Teslarati 
Elon Musk has posted a quick update on the potential rollout of FSD Beta V11, the highly-anticipated update to the electric vehicle maker’s advanced driver-assist suite. As confirmed by the CEO, FSD Beta V11 is quite remarkable as it uses a single software stack for both highway and inner-city driving.
Musk’s recent comments were shared on Twitter. Amidst the ongoing controversy behind his decision to suspend a number of notable journalists on the social media platform over alleged violations of Twitter’s doxxing policy, Musk was asked about the highly-anticipated FSD Beta update.
When asked by the Tesla Owners Silicon Valley group if FSD Beta V11 is still expected to be released before Christmas, Musk noted that the update should release “next week.” While such a timeframe may seem exciting, Musk’s “next week” estimate has become an inside joke of sorts among those who closely follow Tesla. Musk, after all, has missed estimates for V11’s release in the past.
Musk noted last month that the initial rollout of FSD Beta V11 started on 11/11/2022 at 11:11 p.m. PST. Musk later stated that Tesla was looking to release FSD Beta V11 before Thanksgiving. The holiday came and went, and no V11 wide rollout happened. The delay seemed a bit understandable, however, since Tesla did conduct a wide release of FSD Beta to its fleet — it was just V10.69.3.1, not V11.
Due to FSD Beta V11’s initial release being over a month ago, the update’s full release notes have already been shared online. If the release notes are any indication, it would definitely seem that the highly-anticipated update would be well worth the wait. Following are FSD Beta V11’s release notes, as shared by Tesla enthusiasts online.
-Enabled FSD Beta on highway. This unifies the vision and planning stack on and off-highway and replaces the legacy highway stack, which is over four years old. The legacy highway stack still relies on several single-camera and single-frame networks, and was setup to handle simple lane-specific maneuvers. FSD Beta’s multi-camera video networks and next-gen planner, that allows for more complex agent interactions with less reliance on lanes, make way for adding more intelligent behaviors, smoother control and better decision making.
– Improved Occupancy Network’s recall for close by obstacles and precision in severe weather conditions with 4x increase in transformer spatial resolution, 20% increase in image featurizer capacity, improved side camera calibration, and 260k more video training clips (real-world and simulation).
– Improved merging behavior by leveraging lane geometry and lane bounds, association with coarse map information and better gap selection algorithms, allowing for a smoother and safer experience.
– Added highway behavior to offset away from blocked lanes and generic obstacles like road debris while also adding a smooth hand- off between in-lane offsetting and lane changing.
– Improved speed-based lane change decisions to better avoid slowing down traffic in fast lanes, and interfere less with navigation.
– Reduced sensitivity for speed-based lane changes in CHILL mode.
– Improved lane changes to allow higher jerk maneuvers if required to stay on-route or to move away from lane blockages.
– Improved smoothness at highway lane splits by being less strict about centering between lane lines and allowing lower jerk maneuvers, where safe to do so.
– Reduced latency of trajectory optimization by 20% on average, without sacrificing behavior, by leveraging numerical tricks for more efficient computations.
