Connect with us

Hi, what are you looking for?


Autonomous Vehicles

How Your Tesla Is Learning To Drive Itself

If AIs can win at Jeopardy! and beat human champions at popular video games, how hard can it be for them to learn to drive?

Originally published on EVANNEX.
By Charles Morris

If AIs can win at Jeopardy! and beat human champions at popular video games, how hard can it be for them to learn to drive?

Trent Eady, writing in Medium, tells us that AlphaStar, a new AI from Google’s DeepMind, beat professional gamer MaNa at StarCraft II in December. There’s some dispute as to whether this particular man-vs-machine matchup was a fair fight, and MaNa defeated a new version of AlphaStar in a January rematch. However, the AI’s performance was undoubtedly impressive, and the way it learned to play StarCraft has some interesting parallels with the way Tesla is believed to be training its AI systems to drive.

Tesla’s Autopilot in action (Image via Tesla)

Mr. Eady explains that AlphaStar mastered StarCraft by using two different machine learning techniques.

In supervised imitation learning, an AI examines a huge number of examples of something, and eventually learns how to recognize that something — in the classic example, if you show an AI a million photos of cats, it will learn to identify a cat, as opposed to a dog (which isn’t as easy as it sounds).

The second technique, reinforcement learning, is a process of trial and error — an AI takes a random action, observes the effect, and learns which actions lead to the desired results. “Imitation learning followed by reinforcement learning is a one-two punch I suspect we could see a lot of in the future,” writes Eady.

Tesla vehicles produced since October 2016 include the hardware suite that Tesla says will eventually enable full self-driving. As these cars drive around, they collect data from the cameras and other sensors, and the Autopilot computers can use that data to learn by example. The driving decisions of a human driver are analogous to the pictures of cats in the example above.

As Amir Efrati writes in The Information, “Tesla’s engineers believe that by putting enough data from good human driving through a neural network, that network can learn how to directly predict the correct steering, braking and acceleration in most situations.”

How much data is enough? There are currently about 400,000 cars with the Autopilot hardware on the road, and they drive a collective 12.5 million miles per day. The size of the fleet is increasing by over 5,000 cars per week. Tesla is the only company that has anything like this data set.

Mr. Eady reports that Google’s Waymo tested supervised imitation learning on a small scale, using data from up to 75,000 miles of driving, with impressive results. Israeli firm Mobileye, which previously supplied equipment for Tesla’s Autopilot, and is now owned by Intel, has achieved some success with reinforcement learning, and released a video showing its system in action on the famously chaotic streets of Jerusalem.

OpenAI, one of Elon Musk’s many recent side projects, used reinforcement learning to train an AI called OpenAI Five to play a video game called Dota 2, and it was able to beat a team of skilled human players. OpenAI’s Chief Scientist, Ilya Sutskever (who delivered a lengthy speech on the latest advances in AI at the recent AI Frontiers conference), said that, while AI researchers are skeptical that reinforcement learning is capable of solving hard problems, his organization’s work with OpenAI Five demonstrates that reinforcement learning simply hasn’t been used with the scale of training data required until now.

Insight into OpenAI’s efforts with Dota 2 (YouTube: OpenAI)

Mr. Eady reminds us that we don’t know for sure that Tesla is using reinforcement learning to train Autopilot — so far the company has only said it’s using imitation learning. However, considering the vast amounts of driving data Tesla has available, and the success that others have been demonstrating with reinforcement learning, it seems likely that the company is combining the two techniques in its quest to teach a machine to match (or hopefully, exceed) human driving ability. In a recent posting for an intern position, Tesla said it was looking for candidates with expertise in reinforcement learning.

Related: Tesla Autonomy Day Video & Dozens Of Quotes

Don't want to miss a cleantech story? Sign up for daily news updates from CleanTechnica on email. Or follow us on Google News!

Have a tip for CleanTechnica, want to advertise, or want to suggest a guest for our CleanTech Talk podcast? Contact us here.

Written By

We publish a number of guest posts from experts in a large variety of fields. This is our contributor account for those special people, organizations, agencies, and companies.


You May Also Like


Used Tesla vehicles have dropped in price in recent months, causing many prospective buyers to consider buying one with a lower price tag and...


In this article, I explain that Tesla has dropped its lease pricing so much that it costs the same to lease a Tesla Model...


A big portion of new car buyers are now buying fully electric cars. But more are buying non-electric cars. If you’ve been in the...


Mark Purcell and his family have just completed a holiday drive, travelling 8000 km from the Sunshine Coast in Queensland to Hobart in Tasmania...

Copyright © 2023 CleanTechnica. The content produced by this site is for entertainment purposes only. Opinions and comments published on this site may not be sanctioned by and do not necessarily represent the views of CleanTechnica, its owners, sponsors, affiliates, or subsidiaries.