[nfb-talk] Fw: Yes, Driverless Cars Know the Way to San Jose.
edmeskys at roadrunner.com
Sun Oct 28 18:23:57 UTC 2012
Yes, Driverless Cars Know the Way to San Jose.
NY Times Sunday, 2012_10_28
By HENRY FOUNTAIN. MOUNTAIN VIEW, Calif.
THE 'look Ma, no hands' moment came at about 60 miles an hour on Highway
Brian Torcellini, Google's driving program manager, had driven the white
450h out of the parking lot at one of the company's research buildings and
local streets to the freeway, a main artery through Silicon Valley. But
clearing the on-ramp and accelerating to the pace of traffic, he pushed a
button on the modified console between the front seats. A loud electronic
from the car's speakers, followed by a synthesized female voice.
Autodriving,' it announced breathlessly.
Mr. Torcellini took his hands off the steering wheel, lifted his foot from
and the Lexus hybrid drove itself, following the curves of the freeway,
up to get out of another car's blind spot, moving over slightly to stay well
of a truck in the next lane, slowing when a car cut in front.
We adjusted our speed to give him a little room,' said Anthony Levandowski,
the lead engineers for Google's self-driving-car project, who was monitoring
system on a laptop from the passenger seat. Just like a person would.
Since the project was first widely publicized more than two years ago,
been seen as being at the forefront of efforts to free humans from
driving is drudgery. In all, the company's driverless cars --
Toyota Priuses and the newer Lexuses, recognizable by their spinning,
laser range finders -- have logged about 300,000 miles on all kinds of
Torcellini unofficially leads the pack, with roughly 30,000 miles behind the
-- but not turning it.)
But the company is far from alone in its quest for a car that will drive
a person would, or actually better. Most major automobile manufacturers are
on self-driving systems in one form or another.
Google says it does not want to make cars, but instead work with suppliers
to bring its technology to the marketplace. The company sees the project as
of its core work in software and data management, and talks about
relationship with their automobiles.
Self-driving cars, Mr. Levandowski said, will give people 'the ability to
space without necessarily wasting your time.
Driving cars, he added, 'is the most important thing that computers are
do in the next 10 years.
For the automakers, on the other hand, self-driving is more about evolution
revolution -- about building incrementally upon existing features like smart
control and parking assist to make cars that are safer and easier to drive,
the driver is still in control. Full autonomy may be the eventual goal, but
aim is to make cars more desirable to customers.
We have this technology,' said Marcial Hernandez, principal engineer at the
Group's Electronics Research Laboratory, up the road in Belmont, Calif. How
turn it into a product that can be advertised to a customer, that will have
benefit to a customer?
With all the research efforts, there is a growing consensus among
experts that self-driving cars are coming, sooner than later, and that the
benefits -- in crashes, deaths and injuries avoided, and in roads used more
to name a few -- are enormous. Already, Florida, Nevada and California have
self-driving cars legal for testing purposes, giving each car, in effect,
Richard Wallace, director for transportation systems analysis at the Center
Research, a nonprofit group that recently released a report on self-driving
with the consulting firm KPMG, said that probably by the end of the decade,
be able to have a safe, hands-free left-lane commute. In 15 to 20 years, he
'literally from the driveway to destination starts to become possible.
Despite their differing goals, the approaches of Google and the car
much in common. They each rely on sensors to gather data about the car's
processors to crunch the data, algorithms to interpret the results and make
decisions, and actuators to control the car's movements.
Most of the sensors are already in widespread use. Radar, for example, is
features like adaptive cruise control, measuring the distance to the car
that a safe interval can be maintained. Cameras are used in lane-keeping
recognizing lane stripes on the road so the car can be steered between them.
Digital encoders, specialized sensors that precisely measure wheel rotation,
been employed for years in antilock brakes and stability-control systems.
have been used to measure changes in speed, particularly for air bags.
GPS devices are useful for self-driving systems, but only in giving a
of the car's location. More important is knowing the car's position in
other vehicles and objects in its immediate environment -- information the
You use the sensors in the vehicle to very precisely place you locally,' Mr.
In the move toward more autonomous vehicles, one tendency is to integrate
from different sensors. Camera recognition systems may be fooled by shadows,
example, thinking they are objects, but radar is not readily tricked.
Some automakers are developing a feature known as traffic jam assist, which
the information from radar and cameras to allow hands-off driving on the
at speeds of about 30 m.p.h. or less.
We're taking the adaptive cruise control and the lane-keeping and bringing
Mr. Hernandez said.
Traffic jam assist is a step toward more autonomy, but the car is still far
self-driving; it won't change lanes, for example.
A lot of this is getting people comfortable with the technology, showing
benefit,' Mr. Hernandez said. The idea is the driver is always in control --
vehicle is there to help you.
Google's fleet of about a dozen vehicles adds the rooftop laser units to
more useful data stream than the cameras and radar systems alone can do.
finders, known as lidar units, have been used by some automakers to provide
measurements for their adaptive cruise control systems.
But Google's lidar is far more complex, consisting of 64 infrared lasers
inside a housing atop the car to take measurements in all horizontal
(Lidar systems like this are also very expensive -- about $70,000 a unit --
and complexity will have to come down before they can be widely used.)
The units take so many measurements that, when combined with information
radar and cameras, a moving map of the car's surroundings can be created in
computer, a fairly run-of-the-mill desktop. It's a highly detailed map --
can distinguish, for example, a pickup truck carrying something on a rack
similarly sized, but boxier, delivery van.
We like lidar because it is actually the most rich sensor you can put on a
Mr. Levandowski of Google said. It helps you separate out people from bushes
them, people from each other, people from crosswalks, and it helps you make
model of the world.
Still, the key to a car being able to truly drive itself lies in the
piece that's missing is not better radars or cameras or lasers or whatever
using,' he said. It's really the intelligence behind them.
Google's engineers tweak that intelligence based on the driving experience
test cars. Safely coping with four-way-stop intersections was really
Levandowski said, because a certain amount of assertiveness -- moving into
slightly to see how other cars react -- is required.
We realized there's subtle communication that goes on,' he said. Once we've
to a stop, we inch forward a bit to signal, hey, we're ready to go. A
car that did not assert itself might wind up sitting at the intersection for
time as other cars passed on through.
Fundamentally, though, the car has to operate safely, Mr. Levandowski said,
another car tries to enter the intersection out of turn, the self-driving
The learning is constant. On the way back from the Highway 101 drive, for
an extra-long articulated bus turned in front of the Lexus, which was now
human-driving mode because the software had been optimized for only highway
that day. But all the sensors were still doing their jobs, so the bus showed
Mr. Levandowski's laptop screen as a string of red dots that stretched out
bus rounded the corner.
Awesome bus,' Mr. Levandowski said as he typed a note for other engineers to
The system constantly compares the car's map to detailed maps created by
downloaded to the car. Those maps provide a lot of additional information
with navigation, but they also help the car know when conditions have
Perhaps construction barrels have just been set up, closing a lane, or a
or other object has fallen onto the road from a car. By comparing maps, the
its surroundings have changed, and it has to take some action: continue
alert the driver that it's time to take back control or, if all else fails,
over to the side of the road.
The communication is two-way, so in addition to downloading Google's maps,
can upload its map to Google. If several self-driving cars upload maps
new construction barrels, for example, Google can update the map it sends to
cars, letting those cars anticipate the hazard.
This connectivity is critical to Google's approach, and is one reason its
is more advanced than other efforts. (For current and planned features like
cruise control, car companies have not needed to consider communication, but
move toward more fully autonomous vehicles they will have to, experts say.)
But even Google acknowledges that its system is not there yet.
We think it is going to be feasible for a computer to drive a car safer than
can in the not-too-distant future,' Mr. Levandowski said. By no means are we
today. We are in the process of learning.
If and when it is introduced, there will no doubt be limits. What's nice
cars is you can actually confine where they operate and how they work
know where they are,' Mr. Levandowski said.
So the system may work at first only on some highways, or in other specific
It's not going to be George Jetson from day one,' he said.. PHOTO: ROBOTIC:
from the lidar rangefinder unit on its roof, Google's fleet of self-driving
including this Lexus hybrid, look reasonably conventional. (PHOTOGRAPH BY
GRAPHICS: How an Autonomous Car Gets Around: Self-driving cars that are
will rely on a number of sensors and other digital devices, many of which
being used for safety and convenience features. (Sources: Velodyne Lidar;
of America; Google).
More information about the nFB-Talk