Tesla has reportedly initiated the deployment of its Full Self-Driving (FSD) Beta version 11.4.4, as unveiled through the release notes of the latest update. Earlier last week, accounts from Tesla’s FSD Beta tester fleet indicated an escalated release of version 11.4.3. Responding to user reports, CEO Elon Musk confirmed that FSD Beta V11.4.4 would be making its way to users by the end of the week.
Although FSD Beta V11.4.4 appears to be a minor update succeeding V11.4.3, the release notes indicate a series of notable enhancements. Among the highlighted improvements are refined maneuvering during lane changes with tight deadlines and enhanced handling of oncoming vehicles on narrow, unmarked roads.
FSD Beta 11.4.4 starting to roll out! With new release notes! #FSDBeta
11.4.3 has been awesome for me, excited to try this out. https://t.co/N0zrLeOIh5
— Dirty Tesla (@DirtyTesLa) June 19, 2023
The progress achieved by Tesla’s FSD Beta fleet has been nothing short of remarkable. Since its launch in October 2020, the company’s pool of testers has amassed an impressive milestone of over 150 million miles driven in real-world conditions, as revealed in Tesla’s Q1 2023 Update Letter. With the tester fleet continuously expanding, it is anticipated that the cumulative mileage of the FSD Beta program will experience even more significant growth in the forthcoming months.
Following are the release notes of Tesla’s FSD Beta V11.4.4 update:
- Improved short-deadline lane changes, to avoid going off-route, through better modeling of target lane vehicles to improve gap selection assertiveness.
- Improved offset consistency when controlling for static obstacles. Also improved smoothness when changing offset direction by adjusting speed more comfortably.
- Improved handling of oncoming cars on narrow unmarked roads by improving prediction of oncoming car’s trajectory and leaving enough room for them to pass before re-centering.
- Improved Occupancy Flow prediction from the Occupancy Network for arbitrary moving obstacles by 8%.
- Expanded usage of the new object ground truth autolabeler for the NonVRU detection model, improving distant vehicle recall and geometry precision for semi-trucks, trailers, and exotic vehicles.
- Improved VRU control by expanding planning scope to control gently for low-confidence detections that may interfere with ego’s path.
- Improved handling for VRUs near crosswalks by predicting their future intent more accurately. This was done by leveraging more kinematic data to improve association between crosswalks and VRUs.
- Improved ego’s behavior near VRUs by tuning their assumed kinematic properties and utilizing available semantic information to classify more accurately their probability of intersecting ego’s path.
- Improved Automatic Emergency Braking recall in response to cut-in vehicles and vehicles behind ego while reversing.
