Tesla's New FSD Update: Vision-Based Attention Monitoring, Key Changes Explained
Innovations in autonomous driving are what drive Tesla's relentless pursuit of perfection. Their latest update, FSD v12.4.2, comes after a month-long delay, but with substantial improvements and notable changes in vision-based attention monitoring.
Tackling the Delay: Insights from Elon Musk
After a month of anticipation, the FSD v12.4.2 update finally rolled out to Tesla employees and OG testers. Elon Musk took to X (formerly Twitter) to explain the reasons behind the delay. Musk pointed out that although FSD v12.4 saw fewer interventions, it lacked the smoothness in driving that was a key focus of the release. The primary issue stemmed from disproportionate attention to interventions over normal driving—a comparison made to training a doctor on emergency patients versus regular care.
Vision-Based Attention Monitoring Overhauled
One of the most significant changes in the FSD v12.4.2 update pertains to Vision-Based Attention Monitoring. The update has refined the language to clarify how the system operates. Here are the critical modifications:
“When Full Self-Driving (Supervised) is enabled, the driver monitoring system now primarily relies on the cabin camera to determine driver attentiveness. This enhancement is available on vehicles equipped with a cabin camera and only when the cabin camera has clear and continuous visibility of the driver’s eyes, arms are visible, there is sufficient cabin illumination, and the driver is looking forward at the road ahead without sunglasses. Outside these circumstances, the driver monitoring system will primarily rely on a combination of torque-based (steering wheel) and vision-based monitoring to detect driver attentiveness. A green dot appears next to the steering wheel icon on the touchscreen when the cabin camera is actively monitoring driver attentiveness. If the cabin camera detects the driver to be inattentive, a warning will appear. The warning can be dismissed by the driver reverting their attention back to the road ahead. Warnings will escalate depending on the nature and frequency of detected inattentiveness, with continuous inattention leading to a Strikeout. Cabin camera images do not leave the vehicle itself, which means the system cannot save or transmit information unless you enable data sharing.”
A Closer Look at the Changes
Among the more intriguing updates is the requirement for drivers’ arms to be visible. This addition might be a measure to ensure hands are on the wheel or to prevent attempts to bypass the system using static images. Additionally, the phrasing now excludes covering the eyes with hats but emphasizes visibility without sunglasses.
Another technical shift is the removed segment stating that the driver monitoring system relies on both torque-based and vision-based monitoring. Instead, it now declares that the system will 'primarily' rely on torque-based monitoring when vision-based monitoring is unavailable. This raises questions about whether Tesla's FSD system now toggles between one monitoring source or integrates both for enhanced attentiveness detection.
Is Tesla Watching You?
The omission of the line stating cabin camera images cannot be saved or transmitted unless data sharing is enabled has sparked speculation. It suggests Tesla could be leveraging cabin images to augment its AI training models, though this remains unconfirmed.
For drivers, a green dot on the touchscreen will signify when the vision-based monitoring is active. If steps continue as planned, FSD v12.4.2 could soon extend to all Tesla customers with FSD capability and a compatible software version.
The Road Ahead
The excitement doesn't end with the software update. The release of FSD v12.4.2 promises fewer interventions and smoother driving experiences, potentially making autonomous driving more seamless and reliable. If the initial roll-out proves successful, the update might soon become available to all FSD-enabled Tesla vehicles. With anticipation high and Tesla fans eagerly awaiting, the future of driving seems brighter—and more autonomous—than ever.
Stay tuned to discover how these changes evolve and continue to revolutionize the landscape of autonomous vehicles.