Tesla launches new full self-driving beta update with improved object detection – .

0
21
Tesla launches new full self-driving beta update with improved object detection – .


Tesla has started offering a new Full Self-Driving Beta software update (version 10.6) to its fleet with improved object detection.

This is the last step in a long road to improve the FSD package and deliver on a promise to customers that has been repeatedly delayed.

Tesla is now slowly rolling out what it calls Full Self-Driving Beta (FSD Beta), which is an early version of its autonomous driving software currently being tested by a fleet of company-selected Tesla owners and through its ‘test drive’. Security Goal. “

The software allows the vehicle to drive autonomously to a destination entered into the car’s navigation system, but the driver must remain alert and ready to take control at all times.

Since the responsibility lies with the driver and not with Tesla’s system, it is still considered a Level 2 driver assistance system despite its name. It was sort of a ‘two step forward, one step back’ type of program, as some updates have seen regressions in terms of driving ability.

In the latest updates, the automaker has released more details about the changes to driving behaviors in the release notes.

Last month we reported on the FSD 10.5 update with the release notes.

Today, Tesla begins offering a new version of the Full Self-Drive Beta to owners in the United States with a safety score of 98 and above.

Tesla wrote about the changes to version 10.6 in the release notes:

  • Improved object detection network architecture for non-VRUs (eg cars, trucks, buses). 7% higher recall. 16% lower depth error and 21% lower speed error for passing vehicles.
  • New visibility network with an average relative error of 18.5% less.
  • New general static object array with 17% accuracy improvements in high curvature and at night.
  • Improved stopping position in unprotected left turns while yielding to oncoming objects, using predictions of objects beyond the crossing point.
  • Leave more room for longitudinal alignment during fusions by incorporating modeling of the end of the fusion region.
  • Improved comfort when shifting for objects that intersect your lane.

The automaker has indicated that the improvement rate will increase with its Dojo supercomputer.

Earlier this week, we reported that Tesla released new images of its automatic tagging tool for its self-driving efforts.

With Auto Tagging and Dojo combined, we might start to see this rate of improvement accelerated.

FTC: We use automatic affiliate links which generate income. Suite.


Subscribe to Electrek on YouTube for exclusive videos and subscribe to the podcast.

LEAVE A REPLY

Please enter your comment!
Please enter your name here