[nabs-l] Google car takes to the streets

[Robert William Kingett]

this is a more recent news story.

4/11/2013.


No Hands, No Feet: My joyous Ride In Google's Driverless Car

Chunka Mui

Joann Muller

Joann Muller

There’s something unnerving about going for a drive on a crowded freeway 
with a guy who talks with his hands. But Chris Urmson didn’t seem the 
least bit fazed about taking his hands off the wheel (or his feet off 
the pedals) as we motored south on Silicon Valley’s Highway 101 at 65 
miles per hour, so I tried to relax, too.

Urmson is the leader of Google’s driverless car project and he was 
giving me a demonstration of the technology that has the entire auto 
industry buzzing. The car we were riding in was a white Lexus RX450h 
outfitted with a $65,000 laser sensor on the roof, and other gear that 
included radar sensors in the front and rear bumpers, a high-def camera 
looking out from the windshield, and another looking inward at the 
passengers – about $100,000 worth of extra technology in all. It’s all 
pulling in massive amounts of data. The laser, for instance, takes 1.5 
million range measurements per second.

On the instrument panel, a graphic depicted each of the cars around us 
as a white rectangle and tracked its movement relative to ours. It even 
picked up a motorcycle weaving its way between cars despite the fact 
that it wasn’t traveling in a marked lane. It also sent a message to let 
us know there was a tailgater following too closely behind us.

Urmson was explaining to me that the “brains” of the whole system are 
stored in a laptop-sized computer stashed in the rear of the vehicle 
when suddenly a car in the next lane drifted across the lane marker as 
the driver fumbled to reach his hat on the passenger seat. Our Lexus 
automatically slowed, waiting to make sure the distracted driver 
recovered. Urmson just kept talking and waving his arms. I looked over 
at the steering wheel, which was moving ever so slightly to stay within 
the lane markers. If I didn’t know better, I’d say a ghost was driving.

A few minutes later, a slow-moving truck merging onto the highway pulled 
in front of the line of vehicles we were following. Traffic slowed 
suddenly, and our Google car hit the brakes, too. I looked down, 
expecting to see Urmson’s foot firmly on the brake. But it was resting 
on the floor, as it had been since we entered the freeway. Weird.

It was all very normal, except for the fact that Urmson wasn’t driving. 
“The challenge is we’re putting these on the road with humans,” he said. 
“So they need to react the way humans would.”

Having recently taught my teenage daughter to drive, I can say it’s 
relatively easy to drive in a straight line on the freeway. The hard 
part is getting on and off the freeway. Indeed, this is where Urmson 
took the wheel. But the transition was all very seamless. He pushed the 
“off” button and took over. “The goal here is to make the technology 
disappear.”

So far, Google has logged 500,000 miles of autonomous driving. Urmson 
explained that right now, engineers are working to perfect single-lane 
highway driving, but that with the right programming, Google’s car could 
be driven under any circumstances.

This is no easy task, though. Even the best GPS system isn’t enough to 
pilot a driverless car. Before the car can drive itself, Google 
engineers have to drive the route themselves to gather data about the 
environment, and then add it to highly detailed maps of the roads and 
terrain. (Luckily, this is something that Google happens to be very good 
at.) When it’s the autonomous vehicle’s turn to drive, it compares the 
data it is acquiring from all those sensors and cameras to the 
previously recorded data. That helps it differentiate a pedestrian from 
a light pole.

There are limitations, though. Urmson says the driverless car can’t 
handle heavy rain and can’t drive on snow-covered roads “because the 
appearance and shape of the world changes. It can’t figure out where to 
go or what to do.” And engineers are still working on how to program the 
car to handle “rare events” like encountering a stalled vehicle over the 
crest of a hill or identifying debris, like a tire carcass, in the 
middle of the road.

But an exciting moment for Google engineers came one day when the 
autonomous car slowed suddenly on a city street when there was no 
traffic ahead of it. The engineers didn’t know why, until a pedestrian 
emerged from between two parked cars. The engineers hadn’t seen him.

Also on Forbes: