Over the weekend Tesla released the next versionĀ of their Full Self-Driving (FSD) Beta software, V10.3, to both existing and new testers who had achieved a Safety Score of 99.
The release was short lived, with Tesla rolling back on Sunday morning to a production build without FSD Beta. The rollback was due to several issues found through feedback from the testers.
Tesla’s FSD team worked overtime on Sunday and early on Monday morning CEO Elon Musk announced V10.3.1 was already being deployed.
10.3.1 rolling out now
— Elon Musk (@elonmusk) October 25, 2021
Some of the bugs that were present in V10.3 that are supposed to be fixed in 10.3.1 include the inability to engage Autopilot and sudden hard braking due to false front collision warnings.
Despite the announcement by Musk early this morning, the new software only appears to be rolling out to more owners at around 9:00am PST through software update 2021.36.5.3.
Beta 13.1 incoming (2021.36.5.3)
— Mark (@CodingMark) October 25, 2021
Here are the release notes from V10.3.
FSD v10.3 Release Notes
- Added FSD profiles that 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 maneuver 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 surround video vehicle network with more data. Also increased system frame rate by +1.7 frames per second.
- Improved vehicle semantic detections (e.g. brake lights, turn indicators, hazards) by adding +25k video clips to the training data set.
- Improved static obstacle control by upreving the generalized static object network with 6l more video clips (+5.6% prevision, +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.