Tesla is currently under investigation for its Full Self-Driving Beta program, but this hasn’t affected the automaker’s updates schedule. With the latest FSD Beta v10.69.3 update, the manufacturer hasn’t added any new features, yet it seems to have changed a multitude of aspects of that affect how the system operates – it sounds like its changes should be immediately visible.
The update was first rolled out to Tesla employees yesterday and should start reaching members of the public beta program in the very near future. It’s currently only in a limited number of vehicles for internal testing purposes – they will be testing and evaluating this version before wider release.
Elon Musk said last month that this specific version would bring important changes – he said it features “several major architectural upgrades” and because of the update’s complexity, it wasn’t ready for its initially planned rollout date.
There isn’t any footage online of FSD Beta v10.69.3 because it’s not yet in public hands but the most recent public versions – v10.69.2.2 and v10.69.2.3 – is featured in several videos and it shows improvements in some areas, but nothing especially significant over what we’ve seen in recent months; one tester even says it’s a step back. The release notes for v10.69.3 list the following changes:
Upgraded the Object Detection network to photon count video streams and retrained all parameters with the latest autolabeled datasets (with a special emphasis on low visibility scenarios).
Improved the architecture for better accuracy and latency, higher recall of far away vehicles, lower velocity error of crossing vehicles by 20%, and improved VRU precision by 20%.
Converted the VRU Velocity network to a two-stage network, which reduced latency and improved crossing pedestrian velocity error by 6%.
Converted the Non VRU Attributes network to a two-stage network, which reduced latency, reduced incorrect lane assignment of crossing vehicles by 45%, and reduced incorrect parked predictions by 15%.
Reformulated the autoregressive Vector Lanes grammar to improve precision of lanes by 9.2%, recall of lanes by 18.7%, and recall of forks by 51.1%. Includes a full network update where all components were re-trained with 3.8x the amount of data.
Added a new “road markings” module to the Vector Lanes neural network which improves lane topology error at intersections by 38.9%.
Upgraded the Occupancy Network to align with road surface instead of ego for improved detection stability and improved recall at hill crest.
Reduced runtime of candidate trajectory generation by approximately 80% and improved smoothness by distilling an expensive trajectory optimization procedure into a lightweight planner neural network.
Improved decision making for short deadline lane changes around gores by richer modeling of the trade-off between going off-route vs trajectory required to drive through the gore region
Reduced false slowdowns for pedestrians near crosswalk by using a better model for the kinematics of the pedestrian
Added control for more precise object geometry as detected by general occupancy network.
Improved control for vehicles cutting out of our desired path by better modeling of their turning / lateral maneuvers thus avoiding unnatural slowdowns
Improved longitudinal control while offsetting around static obstacles by searching over feasible vehicle motion profiles
Improved longitudinal control smoothness for in-lane vehicles during high relative velocity scenarios by also considering relative acceleration in the trajectory optimization
Reduced best case object photon-to-control system latency by 26% through adaptive planner scheduling, restructuring of trajectory selection, and parallelizing perception compute. This allows us to make quicker decisions and improves reaction time.
