Hold your eyes open wide and look at everything around you. Raise your nose to the air and take a big whiff. Hold your hands out in front of you and run them through the air. Because, friends, you are experiencing the future.
Right now, driving along the streets of California, Google is road-testing a car.
A car that can drive itself.
The car, which runs on an autonomous driving technology known as Google Chauffeur, has been in development for a couple of years now, but its developers think that they’re getting closer to the finished product.
A self-driving car. Let’s all just think of the possibilities here:
– You could have your primary school-aged children travel by car to school/soccer/ballet/karate/piano while you sit on the couch and do the crossword.
– You could never need to worry about finding a parking spot in a busy shopping centre ever again because your car could just go home while you shopped and then pick you up at the end.
– You could lie in bed in your pyjamas while your car goes through the McDonald’s drive thru and brings you hash browns.
Well, maybe not that last one. But, even so, the commercial production of self-driving cars could change our world.
The Wire‘ Eric Jaffe – the first journalist to travel in the car – explains how the six steps that allow the car to take you to wherever you need to go, without needing you at all:
The first is to locate itself — broadly in the world via GPS and more precisely on the street via special maps embedded with detailed data on lane width, traffic light formation, crosswalks, lane curvature and so on. Urmson [the project’s director] says the value of maps is one of the key insights that emerged from the DARPA challenges. They give the car a baseline expectation of its environment; they’re the difference between the car opening its eyes in a completely new place and having some prior idea what’s going on around it.
Next, the car collects sensor data from its radar, lasers and cameras. That helps track all the moving parts of a city no map can know about ahead of time. The third step is to classify this information as actual objects that might have an impact on the car’s route — other cars, pedestrians, cyclists, etc. — and to estimate their size, speed and trajectory. That information then enters a probabilistic prediction model that considers what these objects have been doing and estimates what they will do next. For step five, the car weighs those predictions against its own speed and trajectory and plans its next move.
That leads to the sixth and final step: turning the wheel this much (if at all) and braking or accelerating this much (if at all). It’s the entirety of human progress distilled to two actions.
Alas, Google has no current plans to commercialise the system. However, they are looking to develop the Google Chauffeur to the extent that they could sell it to car manufacturers for their own use.
But for now? We’d all better get used to school pick-ups and tight parking spots.
Would you trust self-driving cars?
Click through to see what other new and interesting inventions we came across…