FSD beta 10.12 visualization of car with open door / @WholeMarsBlog
After Tesla’s Full Self-Driving (FSD) beta 10.12 started rolling out yesterday to employees (as part of the 2022.12.3.10 update), we now have the release notes, as shared by @WholeMarsBlog.
FSD beta 10.12 release notes detail better decision-making for unprotected left turns, improved creeping for visibility, plus upgraded visualizations for vehicles with car doors open, to name a few of the many upgrades.
Tesla CEO Elon Musk replied this morning, “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,” replying to @WholeMarsBlog. Check out the full FSD beta 10.12 release notes below that we helped type out for your reading pleasure:
- 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.
- Improved 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 auto labeled data to the training set.
- Improved 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.
- Improved 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.
- Improved 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
- Improved angular velocity and lane-centric velocity for non-VRL 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.
Back on May 10, Musk said “release notes on this version will be long,” and seeing the details above, yes he was indeed correct. Musk previously stated the Tesla team was “working the weekend to get 10.12 in limited release” for Sunday. Obviously, the release date was delayed as it wasn’t out Sunday, but here we are. Expect FSD beta 10.12 videos to pop up on YouTube soon.
