Tesla is set to introduce new audio and vision capabilities in the upcoming FSD V13.4 update, following the recent rollout of FSD V13.2.1 to HW4/AI4 vehicle owners. This latest update includes features like Park, Unpark, and Reverse, providing users with an enhanced driving experience.
One of the key highlights of FSD V13.4 is the improved handling of audio inputs, as mentioned by Ashok Elluswamy, Tesla’s VP of AI. This update will allow Tesla vehicles to better recognize and respond to emergency vehicles audibly, increasing detection speed and reliability. By analyzing all sounds captured by the internal microphone, FSD will be able to distinguish between approaching sirens and ambient noise, utilizing the Doppler effect for enhanced accuracy.
Furthermore, Tesla users will have the option to opt-in to sharing audio data for FSD training purposes. This feature, available in previous versions like V12.5.6.4 and V13.2, allows users to contribute to the development of Tesla’s autonomous driving system. The updated data sharing feature in V13.2.1 now captures audio recordings when the vehicle detects an emergency vehicle, rather than just sirens, providing more comprehensive data for analysis.
With Tesla’s emphasis on both vision and audio capabilities, users can expect continued advancements in how their vehicles perceive and respond to their surroundings. From improved handling of school buses to potential enhancements in handling school zones, Tesla remains at the forefront of innovation in autonomous driving technology. Stay tuned for more updates as Tesla continues to push the boundaries of self-driving technology.