Last week, Tesla (TSLA) released the FSD v13 self-driving software rollout roadmap. This is a detailed list of features that the automaker plans for offer Tesla owners using FSD Supervised on their vehicles.
In the entire history of the automotive industry, no other car maker has ever shared such details of the vehicle features with its customers and the public.
One interesting new addition to the algorithm of Tesla’s Full Self-Driving AI is “audio inputs”. In the upcoming FSD v13, Tesla vehicles running on Autopilot/FSD will be able to process audio signals to identify and respond to emergency vehicles like ambulances, cop cars, and fire trucks, etc.
Audio inputs for better handling of emergency vehicles.
FSD v13 feature-release roadmap
We recently saw a Tesla car responding to an oncoming fire emergency response truck. The car pulled over to the side to give the fire engine enough space to move towards its destination uninterruptedly.
However, as safety is a top priority at Tesla, the automaker does not want to limit its vehicles to AI Vision only to detect and respond to emergency vehicles. Getting audio input signals is going to improve the response to emergency vehicles and increase collective safety.
Adding the audio signals to the FSD algorithm is going to increase the amount of data that the automaker receives to process, analyze, and create AI responses to specific scenarios.
Currently, Tesla only takes video data from its vehicles to feed its Tesla Vision AI neural network. With the addition of audio signals added to the data stream, FSD Supervised v13 and later versions will not be ‘Vision Only’.
Tesla cars will be using the interior mic to listen to audio signals like different sirens of emergency vehicles and respond to them. There is no external mic installed in Tesla cars except for a speaker that is used for the Boombox feature and talking back to vandals (if such a situation arises).
“Lots of work, but the team’s aiming to get to feature complete for unsupervised FSD with the v13 series!” Tesla’s head of AI Ashok Elluswamy wrote on X (Twitter).
Feature-complete means the automaker aims to complete the promised features with FSD v13 and move to Unsupervised Full Self-Driving. The major remaining feature for FSD is ‘Navigating City Streets’.
Tesla even completed Actually Smart Summon (ASS) this year and released it even for the legacy HW3 vehicles to keep older vehicles on track for new feature-releases.
In the same discussion thread on X, Ashok Elluswamy promised another interesting feature to a Tesla owners request. When asked that the Tesla cars should honk autonomously when needed, Ashok affirmed that he would add this feature to the list of to-dos for the Tesla AI team.
Stay tuned for constant Tesla updates, follow us on:
Google News | Flipboard | X (Twitter) | WhatsApp Channel | RSS (Feedly).
Related Autopilot / FSD News
- Tesla Dojo supercluster looks more advanced and refined than xAI’s Nvidia Colossus
- Tesla launches FSD Early Access Program in the US, here’s how to enroll your car in it
- A Tesla Model 3 spotted probably testing for Unsupervised FSD for the Texas launch in June
- Chinese Tesla owners take FSD v13 testing to the extreme on dangerous mountain roads and more (videos)
- Tesla re-engineers the brake system in the new Model Y Juniper for Autopilot and human drivers
- Tesla FSD v13 passes the ‘painted wall test’ while FSD v12 fails — Tesla owner debunks Mark Rober’s dubious test
