Skip to Content
Smart cities

How Do You Design an Autonomous Car from Scratch?

December 7, 2017

Ford thinks driverless cars need to be rugged and, more surprising, hybrid-powered.

That’s according to an announcement from the automaker, explaining that it will buck the trend of repurposing consumer vehicles as driverless ones and build a car designed specifically for autonomy. It makes sense: when cars can drive themselves, the conventions used to design most automobiles are surplus to requirements. But until now, little thought has been given to bridging the gap between experimental minicabs and more fanciful concept vehicles.

Ford, however, has some fairly pragmatic ideas. First, it thinks autonomous cars are going to need to be tough, in order to withstand the rigors of 24-7 use that a robo-taxi will no doubt endure. With that in mind, it says, its specially designed autonomous cars will use heavy-duty hardware—think burly wheels and upgraded brakes—along the lines of those used in commercial vehicles like its police cars.

Elsewhere—and this may be slightly surprising—it also reckons the vehicles must be hybrids. Many commentators have argued that automation and electrification go hand in hand. But Ford thinks users will demand that cars cover large distances without waiting around at recharge points, and that the computer systems aboard the vehicles would put a huge dent in an all-electric’s range, making a hybrid a better bet.

Finally, the vehicles will come loaded with features that help them integrate with other road and sidewalk users. That, says the automaker, is why it’s been playing around with researchers dressed as car seats and pizza-delivering driverless cars, to see how folks interact with their vehicles when there isn’t a driver behind the wheel.

We don’t yet know what this all looks like when it gets put together as a package. But it seems a far cry from Waymo's famous, frivolous bubble car, which was also designed with autonomy in mind. Still, as we’ve reported, that vehicle got scrapped in favor of exploring more conventional cars. Perhaps ones like Ford’s will roll out.

 

Keep Reading

Most Popular

Large language models can do jaw-dropping things. But nobody knows exactly why.

And that's a problem. Figuring it out is one of the biggest scientific puzzles of our time and a crucial step towards controlling more powerful future models.

The problem with plug-in hybrids? Their drivers.

Plug-in hybrids are often sold as a transition to EVs, but new data from Europe shows we’re still underestimating the emissions they produce.

Google DeepMind’s new generative model makes Super Mario–like games from scratch

Genie learns how to control games by watching hours and hours of video. It could help train next-gen robots too.

How scientists traced a mysterious covid case back to six toilets

When wastewater surveillance turns into a hunt for a single infected individual, the ethics get tricky.

Stay connected

Illustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.