Tesla’s Full Self-Driving beta 10.11 appears to have started its rollout to Early Access Program testers. Screenshots of the FSD beta 10.11 release notes were shared on Sunday by @WholeMarsBlog.
Upgraded modelling 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, modelling 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 VRU interactions. This update improves Autopilot control around fast-moving and cutting-in VRUs.
Improved creeping profile with higher jerk when creeping starts and 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%, achieved by 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 function 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 control
given lateral and longitudinal acceleration and jerk limits as well as vehicle kinematics.
Improved stability of the FSD UI visualizations by optimizing the ethernet data transfer pipeline by 15%
If this version performs well, we can probably lower min safety score to 95
Tesla has announced that the design and engineering details of the original Tesla Roadster are now fully open source. The announcement, made by CEO Elon Musk on Wednesday, signifies a major shift in Tesla’s approach to its proprietary technology. Musk revealed that all of the design and engineering information related to the first Tesla Roadster […]
I find it truly hilarious that almost a year after Tesla’s legendary October 6th leaks, Tesla has done it yet again. I really do hope this becomes an annual trend, but Tesla hasn’t updated the Find Us map in months, so I’m not going to hold my breath. As for me, this isn’t my long […]
The Quebec Superior Court in Quebec, Canada, has authorized two class action lawsuits against Tesla, as confirmed by law firms in Montreal and Granby on Wednesday. The suits received approval last September and target specific issues related to Tesla’s Model 3 and Model Y vehicles. In the first lawsuit, the plaintiff alleges that Tesla Models […]