The release notes for version 10.11 of Tesla’s fully self-driving beta 10.11 hint at a number of critical improvements for advanced driver assistance software. Tesla FSD Beta 10.11 is being rolled out to Tesla employees at this time. However, if the system works well, external users should receive the update in the next few days.
There are several notable improvements described in the FSD Beta v10.11 release notes. Tesla said V10.11 uses more accurate predictions of where other vehicles are turning or merging, reducing unnecessary slowdowns. The company also said that V10.11 should improve understanding of vehicle right-of-way, which should be invaluable in scenarios where maps turn out to be inaccurate.
Most importantly, FSD Beta V10.11 featured specific enhancements for Vulnerable Road Users (VRUs). Tesla notes that the most recent version of FSD Beta is expected to improve VRU detection by 44.9%, allowing the system to significantly reduce “false positive pedestrians and bicycles.” The company was able to achieve these VRU improvements by increasing the size of its next-generation label makers.
Here are FSD Beta v10.11 release notes.
Early Access Program | FSD beta 10.11
– Improved modeling of lane geometry from dense (“bag of points”) rasters to an autoregressive decoder that directly predicts and connects “vector space” lanes point by point using a neural network transformer. This allows us to predict crossover pathways, enables less expensive and less error-prone post-processing, and paves the way for the prediction of many other signals and their relationships jointly and end-to-end.
– Use more accurate predictions of where vehicles turn or merge to reduce unnecessary slowdowns for vehicles that won’t cross our path.
– Better understanding of the right-of-way if the map is inaccurate or the car cannot follow the navigation. In particular, intersection extent modeling is now entirely based on network predictions and no longer uses map-based heuristics.
– Improved accuracy of VRU detections by 44.9%, significantly reducing false positives for pedestrians and bicycles (especially around tar seams, skid marks and raindrops). This was accomplished by increasing the data size of the next-generation automatic labeler, training network parameters that were previously frozen, and modifying network loss functions. We find that this decreases the incidence of VRU-related false slowdowns.
– 63.6% reduction in the predicted speed error of motorcycles, scooters, wheelchairs and very close pedestrians. To do so, we introduced a new dataset of simulated adversarial high-speed VRU interactions. This update improves autopilot control around fast moving and activating VRUs.
– Improved creep profile with higher jerk at the start of creep.
– Improved nearby obstacle control by predicting continuous distance to static geometry with general static obstacle network.
– Reduced “parked” vehicle attribute error rate by 17%, achieved by increasing dataset size by 14%.
– Improved light-to-go scenario speed error by 5% and highway scenario speed error by 10%, achieved by adjusting the loss function to improve performance in difficult scenarios.
– Improved detection and control of open car doors.
– Improved smoothness in turns by using an optimization-based approach to decide which road lines are irrelevant for control given lateral and longitudinal acceleration and jerk limits as well as vehicle kinematics .
– Improved the stability of FSD Ul visualizations by optimizing the Ethernet data transfer pipeline by 15%.
Tesla FSD Beta v10.11 will probably be released as software version number 2022.4.5.15, according to reports from the EV community online. Tests of v10.11’s performance on real-world roads are typically shared by members of the company’s FSD Beta program within hours of the system’s large-scale release.
The Teslarati team would appreciate hearing from you. If you have any advice, contact me at [email protected] or through Twitter @Writer_01001101.