How the Google Self-Driving Car Works
Henry Fountain of the New York Times goes for a ride in a Google car and writes Yes, Driverless Cars Know the Way to San Jose. A lot of the tech needed for basic self-driving systems are already in a lot of cars, like accelerometers for air bags and wheel rotation sensors for antilock brakes. But the Google system takes it to a higher level.
But Google’s lidar is far more complex, consisting of 64 infrared lasers that spin inside a housing atop the car to take measurements in all horizontal directions. (Lidar systems like this are also very expensive — about $70,000 a unit — so cost and complexity will have to come down before they can be widely used.)
The units take so many measurements that, when combined with information from the radar and cameras, a moving map of the car’s surroundings can be created in the onboard computer, a fairly run-of-the-mill desktop. It’s a highly detailed map — the lidar can distinguish, for example, a pickup truck carrying something on a rack from a similarly sized, but boxier, delivery van.
The Google system also is constantly updating the maps, so that if one car sees a pile of traffic cones for a closed lane, it can instantly update the maps so that cars following know what's up ahead. People can't do that.
Interestingly, one of the hardest things to learn is to be a bit aggressive, such as at four way stops.
Google’s engineers tweak that intelligence based on the driving experience of the test cars. Safely coping with four-way-stop intersections was really difficult, [Google engineer] Mr. Levandowski said, because a certain amount of assertiveness — moving into the intersection slightly to see how other cars react — is required.
“We realized there’s subtle communication that goes on,” he said. “Once we’ve come to a stop, we inch forward a bit to signal, hey, we’re ready to go.” A self-driving car that did not assert itself might wind up sitting at the intersection for a long time as other cars passed on through.
More in the New York Times