According to the latest report, Tesla released a new software update. Recently, Tesla released the version number 2022.40.4 update. According to the latest report, Tesla today released the Tesla FSD Beta 11 update to the testers.
As per the Elon Musk statement, Tesla will have a wide rollout to more North American users in a few weeks. Previously, Musk confirmed that the FSD Beta 11 will use a single-stack system, so the FSD Beta 11 performance is smoother and its judgment more intelligent.
. You can check the complete release notes of this update below.
Join Us On Telegram & Add RMC to your Google News feed
Tesla FSD Beta 11 Update Release Notes:
- Enable FSD Beta on the highway.
- This unifies the vision and planning stack on and off the highway, and replaces the four-year-old legacy highway stack. Traditional highway stacks still rely on several single-camera and single-frame networks and are set up to handle simple lane-specific operations. FSD Beta’s multi-camera video network and next-generation planning system allow for more complex agent interactions with fewer lane dependencies, making way for smarter behavior, smoother control, and better decision-making.
- Improved Occupancy Network accuracy for close obstacle recall and severe weather conditions, 4x higher transformer spatial resolution, 20% higher image featureizer capacity, improved side camera calibration, and increased 260,000 video training clips (both actual and simulated).
- Reduced predicted speed error by 63.6% for motorcycles, scooters, wheelchairs, and pedestrians at very close distances. To this end, we introduce a new dataset that simulates adversarial high-speed VRU interactions. This update improves the autopilot control system around fast moving and cutting the VRU.
- Improved creeping profile, increased acceleration at start and end.
- Improved control of nearby obstacles by predicting continuous distances from static geometry using a general static obstacle network.
- By increasing the data set size by 14%, the error rate of the vehicle “parked” attribute was reduced by 17%, while also improving the accuracy of brake lights.
- The performance of difficult scenes is improved by adjusting the loss function, which improves the speed error of clear scenes by 5% and the speed error of highway scenes by 10%.
- Improved detection and control of opening doors.
- When calculating vehicle kinematics, cornering smoothness is improved by using an optimization-based approach to decide which road lines are irrelevant to the calculation for a given lateral and longitudinal acceleration and steep rise limit.
- Improved the stability of the FSD UI visualization by optimizing the Ethernet data transfer pipeline by 15%.
- Improved recall of vehicles behind the ego and improved vehicle detection network accuracy.
FSD Beta on Highway 🛣️ pic.twitter.com/ou0M3Md7av
— HH (@husseinhamdan_) November 12, 2022