Skip to main content
  1. Home
  2. Cars
  3. News

Tesla gains one million miles of self-driving data every 10 hours

Add as a preferred source on Google

The not-so-secret “secret” to Tesla’s autonomous driving research is the perpetual cellular internet connection in its cars. Whether the driver is using any of the Tesla autopilot features or not, the car tracks and transmits data back to the mothership … um, Tesla headquarters, where the company can analyze it and learn from it, according to the MIT Technology Review.

Speaking at the EmTech Digital conference in San Francisco, Tesla’s Autopilot program director Sterling Anderson said that Tesla Model S vehicles have had the constant cellular connection since 2012. The company started installing a suite of 12 new sensors into the cars in 2014, and the ability to track what the car was doing, where it was, what was around it, and how it was behaving increased significantly. The sensors were introduced as a new emergency braking system, and they do perform that function, but the ultrasonic sensors along with radar and forward-facing cameras enable the company to test autonomous driving features.

Recommended Videos

One of the functions of the constant cellular connection is to enable automatic software updates. Owners never have to go to a dealership just to download the latest install. Tesla is also able to add functions that the driver won’t know about or even be able to use, in order to conduct tests. Neither Tesla nor the new functions covertly take over the cars, so the driver is still in control of the vehicle and which functions are actually active. However, there’s an “inert” mode whereby Tesla can access the data streaming from the sensors to see how the car “would have reacted” if it were in autopilot mode.

With every new Tesla sold, the data stream grows. “Since introducing this hardware 18 months ago we’ve accrued 780 million miles,” said Anderson. “We can use all of that data on our servers to look for how people are using our cars and how we can improve things.”

Anderson also spoke about driver expectations. “Autopilot is not an autonomous system and should not be treated as one,” he said. “We ask drivers to keep their hands on [the wheel] and be prepared to take over.”

Tesla Model S drivers that activated the autopilot Summon mode and hit other parked vehicles should know that Tesla knows exactly what you did and when you did it. If this feels too Big Brother-ish for you, just don’t buy a Tesla. In the meantime, unlike any other car company at this time, Tesla is able to gather data in prodigious quantities for installed autonomous features, whether or not the owners know about them.

Bruce Brown
Bruce Brown Contributing Editor   As a Contributing Editor to the Auto teams at Digital Trends and TheManual.com, Bruce…
This sleek Chinese EV pairs supercar styling with three AI brains
The Xpeng L03 is an AI supercomputer disguised as a stylish family SUV
Xpeng L03

Xpeng’s latest electric vehicle carries enough processing power to make the term "smart car" actually sound more realistic than it actually is. The new Xpeng L03 debuted simultaneously in Europe and China on July 16, with the company presenting it across 65 markets. Available as a fully electric vehicle and an L03 Power X range-extender, the coupe-SUV is Xpeng’s most internationally focused model so far. Market-specific prices and sales dates remain unannounced.

Three AI chips and Google Maps built right in

Read more
A new sodium battery posts wild four-minute charging numbers, but don’t expect it in an EV yet
The breakthrough could improve fast charging and battery life, but the study hasn’t demonstrated those results in a production-sized pack
EV Charger

A new sodium-metal battery has posted a charging number that makes today’s EVs look painfully slow. In laboratory testing, the cell operated at a 15C rate, equivalent to completing a charge or discharge in roughly four minutes.

That doesn’t mean researchers plugged in an electric car and watched it fill up before the driver finished buying coffee. The result came from a small experimental cell using a new quasi-solid electrolyte, while the larger pouch-cell prototype delivered far less dramatic performance.

Read more
The Apple Car may be dead, but it became the foundation of Apple Intelligence
A decade of work on a canceled car project reportedly laid the groundwork for Apple Intelligence.
Apple Intelligence in Apple Car

The Apple Car may have never left the garage, but it apparently gave birth to Apple's AI ambitions. According to Bloomberg's Mark Gurman, Apple's canceled autonomous vehicle project, one that consumed more than a decade of work and over $10 billion before being scrapped in 2024, ended up laying the technological foundation for Apple Intelligence. In a rather ironic twist, one of Apple's most expensive failures may also become one of its most important long-term investments.

The Apple Car forced Apple to think like an AI company

Read more