Welcome to Tesla Motors Club
Discuss Tesla's Model S, Model 3, Model X, Model Y, Cybertruck, Roadster and More.
Register

The Key to Autonomous Driving? An Impossibly Perfect Map

This site may earn commission on affiliate links.
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)
 
I find it so funny how so many, so called, experts, can be so wrong.

The ability to drive from point A to point B, autonomously, is already available, been there for awhile.
Detailed maps, to the point of knowing the number of lanes, the types of intersections, and the direction of the lanes has also been around for a number of years.

The ability for a vision system to determine the lane that they are in has also been around and it pretty easy to determine.

GPSs aren't as accurate as most people think that they are. But when you add the knowledge of where the roads are and what lane that you are in, you get a very high ability to accurately position yourself on the road.

Take the people and the cars off the road, and I'm sure that every manufacturer would have full self driving available in a few months. You really don't even need the advanced sensors for navigation.

Its very obvious that precision mapping is the least of the issues.

It's when you add cars that move, people that move, and all sorts of things that appear randomly on roads that the problems occur.
 
I completely agree with ewoodrick.. It's dealing with the unexpected that is challenging, but not impossible to overcome as autonomous cars develop and implement more and more sensors and acquired (AI experiences) skills at handling emergencies, erratic drivers in surrounding vehicles, unsafe roads (potholes, slick spots, water puddles, construction zones, debris in roadway, ....). I'm completely confident that autonomous driving on interstates, state and county roads and even city streets is less than 5 years in the future..