Traditional Culture Encyclopedia - Weather forecast - Musk: Tesla began to push the version of FSD Beta V 1 1 overseas.

Musk: Tesla began to push the version of FSD Beta V 1 1 overseas.

A few days ago, Musk said on overseas social platforms that Tesla has started to push the FSD Beta V 1 1 version of the assisted driving system to testers, and overseas users can receive the push after 15: 1 12. Musk also confirmed that Tesla will be "widely launched" to more North American users in a few weeks.

According to the release notes, fsd beta v11(April 5, 2022) has been updated and optimized in the following aspects:

Enable FSD Beta on expressway. FSD Beta's multi-camera video network and next generation planning system allow more complex agent interaction, reduce dependence on lanes, and pave the way for smarter behavior, smoother control and better decision-making.

Under the conditions of short-range obstacle recall and bad weather, the accuracy of the occupying network is improved. The spatial resolution of transformer is improved by 4 times, the image feature capacity is improved by 20%, the calibration of the side camera is improved, and 260,000 video training clips (both actual and simulated) are added.

The predicted speed error of motorcycles, scooters, wheelchairs and pedestrians in very close range is reduced by 63.6%.

The crawling contour is improved, and the acceleration at the beginning and end is increased.

By using the general static obstacle network to predict the continuous distance from static geometry, the control of nearby obstacles is improved.

By increasing the data set size of 14%, the error rate of vehicle "parking" attribute is reduced by 17%, and the accuracy of brake lights is also improved.

By adjusting the loss function, the performance of difficult scenes is improved, the speed error of clear scenes is increased by 5%, and the speed error of expressway scenes is increased by 10%.

The detection and control of opening the car door are improved.

When calculating the vehicle movement time, the optimization-based method is used to determine which lane routes have nothing to do with calculating the given lateral and longitudinal acceleration and steep slope limit, thus improving the turning comfort.

Ethernet data transmission pipeline optimization 15% improves the stability of FSD UI visualization.

The recall rate of vehicles behind ego is improved, and the accuracy of vehicle detection network is improved.

According to the "hot list" data of Easy Car App, Tesla (imported) ranks 89th among all brands. If you need more data, please visit the Easy Car App.