Ford's Nair: Sensors, software are self-driving cars' main obstacles

LAS VEGAS -- Raj Nair says he will be first in line when autonomous vehicles go on sale. Nair, Ford Motor Co.'s product development chief and a big fan of self-driving cars, says the vehicles' two biggest needs are improved sensor capability and development of software that can read the road as a human would.

Nair, 51, has global responsibility for Ford's design, engineering, research and product development. He was interviewed by Automotive News Europe Editor Luca Ciferri in January at the Consumer Electronics Show here.

Q: When will autonomous vehicles go on sale?

A: I think it is credible that an autonomous vehicle at SAE Level 4 [one step below full automation] will hit the market by 2020.

What are the main technical problems?

There are two we are focusing on: software algorithms and sensor capability. The human body is an amazing array of sensors -- two great optical sensors, auditory sensors and balance sensors that provide information that the brain doesn't only perceive but also filters.

 To reproduce all of that with a combination of lidar [a kind of radar based on laser beams], radar and ultrasonic sensors is a big challenge. Then there are the algorithms. They are reasonably straightforward for the basic aspects of driving. If you can see the white lines it's not that hard to steer the vehicle between them. But for all the other things that your mind works through when driving, you need to be prepared for all of them. This increases the level of sensor capability processing you need.

So greater sophistication increases the challenge?

Yes, a lot. It's almost like going up an exponential scale. To get to the first portion is not that hard, but with every percentage above it you're going up exponentially in terms of sensors and processing capability. You also have to ask how far up that scale do we need to be -- forgetting the regulatory aspect -- for our own comfort as a manufacturer. How much better than a human driver does the system need to be for us to feel comfortable putting it into thousands of vehicles?

From Level 4 to a car that can go from one city center to another, how much more time will be needed? Five years?

I think it depends. ... We really need exact positioning of the vehicle and to have the vehicle reference itself to a known map. That makes some of the sensing a little bit easier. If you know that an image, based on previous mapping, is a fire hydrant, then you don't need to consider whether it is a fire hydrant or a small boy. ... If you were to provide laser mapping for a highway connecting two cities as you mentioned, then even Level 4 would be capable of that. But if you want to go out on a dirt road or somewhere not previously mapped and expect the vehicle to be able to deal with all the possibilities that could happen -- a cow running across the road, for example -- that's a challenge for Level 5.

Does connected car require high-resolution digital mapping?

Our view in the medium time frame we're talking about is yes, we need high-definition digital maps.

Those come from Google and not many other providers, right?

No. There are quite a few mapping companies and one of them has just been bought by a German alliance. (In December, BMW Group, Audi AG and Daimler AG completed their acquisition of Nokia's mapping business, Here.) In some of our vehicles with lidar systems, we've been mapping as well. We haven't decided whether we will source maps from a partner or develop them ourselves.

Does it make more sense to buy or license them?

I think everybody's kind of starting from the same spot as far as developing the high-definition maps we're talking about. It's not enough to have the GPS maps everybody has now. It's not even enough to have Google Street View. You have to go out and do the work. We haven't determined what the right direction is yet.

Does the world need to be remapped for autonomous driving and how much does it cost per mapping mile?

For the technology as we see it and within that four-year time frame, yes. As regards costs, I don't have an estimate. Eventually we foresee an environment where the vehicle is not only referencing itself to a map but is also updating that map as it's driving.

What is the key to connected cars?

The user experience. We used to talk about connectivity as an individual remaining seamlessly connected when he was driving and that was the basis of Ford Sync. Now we're talking about connectivity as a vehicle being just one of the devices on the Internet of Things. As such, it needs its own connectivity and that's what Sync Connect has -- a 4G LTE connection to the vehicle itself. This creates a lot of capability and possibilities. Our recent announcement of partnerships with Amazon Echo and Alexa is just the start. With Alexa you can be in your house and say, "Alexa, please start my car. Alexa, what's the range of my vehicle?" And on the way home you can say, "Alexa, open the garage door. Alexa, please turn on the TV or change the temperature to 70 degrees." These features are not just about technology for technology's sake, but about making people's lives better and easier.

When will this technology be available?

We're talking about this year.