Tesla secretly tests self-driving software; gets million miles worth of data every 10 hours

Tesla’s electric vehicles are widely seen as the first truly desirable EVs to hit the market, while the company’s efforts in the autonomous car field are deemed to be one of the most exciting advancements in this field. But the company has even bigger plans for the future and they all rely on the always-on, cellular internet connection that Tesla cars have.

Talking at a technology conference in San Francisco yesterday, Tesla’s Autopilot program director, Sterling Anderson explained how the company relies on the continuous connection between its servers and its cars, which are being used by the public.

According to Anderson, the company pulls down huge amounts of data from its existing cars, which it then feeds back into its machine learning algorithms. To be more precise, every ten hours Tesla gets another million miles worth of data. By doing this, and testing new algorithms against all of this data, the company went from being a nobody in the autonomous vehicle market, to a strong contender destined to popularize the first self-driving cars. Anderson mentioned that the company had accrued over 780 million miles of driving data.

Recently, Elon Musk, Tesla’s CEO, praised the company’s Autopilot feature and said early data showed that, while not being truly autonomous, Teslas using autopilot were twice as safe as when the human was driving. Musk went on to say that the company will have a strong case to make for self-driving cars once they've driven billions of miles and are deemed safe. With these data collection techniques, it seems Tesla is closer to that billion-mile mark than all of its competitors combined.

Tesla also uses its cars' data connections to try out new algorithms on existing, real-life drivers. The company quietly deploys software to its cars, which then gets tested out in the real world. While that may sound incredibly shady and dangerous, Anderson repeatedly mentions that the software is “inert” and never actually controls the car – it’s just running in the background and sending its results back to Tesla.

And this approach, which is also touted by the company’s PR reps, has propelled Tesla to the forefront of the autonomous vehicle field. While Google, GM, Apple and others are limited to only using data from their existing fleet of test vehicles, Tesla is continuously learning from cars that are being used all the time, by real people.

With the incredibly large number of pre-orders that Tesla recently got for its upcoming Model 3 sedan, the company seems to be very well positioned to expand its capabilities and technical prowess even further.

Source: MIT Technology Review

Report a problem with article
office-sale-versions
Next Article

Microsoft reduces prices of Office 365 Home and Office Home & Student 2016 in US

microsoft-logo-phone
Previous Article

Microsoft restructures its phone business again, cuts up to 1,850 jobs, writes off $950m

24 Comments - Add comment

Advertisement