Canadian Full Self-Driving (FSD) Beta testers in Canada received their first update this morning with the release of 2022.4.5.21.
The update was released at the same time in both Canada and the US, setting a good precedent moving forward that Canadians should expect to receive FSD Beta updates at the same time as our counterparts south of the border.
Unfortunately it does not look like this release adds more owners to the testing program.
FSD Beta update rolling out simultaneously in canada and the US with 2022.4.5.21
If you’re getting this update for the first time let us know what your Safety Score is. pic.twitter.com/IzsLcD2Plw
— Drive Tesla 🇨🇦 (@DriveTeslaca) April 4, 2022
According to the release notes, there are no major changes to this version as they remain unchanged from the original 10.11 release several weeks ago.
The biggest change though is that if your Boombox wasn’t already disabled while in Drive, it is now.
2022.4.5.21 Release Notes
Upgraded modeling of lane geometry from dense rasters (“bag of points”) to an autoregressive decoder that directly predicts and connects “vector space” lanes point by point using a transformer neural network. This enables us to predict crossing lanes, allows computationally cheaper and less error prone post-processing, and paves the way for predicting many other signals and their relationships jointly and end-to-end.
Use more accurate predictions of where vehicles are turning or merging to reduce unnecessary slowdowns for vehicles that will not cross our path.
Improved right-of-way understanding if the map is inaccurate or the car cannot follow the navigation. In particular, modeling intersection extents is now entirely based on network predictions and no longer uses map-based heuristics.
Improved the precision of VRU detections by 44.9%, dramatically reducing spurious false positive pedestrians and bicycles (especially around tar seams, skid marks, and rain drops). This was accomplished by increasing the data size of the next-gen autolabeler, training network parameters that were previously frozen, and modifying the network loss functions. We find that this decreases the incidence of VRU-related false slowdowns.
Reduced the predicted velocity error of very close-by motorcycles, scooters, wheelchairs, and pedestrians by 63.6%. To do this, we introduced a new dataset of simulated adversarial high speed VI interactions. This update improves autopilot control around fast-moving and cutting-in VRUs.
Improved creeping profile with higher jerk when creeping stand ends.
Improved control for nearby obstacles by predicting continuous distance to static geometry with the general static obstacle network.
Reduced vehicle “parked” attribute error rate by 17%, achieve increasing the dataset size by 14%. Also improved brake light accuracy.
Improved clear-to-go scenario velocity error by 5% and highway scenario velocity error by 10%, achieved by tuning loss functions targeted at improving performance in difficult scenarios.
Improved detection and control for open car doors.
Improved smoothness through turns by using an optimization based approach to decide which road lines are irrelevant for c ? given lateral and longitudinal acceleration and jerk limits as w? vehicle kinematics.
Improved stability of the FSD Ul visualizations by optimizing ethernet data transfer pipeline by 15%.
Improved recall for vehicles directly behind ego, and improved precision for vehicle detection network.
