Tesla's Autopilot Hardware Maxed Out But the Fleet Will Continue to Learn

Tesla Autopilot 1 photo
Photo: Marc van der Chijs on Flickr
The last two weeks have been pretty patchy for Elon Musk with everything that happened at Cape Canaveral, but at least he got to talk about his favorite subject these past days.
That would be the Autopilot, the semi-autonomous driving system that all Teslas have come equipped with since 2014 and have actually been able to use over the past year. But it's not like the Autopilot didn't give Musk its fair share of headaches since its introduction.

After a smooth start, crashes involving Teslas running on Autopilot have begun appearing, making it look like all they needed was that first one to break the ice for the floodgates to open. After a while, it became apparent it was just a matter of time until we had the first casualty of such an incident, and that's precisely what happened early this May (even though we only found out about it on the last day of June).

All this, good and bad, has made Autopilot the most talked-about semi-autonomous system out there, and Tesla isn't likely to want to give up on this. Before switching over to the so-called Autopilot 2.0, the company has just released the latest update for the initial version of this feature, and Musk was there to talk everybody through it.

He wrote the usual blog post but also held a press conference where he took some live questions. One of them was asked by Electrek's Fred Lambert and was aimed at the hardware reserve the current setup of the Models S and X has. “It was a hard software problem," Musk said. "I think in term of macro, major improvements, yes, we are almost reaching the limits, but it is important to emphasize that the fleet learning will continue, and the intelligence of how that fleet learning is applied to the car will continue to improve.”

“So while we are reaching the limit of the hardware, I think we have not quite yet reached the algorithmic intelligence on the car and of course, anything that’s done on our servers – where we are not computer constraint or space constraint in any way. I think, in fact, I’m quite certain that it would continue to improve quite a lot just because the software and the data would improve quite an enormous amount.”

According to Musk, the current hardware still has plenty of years ahead of it thanks to the constant improvements generated by the software. As for the actual extra gear that will adorn next Tesla models, there's plenty of talk going around. Musk has said it doesn't consider using a LIDAR sensor yet due to its limitations and high cost, opting instead of extra video cameras and radars. However, a lot of people doubt he can make a Level 4 or Level 5 autonomous car without the use of the much more accurate LIDAR.
If you liked the article, please follow us:  Google News icon Google News Youtube Instagram
About the author: Vlad Mitrache
Vlad Mitrache profile photo

"Boy meets car, boy loves car, boy gets journalism degree and starts job writing and editing at a car magazine" - 5/5. (Vlad Mitrache if he was a movie)
Full profile


Would you like AUTOEVOLUTION to send you notifications?

You will only receive our top stories