Tesla Begins Wider Release of FSD Beta 11.3.2 with Improved Driving Behaviors and Detection Accuracy


Tesla has launched v11 of its Full Self-Driving (FSD) Beta program: The electric vehicle giant has been testing the software with a limited group of users, mostly employees and long-standing testers, since late last year. However, the latest rollout is expected to be much broader in scope.

According to reports, Tesla is releasing FSD Beta v11.3.2 to more vehicles, making it available to more drivers. The automaker has been rolling out the beta software gradually, allowing it to monitor its performance on a small scale and address any bugs or issues that arise.

FSD Beta v11 has been highly anticipated by Tesla fans and owners, as it promises to bring the company one step closer to fully autonomous driving. However, as with any beta software, there are still many kinks to work out, and Tesla is taking a cautious approach to ensure that the rollout is successful.

Tesla Begins Wider Release of FSD Beta 11.3.2
Tesla Begins Wider Release of FSD Beta 11.3.2

Improved Highway and Inner-City Street Navigation

Users who have access to the latest FSD Beta v11.3.2 have reported several improvements, especially related to highway driving. For instance, Tesla has unified its vision and planning stack for both on and off-highway driving, replacing the legacy highway stack that was over four years old.

The FSD Beta program’s multi-camera video networks and next-gen planner allow for more complex agent interactions with less reliance on lanes, which in turn makes way for adding more intelligent behaviors, smoother control, and better decision-making.

Moreover, inner-city street navigation has also been refined to improve accuracy, making for a safer and more seamless driving experience. https://twitter.com/DriveTeslaca/status/1637452399924355072

Enhancements for Improved Recall and Handling

Tesla has worked on several areas to enhance vehicle safety and optimize the driving experience. For instance, there has been improved recall for close-by cut-in cases, which is vital for avoiding accidents, particularly for large trucks and high-yaw rate scenarios.

The automaker has also improved the position of the car’s ego in wide lanes, allowing other cars to maneuver around it safely. Additionally, Tesla has worked on improving handling during high curvature or large truck scenarios by offsetting the lane to maintain safe distances and increase comfort.

Improved Lane Changes, Smoother Turns, and Accurate Object Detection

Tesla has also worked on improving lane changes in dense traffic scenarios by allowing higher acceleration during the alignment phase. This results in more natural gap selection to overtake adjacent lane vehicles very close to ego. Moreover, turns are now smoother, thanks to improved detection consistency between lanes, lines, and road edge predictions.

Furthermore, Tesla has enhanced the recall and precision of object detection by improving the video context in the network, adding more data, and increasing the loss penalty for control-relevant vehicles. Motorbikes have also been included, with the recall improved by 5%.

Final Thoughts

The latest rollout of Tesla’s Full Self-Driving Beta program v11.3.2 promises to bring significant improvements to vehicle safety and automation. Although the software is still in its beta phase, Tesla’s attention to detail and commitment to safety are evident in the improvements made to the software.

As more drivers gain access to FSD Beta v11.3.2, it will be interesting to observe how the software performs and how Tesla will adjust it based on feedback from drivers. Nonetheless, the latest release could be a significant milestone for the electric vehicle industry, moving it closer to the vision of truly autonomous vehicles.


Please enter your comment!
Please enter your name here