Tesla FSD Beta V10.7 Release Notes Show Significant Improvements in Reducing False Cut-In Slowdowns

Image: not a tesla app

Tesla has released FSD Beta V10.7. The release notes show significant improvements in reducing false cut-in slowdowns and improving overall driving comfort. Although the release of an update to this version was not expected, it seems that the company decided to test some of the improvements before including them in V10.8.

Tesla has begun rolling out FSD Beta V10.7, which was no longer expected to be released. Last weekend, Tesla CEO Elon Musk tweeted that the company will release FSD Beta V10.8, presumably on Tuesday, and skip the V10.7 release. He pointed out that the newest version is almost complete, so there was no need for a V10.7 release. However, the manufacturer changed its plans and released V10.7, probably in order to test a number of important improvements before including them in V10.8.

10.8 is close, so just jumping to that

— Elon Musk (@elonmusk) December 18, 2021

The FSD Beta V10.7 release notes indicate that Tesla has placed particular emphasis on reducing false cut-in slowdowns and achieved a 50% improvement over the previous version. In addition, extended use of regenerative braking in Autopilot has been applied to 0 mph for smoother stops and improved energy efficiency. Improved behavior when crossing bike lanes and reacting to pedestrians has been added, as well as improved lane changes.

FSD Beta V10.7 Release Notes:

• Improved object attributes network to reduce false cut-in slowdowns by 50% and lane assignment error by 19%.
• Improved photon-to-control vehicle response latency by 20% on average.
• Expanded use of regenerative braking in Autopilot down to 0mph for smoother stops and improved energy efficiency.
• Improved VRU (pedestrians, bicyclists, motorcycles, animals) lateral velocity error by 4.9% by adding more auto-labeled and simulated training examples to the dataset.
• Reduced false slowdowns for crossing objects by improved velocity estimates for objects at the end of visibility.
• Reduced false slowdowns by adding geometric checks to cross-validate lane assignment of objects.
• Improved speed profile for unprotected left turns when visibility is low.
• Added more natural behavior to bias over bike lanes during right turns.
• Improved comfort when yielding to jaywalkers by better modeling of stopping region with soft and hard deadlines.
• Improved smoothness for merge control with better modeling of merge point and ghost objects positioned at the edge of visibility.
• Improved overall comfort by enforcing stricter lateral jerk bounds in trajectory optimizer
• Improved short deadline lane changes through richer trajectory modeling.
• Improved integration between lead vehicle overtake and lane change gap selection.
• Updated trajectory line visualization.

 

© 2021, Eva Fox | Tesmanian. All rights reserved.

_____________________________

We appreciate your readership! Please share your thoughts in the comment section below. 

Article edited by @SmokeyShorts, you can follow him on Twitter

Follow @EvaFoxU