Here were the FSD Beta V11.3 Notes from 2.19.23.
Here are the Full Self-Driving Beta V11.3 release notes in text form for improved readability.
Key points: FSD on Highways, improved lane changes, resolves recall concerns, improves AEB, report autopilot mistakes via voice notes.
More details are below, by clicking “Read more”...
1️⃣ 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.
2️⃣ Added voice drive-notes. After an intervention, you can now send Tesla an anonymous voice message describing your experience to help improve Autopilot.
3️⃣ Expanded Automatic Emergency Braking (AEB) to handle vehicles that cross ego's path. This includes cases where other vehicles run their red light or turn across ego's path, stealing the right-of-way.
Replay of previous collisions of this type suggests that 49% of the events would be mitigated by the new behavior. This improvement is now active in both manual driving and autopilot operation.
4️⃣ Improved autopilot reaction time to red light runners and stop sign runners by 500ms, by increased reliance on object's instantaneous kinematics along with trajectory estimates.
5️⃣ Added a long-range highway lanes network to enable earlier response to blocked lanes and high curvature.
6️⃣ Reduced goal pose prediction error for candidate trajectory neural network by 40% and reduced runtime by 3X. This was achieved by improving the dataset using heavier and more robust offline optimization, increasing the size of this improved dataset by 4X, and implementing a better architecture and feature space.
7️⃣ Improved occupancy network detections by oversampling on
180K challenging videos including rain reflections, road debris, and high curvature.
8️⃣ Improved recall for close-by cut-in cases by 20% by adding 40k autolabeled fleet clips of this scenario to the dataset. Also improved handling of cut-in cases by improved modeling of their motion into ego's lane, leveraging the same for smoother lateral and longitudinal control for cut-in objects.
9️⃣ Added "lane guidance module and perceptual loss to the Road Edges and Lines network, improving the absolute recall of lines by 6% and the absolute recall of road edges by 7%.
1️⃣0️⃣ Improved overall geometry and stability of lane predictions by updating the "lane guidance" module representation with information relevant to predicting crossing and oncoming lanes.
1️⃣1️⃣ Improved handling through high speed and high curvature scenarios by offsetting towards inner lane lines.
1️⃣2️⃣ Improved lane changes, including earlier detection and handling for simultaneous lane changes, better gap selection when approaching deadlines, better integration between speed-based and nav-based lane change decisions and more differentiation [...]
