE SELF-DRIVING CAR WOULD BE OPERATING AT LEVEL 4 OR 5, WHERE IT CAN STEER,
01:55
BRAKE, ACCELERATE, MONITOR THE ROAD, RESPOND TO RANDOM EVENTS, CHOOSE TO CHANGE LANES,
02:00
TURN, AND OF COURSE…
02:02
USE ITS BLINKER LIKE ANY DECENT CITIZEN.
02:06
THE YELLOW BRICK ROAD TOWARD SELF-DRIVING TECHNOLOGY HAS BEEN A WINDING ONE.
02:11
DR. DEAN POMERLEAU HAS BEEN NAVIGATING IT FOR A LONG TIME.
02:14
YOU COULD CALL HIM THE GRANDFATHER, OR AT LEAST THE COOL UNCLE,
02:17
OF AUTONOMOUS VEHICLES.
02:19
BACK IN 1995, DEAN AND HIS GRADUATE STUDENT MADE A PILGRIMAGE ACROSS THE COUNTRY
02:23
"LOOK MA, NO HANDS”-STYLE, AFTER THEY TRICKED OUT A STYLISH MINIVAN WITH CAMERAS
02:28
AND COMPUTER VISION ALGORITHMS.
02:31
About 98.2% of the trip, as I recall, was hands-off, feet-off, with the system controlling
02:38
the vehicle all on its own.
02:40
It was a proof of concept, basically, for some of the technologies that we're seeing
02:45
finally being deployed today.
02:48
IN THE YEARS THAT FOLLOWED, RESEARCH TEAMS COMPETED
02:51
TO DEVELOP THAT TECHNOLOGY FURTHER.
02:52
IT WASN’T UNTIL 2005, AFTER SOME…
02:56
CATASTROPHIC FAILURES, THAT DARPA’S GRAND CHALLENGE TO BUILD A SELF-DRIVING CAR FINALLY
03:01
AWARDED FIRST PLACE TO A STANFORD TEAM, LED BY SEBASTIAN THRUN.
03:06
YEAH, YOU MIGHT’VE SEEN HIM AROUND.
03:08
FAST FORWARD TO 2009, WHEN HE STARTS A LITTLE PROJECT CALLED WAYMO.
03:12
IN SECRET.
03:14
IN 2016, WAYMO SPINS OFF FROM GOOGLE, AND IN A FEW SHORT YEARS, THE INDUSTRY’S ERUPTED,
03:20
WITH ESTABLISHED TECH AND CAR COMPANIES JUST AS EAGER AS STARTUPS TO GET IN ON THE ACTION.
03:26
Waymo is probably the recognized leader.
03:29
GM bought Cruise Automation; Argo AI here in Pittsburgh is one leading player;
03:35
BMW Mercedes, are all working on their own projects for self-driving cars.
03:41
It remains to be seen whether it's a good investment or not.
03:46
FOR THAT INVESTMENT TO PAY OFF, DRIVERLESS TECHNOLOGY MUST BE REFINED TO THE POINT
03:50
WHERE IT’S BOTH RELIABLE AND FLEXIBLE ENOUGH TO HANDLE A COMPLEX JOURNEY.
03:55
THAT MEANS SOPHISTICATED SENSORS, ROBUST COMPUTER HARDWARE,
03:59
AND INTELLIGENT DECISION-MAKING SOFTWARE.
04:02
TO START WITH, AUTONOMOUS VEHICLES RELY ON SOMETHING NOT ALL HUMAN DRIVERS
04:05
ARE EQUIPPED WITH: A SENSE OF DIRECTION.
04:08
The companies that are building these self-driving cars build their own maps.
04:12
Very much like Google has its street-view cars that drive through neighborhoods and
04:18
collect map data, they have another fleet with many additional sensors to drive through
04:24
a city and map it in great detail –static obstacles, like telephone poles or the curbs
04:31
around the road, that it should be aware of and avoid.
04:36
BUT TO BE TRULY ADAPTIVE, THE CAR NEEDS TO BE ABLE TO GATHER REAL-TIME INFORMATION ABOUT
04:42
A DYNAMIC, UNPREDICTABLE ENVIRONMENT.
04:44
ELON MUSK THINKS WE CAN ACCOMPLISH THIS WITH CAMERAS ALONE.
04:48
BUT IF YOU’VE EVER TAKEN A SELFIE IN THE CLUB, YOU KNOW THAT CAMERAS PROBABLY AREN’T
04:52
GOING TO CUT IT, BECAUSE THEY STILL STRUGGLE WITH DARKNESS, DEPTH, AND REFLECTIONS.
04:58
So self-driving-car companies are investigating many different sensors, for example, millimeter
05:04
wave radars for long-range sensing, and short-range, often ultrasound, sensors that see things
05:11
that are very close to the vehicle.
05:13
LiDAR is probably the most common and most impressive technology currently being used.
05:20
LiDAR is a laser-based technology that shoots a laser beam out into the environment, scans
05:26
it very quickly, and detects the range to objects and other vehicles.
05:32
LiDARs are both a great sensor but also a weak link; they're very expensive and
05:37
break down fairly often.
05:39
AND THIS HAS BEEN A MAJOR ROADBLOCK TO FULLY AUTONOMOUS ROADS.
05:43
LIDAR HAS HUGE POTENTIAL, BUT IT’S JUST TOO DELICATE AT THE MOMENT, BECAUSE IT’S
05:49
MADE UP OF FRAGILE, MOVING PARTS.
05:51
BUT SOMETHING CALLED SOLID-STATE LIDAR, WHICH SCANS THE ENVIRONMENT USING NO MOVING PARTS
05:57
COULD CHANGE ALL THAT.
05:58
AND THESE SENSORS, WHILE IN THEIR INFANCY, ARE IN SUCH DEMAND THAT MANUFACTURERS LITERALLY
06:03
CAN’T MAKE THEM FAST ENOUGH TO SUPPLY THE DEMANDS OF COMPANIES LIKE FORD AND BAIDU.
06:08
It's much more reliable and also much cheaper to manufacture, which is very important if
06:13
you're going to do this at scales on thousands of vehicles.
06:18
OKAY, SO SAY WE CAN BUILD A DRIVING ROBOT.
06:21
THAT IS, AN ENTITY THAT CAN PERCEIVE ITS ENVIRONMENT, JUDGE, AND ACT ON THE ROAD
06:25
BASED ON A COMPLEX NETWORK OF REAL-TIME DATA ANALYSIS.
06:28
IN A WAY, IT’S STILL ONLY PREPARED TO DRIVE ON A MAP.
06:33
TO BE ABLE TO NAVIGATE IN THE REAL WORLD, AND SHARE THE ROAD, AND THE STEERING WHEEL,
06:37
WITH HUMAN DRIVERS, WE’LL NEED TO TAKE IT TO DRIVER’S ED.
06:41
Some of the biggest safety concerns are involved with perception and behavior
06:47
of drivers or pedestrians or cyclists.
06:50
Slushy roads covered with ice and snow are very hard to cope with, and there's really
06:57
been very little effort or progress in self-driving cars in these very challenging environments.
07:06
TO MAKE THAT PROGRESS, WE HAVE TO STUDY HOW HUMAN DRIVERS ACTUALLY RESPOND – BOTH TO
07:10
RISKY ROAD CONDITIONS, AND TO AUTONOMY ITSELF.
07:14
SO TO FIND OUT MORE ABOUT THE HUMAN IN THE WHOLE EQUATION, WE HEADED TO STANFORD’S
07:18
AUTOMOTIVE INNOVATION LAB.
07:23
We are working together to really get a detailed understanding of the human as we move forward
07:28
in designing active safety systems and automated vehicles.
07:32
So, we're gonna set up this NIRS cap on her right now.
07:34
It will be shining a little bit of infrared light onto her motor cortex.
07:38
We'll be able to see as she's turning left, turning right, using the gas pedal and the
07:44
brake pedal, all in our data streams back there.
07:46
The majority of accidents that we do see do come down to human error in either recognition,
07:52
decision, or performance.
07:53
So when we can get to the point where the system does a better job at those three things
07:59
than humans, then I think it's clear that our roads will be safer.
08:03
This is X-1, our experimental test vehicle.
08:05
The flexibility in steering allows us to set up all sorts of experiments.
08:09
We can emulate driving on an unexpected change of friction.
08:14
Going from snow to ice, for example.
08:16
There are studies going on in the dynamic design lab, measuring the inputs that professional
08:21
drivers make, so that we can try and understand what they're doing differently to drive right
08:26
at the limits of the vehicle. We can use that to inform the way that the autonomous vehicle
08:32
control algorithms are designed, so that hopefully, your autonomous vehicle will drive as well
08:37
as the very best human driver.
08:40
LENE’S MOST RECENT PROJECT INVESTIGATED A SCENARIO THAT MIGHT POP UP IN SOMETHING
08:45
LIKE LEVEL 3 AUTONOMY, WHERE THE CAR’S BEEN ROLLING SOLO WHEN SUDDENLY, IT ENCOUNTERS
08:50
SOME SCENARIO IT CAN’T MAKE SENSE OF, AND THE HUMAN DRIVER IS ASKED TO INTERVENE.
08:56
What our studies of brain and behavior tell us is that it's important to consider a period
09:02
of time when people's driving behavior may be significantly different if they've taken
09:07
control of a vehicle after a certain amount of time out of the loop.
09:11
We can see almost in real time the cognitive resources being deployed. They may have more
09:17
limited cognitive resources to deal with an emergency situation under those conditions.
09:21
It's potentially a quite dangerous situation if you're handing off control back and forth
09:26
with the system.
09:29
THOUGH IT MAY SEEM EXTREME FOR CONSUMERS TO MAKE THE JUMP FROM CRUISING AROUND
09:33
IN A LEVEL 1 CAR TO HOPPING IN A FULLY AUTONOMOUS ONE,
09:37
MANY RESEARCHERS AGREE THAT PARTIAL AUTONOMY
09:39
SHOULD ONLY BE RESERVED FOR TESTING PURPOSES.
09:42
AND UNFORTUNATELY, MOST OF THE ACCIDENTS THAT HAVE ALREADY OCCURRED HAVE
09:46
PROVEN THEM RIGHT.
09:47
I think the next five years or so of autonomous vehicle design is actually going to focus
09:53
more on the ways in which we can implement full autonomy in a much smaller, more controlled
10:00
environment, and sort of do it that way rather than necessarily going through this partial
10:06
autonomy stage to get there.
10:09
People are easily distractible, and that's the underlying problem that autonomous vehicles
10:13
are setting out to solve.
10:15
So NACTO cities believe that it needs to be really full automation to achieve the safety
10:19
benefits that are the major promise behind autonomous vehicles.
10:23
THE NATIONAL ASSOCIATION OF CITY TRANSPORTATION OFFICIALS
10:26
REPRESENTS 68 CITIES AND 11 TRANSIT
10:28
AGENCIES ACROSS NORTH AMERICA.
10:31
NACTO RECENTLY CONVENED TO DISCUSS HOW THE WORLD WILL PREPARE
10:34
FOR FULLY AUTONOMOUS CARS
10:36
TO BECOME A REALITY.
10:37
It's unrealistic to expect city governments to redesign streets
10:42
to accommodate autonomous vehicles.
10:44
THIS MEANS, WHEN SELF-DRIVING CARS DO HIT THE ROAD, THEY’LL NEED TO TRAVEL AT LOW
10:49
SPEEDS, AND MAKE USE OF OUR EXISTING INFRASTRUCTURE.
10:52
BECAUSE OVER THE PAST CENTURY, WE’VE MADE COUNTLESS COMPROMISES
10:56
TO ACCOMMODATE THE SHINY NEW TECHNOLOGY OF THE TIME…
10:58
THE AUTOMOBILE.
11:00
BUT URBAN PLANNERS THINK WE CAN DO BETTER THIS TIME AROUND.
11:05
We've seen neighborhoods cut off from opportunities, we've seen congestion, greenhouse gas emissions,
11:11
pollution, decreases in public health… we risk repeating a lot of those same mistakes
11:15
with autonomous vehicles.
11:17
The Bblueprint for Autonomous Urbanism came about because we were seeing too many visions
11:20
for driverless cars in a people-less city.
11:23
The Blueprint is imagining how cities can structure their streets to prioritize walking
11:28
and biking and transit and public space, to really maximize those benefits of living and
11:32
being in a city, while using autonomous vehicles to help achieve those goals.
11:35
THE IMAGES YOU SEE HERE ARE JUST SKETCHES AND SUGGESTIONS FOR THE FUTURE.
11:40
THE REALITY IS, REGULATION FOR THESE KINDS OF VEHICLES IS PRETTY NEW – AND
11:44
IT’S DIFFERENT IN EVERY STATE.
11:46
BUT PLANNERS AND TRANSPORTATION OFFICIALS LARGELY AGREE ON THE NEED FOR EQUAL ACCESS,
11:50
SAFETY, AND SUSTAINABILITY.
11:53
It requires really thoughtful and intentional policies to make that vision and that promise
11:57
a reality.
11:59
SO, HUMANS ARE ADAPTABLE LEARNERS.
12:01
AND WE’RE DESIGNING SYSTEMS THAT CAN WORK THAT WAY TOO.
12:04
BUT ON A GRANDER SCALE, WE AS A SOCIETY HAVE TO BE WILLING TO ASSESS RISK, AND STEER IN
12:10
THE RIGHT DIRECTION BEFORE WE CHANGE LANES AND CHARGE FULL SPEED AHEAD.
12:14
SO…
12:15
HOW CLOSE ARE WE TO A DRIVERLESS WORLD?
12:19
If you look at particular geographical locations, it's already happening.
12:23
Over time, I believe that those islands will grow in number and expand, and that's how
12:28
you will see the expansion of fully automated vehicles on the road.
12:32
I think in the next year or two we will see companies like Waymo and GM Cruise deploying
12:39
maybe a few hundred of these vehicles for the general public to ride in.
12:43
Probably by early 2020s, we'll see cars without drivers giving rides and then driving empty
12:53
to pick up the next passenger.
12:54
It'll be probably at least a decade, I would say, before you can walk into a showroom and
13:00
buy a car at an affordable price that can do, say, level four or five autonomy, which
13:06
means you don't have to do anything.
13:09
The fact that Waymo's CEO said we're still quite a ways off makes me think
13:12
that that's probably true.
13:14
But in the near term, I think there are some applications, especially for transit, to use
13:18
autonomous technology to achieve some of our goals.
13:21
Access to affordable, convenient transportation is really important.
13:25
We all have a grandparent or a friend of our grandparents who had to give up driving and
13:29
lost a lot of their independence.
13:31
I think it can change lives and save lives across the board as long as we take into consideration
13:38
everyone across the spectrum as we as a society move forward with automated vehicles.
13:44
SOUNDS LIKE AS LONG AS WE TAKE CARE OF SOME POTHOLES FIRST…
13:46
WE’VE GOT A GREEN LIGHT.
13:49
TO MAKE SURE YOU NEVER MISS AN EPISODE, DON'T FORGET TO SUBSCRIBE.
13:52
AND FOR MORE HOW CLOSE ARE WE?
13:53
CHECK OUT THIS PLAYLIST HERE.
13:54
THANKS FOR WATCHING AND I'LL SEE YOU NEXT TIME ON SEEKER.

Subscribe to get more videos :

Subscribe by Email