One of the coolest features of a Tesla is the built-in self-driving system. With it, you can toggle between self-driving and manual mode, and the car does all the work. Tesla announced that they will be starting a beta program for their self-driving feature in October 2020. The company made the announcement in a blog post, saying that they are looking for volunteers to help them test the feature. Tesla says that the beta program will give people the opportunity to experience “the convenience of autonomous driving.” Participants in the program will be able to use Tesla’s full self-driving feature on public roads.
While this feature is still in beta, it’s already started improving day by day based on the data it collects from the Tesla owners. As part of the beta program, Tesla will also be collecting feedback from participants about how well the feature works.
Tesla FSD Beta 10.11 Enhancements
Tesla has been hard at work on their self-driving software and they have just released a new beta version 10.11. This new version is a big step forward for Tesla and for the self-driving car industry as a whole. The new beta includes some major updates that make the cars more autonomous than ever before. With this latest release, Tesla is one step closer to making its dream of a self-driving car a reality.
slightly better pics pic.twitter.com/KhWrZ7PrtP
— Whole Mars Catalog (@WholeMarsBlog) March 13, 2022
According to the release notes for Tesla’s latest FSD beta (10.11), there are some critical improvements in store. This includes a better understanding of the lane if the map is inaccurate, improved control for nearby obstacles, and more. With these enhancements, Tesla’s autonomous driving system should be getting even closer to perfection. As always, it will be interesting to see how these new features perform in the real world.
Tesla FSD Beta 10.11 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 raindrops). This was accomplished by increasing the data size of the next-gen auto-labeler, 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.
- 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%.
- 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 Ul visualizations by optimizing the ethernet data transfer pipeline by 15%.
Tesla’s Full Self-Driving Beta 10.11 update is a huge step forward for the company, and it will be interesting to see how the technology develops in the coming years.
Imagine paying the company to beta test which puts the passengers and vehicle at risk. Honestly they should be paying users for their data which helps them do modeling