To achieve the dream of autonomous vehicles and robots, it’s going to take much more than computer vision and artificial intelligence. Cars, drones, delivery bots, even our vacuum cleaners and robot chefs are going to need something that our ancestors developed millions of years ago: a sense of place.
But the cost of such precision mapping sensors at the moment is very high, says Mr. Thibodeau, adding at least $100,000 to the price of each vehicle. These systems will become cheaper, but he believes it will be at least three to five years before they make it onto the kind of vehicles that private citizens could buy, and that it will take many years after that for them to achieve sufficient density on the world’s roadways to contribute to detailed maps suitable for autonomous driving.
The Key to Autonomous Driving? An Impossibly Perfect Map (WSJ - paywalled)