Seth Rosenblatt, writing for CNET:
Google’s self-driving car is an ambitious project that hopes to end human error behind the wheel with a very Googley solution: software. The tech titan’s robo-cars have logged more than 700,000 hours since it began working on the vehicles in 2009. Google expects to have them ready for public use between 2017 and 2020.
At the heart of the technology, what separates it from other sensor-driven autonomous vehicle projects, is a Google-made topographical map that gives the car a sense of what it should expect. The map, different from Google Maps, includes the height of the traffic signals above the street, the placement of stop signs and crosswalks, the depth of the sidewalk curb, the width of the lanes, and can differentiate lane markings from white and dashed to double-yellow.
When you think of all the permutations that driving on a public road entails, this technology is pretty amazing. It also highlights just how smart humans are and how quickly we can synthesize a vast amount of realtime data.