Tesla Starts Rollout of FSD Beta V10.12 with Dramatic Improvements, First to Employees

Image: @WholeMarsBlog/Twitter

Tesla has begun rolling out Tesla FSD Beta V10.12 to employees, with dramatic improvements that bring the manufacturer even closer to achieving autonomous driving. If the testing is successful, then, starting with version 10.12.2 or 10.13, the update will be distributed to owners with a safety score of 95+.

The Tesla Full Self-Driving Beta V10.12 update is now rolling out to employees. According to CEO Elon Musk, it contains many improvements to the autonomous driving code, which will lead to the discovery of new behaviors during testing. Therefore, employees should thoroughly test the update to make sure it works and make the appropriate corrections, if necessary. The head of the company explained that at the moment there is something like two steps forward and one step back, so we should expect some slowdown in progress, but eventually which will bring significant improvements.

This is a big one! Expect some two steps forward, one step back situations. These will be great ironed in point releases, hence ~10.12.2 or 10.13 for wider beta release.

— Elon Musk (@elonmusk) May 19, 2022

The Tesla FSD 10.12 beta release notes have been posted by @WholeMarsBlog/Twitter, and contain a lot of interesting information pointing to the manufacturer's new achievements. A list of all improvements can be found below.

FSD Beta v10.12 Release Notes

• Upgraded decision making framework for unprotected left turns with better modeling of objects' response to ego's actions by adding more features that shape the go/no-go decision. This increases robustness to noisy measurements while being more sticky to decisions within a safety margin. The framework also leverages median safe regions when necessary to maneuver across large turns and accelerating harder through maneuvers when required to safely exit the intersection.
• Improved creeping for visibility using more accurate lane geometry and higher resolution occlusion detection.
• Reduced instances of attempting uncomfortable turns through better integration with object future predictions during lane selection.
• Upgraded planner to rely less on lanes to enable maneuvering smoothly out of restricted space.
• Increased safety of turns with crossing traffic by improving the architecture of the lanes neural network which greatly boosted recall and geometric accuracy of crossing lanes.
• Improved the recall and geometric accuracy of all lane predictions by adding 180k video clips to the training set.
• Reduced traffic control related false slowdowns through better integration with lane structure and improved behavior with respect to yellow lights.
• Improved the geometric accuracy of road edge and line predictions by adding a mixing/coupling layer with the generalized static obstacle network.
• lmproved geometric accuracy and understanding of visibility by retraining the generalized static obstacle network with improved data from the autolabeler and by adding 30k more videos clips.
• Improved recall of motorcycles, reduced velocity error of close-by pedestrians and bicyclists, and reduced heading error of pedestrians by adding new sim and autolabeled data to the training set.
• lmproved precision of the "is parked" attribute on vehicles by adding 41k clips to the training set. Solved 48% of failure cases captured by our telemetry of 10.11.
• lmproved detection recall of far-away crossing objects by regenerating the dataset with improved versions of the neural networks used in the autolabeler which increased data quality.
• lmproved offsetting behavior when maneuvering around cars with open doors.
• Improved angular velocity and lane-centric velocity for non-VRU objects by upgrading it into network predicted tasks.
• Improved comfort when lane changing behind vehicles with harsh deceleration by tighter integration between lead vehicles future motion estimate and planned lane change profile.
• Increased reliance on network-predicted acceleration for all moving objects, previously only longitudinally relevant objects.
• Updated nearby vehicle assets with visualization indicating when a vehicle has a door open.
• Improved system frame rate +1.8 frames per second by removing three legacy neural networks.

© 2022, Eva Fox | Tesmanian. All rights reserved.

_____________________________

We appreciate your readership! Please share your thoughts in the comment section below. 

Article edited by @SmokeyShorts, you can follow him on Twitter

Follow @EvaFoxU