Connect with us
Tesla-fsd-10.3-release Tesla-fsd-10.3-release

News

Tesla FSD Beta 10.69 release notes highlight better left turns, smoother driving

(Credit: Tesla)

Published

3 years ago

on

Tesla released FSD Beta 10.69 to the first round of testers over the weekend. Read v.10.69’s release notes below to check out the latest improvements. 

Stay in your Lanes

  • Added a new “deep lane guidance” module to the Vector Lanes neural network which fuses features extracted from the video streams with coarse map data, i.e. lane counts and lane connectivites. This architecture achieves a 44% lower error rate on lane topology compared to the previous model, enabling smoother control before lanes and their connectivities becomes visually apparent. This provides a way to make every Autopilot drive as good as someone driving their own commute, yet in a sufficiently general way that adapts for road changes.

 Nothing Like Smooth Driving

  • Improved overall driving smoothness, without sacrificing latency, through better modeling of system and actuation latency in trajectory planning. Trajectory planner now independently accounts for latency from steering commands to actual steering actuation, as well as acceleration and brake commands to actuation. This results in a trajectory that is a more accurate model of how the vehicle would drive. This allows better downstream controller tracking and smoothness while also allowing a more accurate response during harsh manevuers.
  • Increased smoothness for protected right turns by improving the association of traffic lights with slip lanes vs yield signs with slip lanes. This reduces false slowdowns when there are no relevant objects present and also improves yielding position when they are present.
  • Reduced false slowdowns near crosswalks. This was done with improved understanding of pedestrian and bicyclist intent based on their motion.
  • Enabled creeping for visibility at any intersection where objects might cross ego’s path, regardless of presence of traffic controls.
  • Improved accuracy of stopping position in critical scenarios with crossing objects, by allowing dynamic resolution in trajectory optimization to focus more on areas where finer control is essential.
  • Reduced latency when starting from a stop by accounting for lead vehicle jerk.

Chuck’s Left Turn

  • Improved unprotected left turns with more appropriate speed profile when approaching and exiting median crossover regions, in the presence of high speed cross traffic (“Chuck Cook style” unprotected left turns). This was done by allowing optimizable initial jerk, to mimic the harsh pedal press by a human, when required to go in front of high speed objects. Also improved lateral profile approaching such safety regions to allow for better pose that aligns well for exiting the region. Finally, improved interaction with objects that are entering or waiting inside the median crossover region with better modeling of their future intent.

Safety is Number 1

  • Added control for arbitrary low-speed moving volumes from Occupancy Network. This also enables finer control for more precise object shapes that cannot be easily represented by a cuboid primitive. This required predicting velocity at every 3D voxel. We may now control for slow-moving UFOs.
  • Made speed profile more comfortable when creeping for visibility, to allow for smoother stops when protecting for potentially occluded objects.
  • Improved speed when entering highway by better handling of upcoming map speed changes, which increases the confidence of merging onto the highway.
  • Enabled faster identification of red light runners by evaluating their current kinematic state against their expected braking profile.

Tesla FSD “Brain” Improvements

  • Upgraded Occupancy Network to use video instead of images from single time step. This temporal context allows the network to be robust to temporary occlusions and enables prediction of occupancy flow. Also, improved ground truth with semantics-driven outlier rejection, hard example mining, and increasing the dataset size by 2.4x.
  • Upgraded to a new two-stage architecture to produce object kinematics (e.g. velocity, acceleration, yaw rate) where network compute is allocated O(objects) instead of O(space). This improved velocity estimates for far away crossing vehicles by 20%, while using one tenth of the compute.
  • Improved geometry error of ego-relevant lanes by 34% and crossing lanes by 21% with a full Vector Lanes neural network update. Information bottlenecks in the network architecture were eliminated by increasing the size of the per-camera feature extractors, video modules, internals of the autoregressive decoder, and by adding a hard attention mechanism which greatly improved the fine position of lanes.
  • Improved recall of animals by 34% by doubling the size of the auto-labeled training set.
  • Increased recall of forking lanes by 36% by having topological tokens participate in the attention operations of the autoregressive decoder and by increasing the loss applied to fork tokens during training.
  • Improved velocity error for pedestrians and bicyclists by 17%, especially when ego is making a turn, by improving the onboard trajectory estimation used as input to the neural network.
  • Improved recall of object detection, eliminating 26% of missing detections for far away crossing vehicles by tuning the loss function used during training and improving label quality.
  • Improved object future path prediction in scenarios with high yaw rate by incorporating yaw rate and lateral motion into the likelihood estimation. This helps with objects turning into or away from ego’s lane, especially in intersections or cut-in scenarios.

Tesla is rolling out FSD Beta v.10.69 in phases, starting with ~1,000 testers over the weekend. Once the update is rolled out for wide release, the price of FSD Beta will increase.

The Teslarati team would appreciate hearing from you. If you have any tips, contact me at maria@teslarati.com or via Twitter @Writer_01001101.

Related Topics:

Maria--aka "M"-- is an experienced writer and book editor. She's written about several topics including health, tech, and politics. As a book editor, she's worked with authors who write Sci-Fi, Romance, and Dark Fantasy. M loves hearing from TESLARATI readers. If you have any tips or article ideas, contact her at maria@teslarati.com or via X, @Writer_01001101.

Advertisement
Comments

Elon Musk

Elon Musk reveals when SpaceX will perform first-ever Starship catch

“Starship catch is probably flight 13 to 15, depending on how well V3 flights go,” Musk said.

Published

4 hours ago

on

August 28, 2025

By

Credit: SpaceX

Elon Musk revealed when SpaceX would perform the first-ever catch attempt of Starship, its massive rocket that will one day take life to other planets.

On Tuesday, Starship aced its tenth test flight as SpaceX was able to complete each of its mission objectives, including a splashdown of the Super Heavy Booster in the Gulf, the deployment of eight Starlink simulators, and another splashdown of the ship in the Indian Ocean.

It was the first launch that featured a payload deployment:

SpaceX Starship Flight 10 was so successful, it’s breaking the anti-Musk narrative

SpaceX was transparent that it would not attempt to catch the Super Heavy Booster, something it has done on three previous occasions: Flight 5 on October 13, 2024, Flight 7 on January 16, and Flight 8 on March 6.

This time, it was not attempting to do so. However, there are bigger plans for the future, and Musk detailed them in a recent post on X, where he discussed SpaceX’s plans to catch Starship, which would be a monumental accomplishment.

Musk said the most likely opportunities for SpaceX to catch Starship itself would be Flight 13, Flight 14, and Flight 15, but it depends on “how well the V3 flights go.”

The Starship launched with Flight 10 was a V2, which is the same size as the subsequent V3 rocket but has a smaller payload-to-orbit rating and is less powerful in terms of initial thrust and booster thrust. Musk said there is only one more V2 rocket left to launch.

V3 will be the version flown through 2026, as V4, which will be the most capable Starship build SpaceX manufactures, is likely to be the first company ship to carry humans to space.

Musk said that SpaceX planned to “hopefully” attempt a catch of Starship in 2025. However, it appears that this will likely be pushed back to 2026 due to timing.

SpaceX will take Starship catch one step further very soon, Elon Musk confirms

SpaceX would need to launch the 11th and 12th test flights by the end of the year in order to get to Musk’s expected first catch attempt of Flight 13. It’s not unheard of, but the company will need to accelerate its launch rate as it has only had three test flights this year.

Continue Reading

News

Tesla Robotaxi rival Waymo confirms massive fleet expansion in Bay Area

New data from the California Public Utilities Commission (CPUC) said Waymo had 1,429 vehicles operating in California, and 875 of them were “associated with a terminal in San Francisco,” according to The SF Examiner.

Published

7 hours ago

on

August 28, 2025

By

Credit: Uber

Tesla Robotaxi rival Waymo has confirmed that it has expanded its fleet of driverless ride-sharing vehicles in the Bay Area of California massively since its last public disclosure.

It is perhaps one of the most important metrics in the race for autonomous supremacy, along with overall service area. Tesla has seemed to focus on the latter, while expanding its fleet slowly to maintain safety.

Waymo, on the other hand, is bringing its fleet size across the country to significant levels. In March, it told The SF Examiner that there were over 300 Waymos in service in the San Francisco area, which was not a significant increase from the 250 vehicles on the road it reported in August 2023.

In May, the company said in a press release that it had more than 1,500 self-driving Waymos operating nationwide. More than 600 were in the San Francisco area.

Tesla analyst compares Robotaxi to Waymo: ‘The contrast was clear’

However, new data from the California Public Utilities Commission (CPUC) said Waymo had 1,429 vehicles operating in California, and 875 of them were “associated with a terminal in San Francisco,” according to The SF Examiner.

CPUC data from March 2025 indicated that there were a total of 1,087 Waymo vehicles in California, with 762 located in San Francisco. Some were test vehicles, others were deployed to operate as ride-sharing vehicles.

The company’s August update also said that it deploys more than 2,000 commercial vehicles in the United States. That number was 1,500 in May. There are also roughly 400 in Phoenix and 500 in Los Angeles.

While Waymo has done a good job of expanding its fleet, it has also been able to expand its footprint in the various cities it is operating in.

Most recently, it grew its geofence in Austin, Texas, to 90 square miles. This outpaced Tesla for a short period before the company expanded its Robotaxi service area earlier this week to roughly 170 square miles.

Tesla one-ups Waymo once again with latest Robotaxi expansion in Austin

The two companies have drastically different approaches to self-driving, as Waymo utilizes LiDAR, while Tesla relies solely on cameras for its suite. Tesla CEO Elon Musk has made no mistake about which he believes to be the superior solution to autonomy.

Continue Reading

News

Tesla launches Full Self-Driving in a new region

Today, Tesla launched Full Self-Driving in Australia for purchase by car buyers for $10,100, according to Aussie automotive blog Man of Many, which tried out the suite earlier this week.

Published

8 hours ago

on

August 28, 2025

By

Credit: Tesla

Tesla has launched its Full Self-Driving suite in a new region, marking a significant step in the company’s progress to expand its driver assistance suite on a global scale.

It is also the first time Tesla has launched FSD in a right-hand-drive market.

Today, Tesla launched Full Self-Driving in Australia for purchase by car buyers for $10,100, according to Aussie automotive blog Man of Many, which tried out the suite earlier this week.

Previously, Basic and Enhanced Autopilot suites were available, but the FSD capability now adds Traffic Light and Stop Sign Control, along with all the features of the previous two Autopilot suites.

It is the first time Tesla has launched the suite by name in a region outside of North America. In China, Tesla has “City Autopilot,” as it was not permitted to use the Full Self-Driving label for regulatory reasons.

However, Tesla still lists Full Self-Driving (Supervised) as available in the U.S., Canada, China, Mexico, and Puerto Rico.

The company teased the launch of the suite in Australia earlier this week, and it appeared to have been released to select media members in the region earlier this week:

Tesla FSD upcoming Australia release seemingly teased bv media

The rollout of Full Self-Driving in the Australian market will occur in stages, as Model 3 and Model Y vehicles with Hardware 4 will receive the first batch of FSD rollouts in the region.

TechAU also reported that “the initial deployment of FSDs in Australia will roll out to a select number of people outside the company, these people are being invited into Tesla’s Early Access Program.”

Additionally, the company reportedly said it is “very close” to unlocking FSD in customer cars:

Each new Tesla sold will also come with a 30-day free trial of the suite.

Australia is the sixth country to officially have Full Self-Driving available to them, following the United States, Canada, China, Mexico, and Puerto Rico.

Here’s the first look at the suite operating in Australia:

Continue Reading

Trending