Cleantech & EV'sNews

Tesla starts rolling out Full Self-Driving Beta 10.3 after a false start

Tesla has restarted the rollout of its Full Self-Driving Beta 10.3 update after a false start with a lot of bugs had them revert to the previous version.

Tesla FSD Beta 10.3 was supposed to come Friday, but the automaker’s internal QA found a problem with “left turns at traffic lights.”

The company has warned that the process of developing its self-driving technology is a “two step forward one step back” experience.

CEO Elon Musk said that it was fixed on Sunday, and Tesla started rolling out 10.3, but the update caused a log of problems to many FSD Beta testers.

The automaker decided to roll back the update while it figures out the problems.

Musk wrote on Twitter:

Please note, this is to be expected with beta software. It is impossible to test all hardware configurations in all conditions with internal QA (quality assurance), hence public beta.

It was apparently a quick fix, since this morning, Tesla started to push the FSD Beta 10.3 update again.

In the release notes of the update, Tesla lists the changes in the update:

  • Added FSD Profiles hat allow drivers to control behaviors like rolling stops, exiting passing lanes, speed-based lane changes, following distance and yellow light headway.
  • Added planning capability to drive along oncoming lanes to manauver around path blockage.
  • Improved creeping speed by linking speed to visibility network estimation and distance to encroachment point of crossing lanes.
  • Improved crossing object velocity estimation by 20% and yaw estimation by 25% by upreving surrond video vehicle network with more data. Also increased system frame rate by +1.7 per second.
  • Improved vehicle semantic detections (e.g. brake lights , turn indicators, hazards) by adding +25 video clips to the training data set.
  • Improved static obstacle control by upreving the generalized static object network with 6k more video clips (+5.6 precision, +2.5% recall).
  • Allowed more acceleration when merging from on-ramps onto major roads and when lane changing from slow to fast lanes.
  • Reduced false slowdowns and improved offsetting for pedestrians by improving the model of interaction between pedestrians and the static world.
  • Improved turning profile for unprotected turns by allowing ego to cross over lane lines more naturally, when safe to do so.
  • Improved speed profile for boosting onto high-speed roads by enforcing stricter longitudinal and lateral acceleration limits required to beat the crossing objects.

The update is now being pushed to the fleet again for people who already had access to the beta and also people who scored 99 out of 100 on the safety score.


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


Author: Fred Lambert
Source: Electrek

Related posts
AI & RoboticsNews

Hacking internal AI chatbots with ASCII art is a security team’s worst nightmare

AI & RoboticsNews

Microsoft launches new Azure AI tools to cut out LLM safety and reliability risks

AI & RoboticsNews

AI21 Labs juices up gen AI transformers with Jamba

DefenseNews

Northrop says Air Force design changes drove higher Sentinel ICBM cost

Sign up for our Newsletter and
stay informed!