The December 2022 issue of IEEE Spectrum is here!

Close bar

Startup Teaches Old Cars Some Robotic Tricks

Nauto retrofits cars with connectivity, machine learning and safety systems

2 min read
Startup Teaches Old Cars Some Robotic Tricks
Photo: NAUTO

Automated systems can improve driving only so much when they're available in just a handful of the latest cars. We need to retrofit the millions now on the road—and that’s a key part of the business model of Nauto, a startup in Palo Alto, Calif.

The company was founded this year by CEO Stefan Heck, an engineer, and Frederick Soo, a neuroscientist, and will be showing its stuff next month at the Consumer Electronics Show in Las Vegas.

Right now Nauto is concentrating on fleet operators—mostly delivery, limousine, and taxi companies—because they stand to immediately gain from improved driving skills, better routing, and better cataloguing of traffic conditions at various times of day. Later, when the work is vindicated and the database well stocked, the company will woo consumers as well.

Fleet managers pay $400 per vehicle up front and a monthly service fee. Pricing for consumers hasn’t been released yet.

The system begins with a dashboard-mounted gizmo that connects cameras that look not only out at the road but also inside the car—the better to gather information that might exonerate a falsely accused driver of a fleet car. “There are a lot of people out there who claim they were whiplashed or rear-ended so they can get a quick settlement,” says Jeanne Meyer, a spokesperson fo the company. “Our reporting will defend both the driver and the company.”

Next, the system beams the data to the cloud, where a machine-learning system pools it with input from other cars in order to work out improvements in driving patterns—either of an individual driver or a bunch of them. Meyer says it’s a bit like Waze, the cloud-sourced navigation service now owned by Google. But it’s better because it gathers information about the route automatically rather than requiring the driver to key things in after the fact, while idling at a stoplight. “Navigation is one of our benefits, but not the only one; we give precise help, based on your driving patterns this week,” she says.

So it’s not threatening to supplant Google Car or Tesla Autopilot—just combine a dollop of situational awareness with some connected-car goodness. Nauto might help you find a parking spot. Or it might conclude that you should leave a bit earlier than usual in order to avoid the worst of the traffic. Nauto is testing the device with 20 fleet managers and delivery services in California’s Bay Area, as well as in 22 other cities around the world.

Sometime next year, Nauto will offer the service to consumers. The package will include an in-dash console together with cameras and an alerting device to warn you when trouble’s brewing. 

The Conversation (0)

Chinese Joint Venture Will Begin Mass-Producing an Autonomous Electric Car

With the Robo-01, Baidu and Chinese carmaker Geely aim for a fully self-driving car

4 min read
A black car sits against a white backdrop decorated with Chinese writing. The car’s doors are open, like a butterfly’s wings. Two charging stations are on the car’s left; two men stand on the right.

The Robo-01 autonomous electric car shows off its butterfly doors at a reveal to the media in Beijing, in June 2022.

Tingshu Wang/Reuters/Alamy
Purple

In October, a startup called Jidu Automotive, backed by Chinese AI giant Baidu and Chinese carmaker Geely, officially released an autonomous electric car, the Robo-01 Lunar Edition. In 2023, the car will go on sale.

At roughly US $55,000, the Robo-01 Lunar Edition is a limited edition, cobranded with China’s Lunar Exploration Project. It has two lidars, a 5-millimeter-wave radars, 12 ultrasonic sensors, and 12 high-definition cameras. It is the first vehicle to offer on-board, AI-assisted voice recognition, with voice response speeds within 700 milliseconds, thanks to the Qualcomm Snapdragon 8295 chip.

Keep Reading ↓Show less