Major progress in autonomous driving, major update to Tesla FSD!

Publisher:DelightfulWishLatest update time:2024-02-02 Reading articles on mobile phones Scan QR code
Read articles on your mobile phone anytime, anywhere

"FSDBetav12 upgrades the urban street driving stack to an end-to-end neural network, trained on millions of videos, replacing more than 300,000 lines of C++ code." Tesla said in the update description.

Tesla FSDv12 (FSDv12.1.2) has been pushed to users, marking Tesla's significant progress in autonomous driving technology. This update upgrades the urban street driving stack to an end-to-end neural network, replacing hundreds of thousands of lines of C++ code, allowing artificial intelligence to govern vehicle behavior in autonomous driving mode.


The evaluation video of Tesla evaluation blogger WholeMars shows that FSDv12 performed well in the process of taking over the vehicle. It can smoothly avoid vehicles stopped in the lane and wait for pedestrians to cross the road in front of the zebra crossing in time. This is the biggest advancement yet for FSDBeta, with significant improvements in all key aspects.

However, compared with previous versions, FSDv12.1.2 has more situations that require manual takeover and is not yet ready to achieve fully driverless driving. The end-to-end solution is the biggest selling point of Tesla FSDv12. Its advantages include high flexibility, strong adaptability, high upper limit, and the ability to drive in a highly anthropomorphic state, which greatly improves the driving experience. Musk believes that the end-to-end solution is the correct universal decision-making solution because humans rely on their eyes and biological neural networks to drive. For autonomous driving, cameras and neural network AI are the right choices.

Tesla is continuously conducting additional testing to ensure the performance of FSDv12 in various environments. Although performance in California is good, more training is needed for areas with high rainfall. In addition, sophisticated algorithms, massive data, and large-scale computing power are also necessary conditions for FSDV12, among which data is the top priority for training good algorithms.


Overall, the launch of Tesla FSDv12 marks significant progress in autonomous driving technology, but it still needs continuous improvement and optimization. In the future, with the continuous development of technology, I believe that autonomous driving technology will become more mature, safer and more reliable, bringing a more convenient and efficient travel experience to humans.


Reference address:Major progress in autonomous driving, major update to Tesla FSD!

Previous article:After ten years of building cars, Apple finally compromises with reality?
Next article:Honda Motor announces cooperation with this SiC leader

Latest Automotive Electronics Articles
Change More Related Popular Components

EEWorld
subscription
account

EEWorld
service
account

Automotive
development
circle

About Us Customer Service Contact Information Datasheet Sitemap LatestNews


Room 1530, 15th Floor, Building B, No.18 Zhongguancun Street, Haidian District, Beijing, Postal Code: 100190 China Telephone: 008610 8235 0740

Copyright © 2005-2024 EEWORLD.com.cn, Inc. All rights reserved 京ICP证060456号 京ICP备10001474号-1 电信业务审批[2006]字第258号函 京公网安备 11010802033920号