The 10.11 release notes for Tesla’s Full Self-Driving Beta Beta 10.11 point to a number of significant improvements to the advanced driver assistance program. The Tesla FSD Beta 10.11 is rolling out to Tesla employees right now. However, if the system is performing well, external users should receive the update within the next days.
There are several notable improvements described in the release notes for FSD Beta v10.11. Tesla mentioned that V10.11 uses More accurate predictions Where other vehicles turn or merge, reducing unnecessary decelerations. The company also stated that V10.11 should improve vehicles’ understanding of the right of way, which should be invaluable in scenarios when maps are imprecise.
Most importantly, FSD Beta V10.11 specifically appeared Improvements for Vulnerable Road Users (VRU). Tesla notes that the latest version of the FSD Beta should improve VRU detection by 44.9%, allowing the system to reduce “pseudo-positive pedestrians and bikes”. The company was able to achieve these VRU improvements by scaling up next generation labels.
Below is FSD Beta v10.11’s Release Notes.
Early Access Program | FSD Beta 10.11.2 Update
Improved lane architecture modeling from a dense raster (“bag of points”) to a self-regressive decoder that predicts and directly connects point-to-point “vector space” lanes using a neural network of transformers. This enables us to predict cross-lanes, allows for computationally cheaper and less error-prone subsequent processing, and paves the way for predicting many other signals and their relationships jointly and comprehensively.
– Use more accurate predictions of where vehicles will turn or merge to reduce unnecessary deceleration for vehicles that will not cross our path.
– Improved understanding of the right of way if the map is inaccurate or the vehicle cannot follow the navigation. In particular, modeling intersection ranges are now entirely based on network predictions and no longer use map-based inference methods.
– The accuracy of VRU detections is improved by 44.9%, significantly reducing false positive pedestrians and bicycles (especially around tar layers, slip marks and raindrops). This was achieved by increasing the data volume of the next generation of automatic labeling tool, training previously frozen network parameters, and modifying network loss functions. We find that this reduces the incidence of VRU-related pseudohysteresis.
Reducing the expected speed error of motorcycles, scooters, wheelchairs and pedestrians who are too close by 63.6%. To do this, we presented a new data set to simulate high-speed VRU interactions for antagonism. This update improves the autopilot control around fast-moving and cutting VRUs.
– Improved crawler profile with higher jerk when starting to crawl.
– Improved control of nearby obstacles by predicting the continuous distance of static geometry with the general static obstacle network.
Reducing the vehicle’s “stopped” error rate by 17%, by increasing the size of the data set by 14%.
– The ‘clear-to-go’ scenario speed error of 5% and the highway scenario speed error of 10% has been improved, which is achieved by adjusting the loss function targeting performance improvement in challenging scenarios.
– Improved detection and control of open car doors.
– Improved smoothness during cornering using an optimization-based approach to identify road lines unrelated to control due to lateral and longitudinal acceleration and vibration limits as well as vehicle kinematics.
Improved stability of FSD Ul visualizations by improving the Ethernet data transmission pipeline by 15%.
Tesla FSD Beta v10.11 is likely to be released as Software version number 2022.4.5.15, according to reports from the online electric car community. 10.11 performance tests in real-world ways are typically shared by members of the company’s FSD Beta program within hours of a system wide release.
The Teslarati team would be grateful to contact you. If you have any tips, contact me at [email protected] or via Twitter @Writer_01001101.
“Web aficionado. Travel guru. Zombie enthusiast. Proud music scholar. Social media buff. Internet fanatic. Writer. Pop culture expert.”