This site is reader-supported. When you click through links on our site, we may be compensated.
Tesla’s Full Self-Driving program is still under its final testing phase before being rolled out to the masses, and a select group of “Beta Testers” are responsible for assessing the performance of the FSD suite in real-world situations. The Beta program has been constantly improved through Tesla’s Over-the-Air software updates, and the next one is set to be ready for installation in “probably two weeks.” Elon Musk says that it “will blow your mind.”
Gating factor is achieving & proving higher safety with pure vision than with vision+radar. We are almost there.
FSD Beta V9.0 will blow your mind.
— Elon Musk (@elonmusk) April 29, 2021
Identified as FSD Beta v9.0, more improvements are set to be applied to the semi-autonomous driving suite in the coming weeks. Tesla has utilized its real-world owners to test the FSD functionality due to the use of the Neural Network that captures and stores information and behaviors from other drivers and applies it to future situations to ensure safety. Tesla’s FSD Suite is constantly improving because of the Neural Network, and with every mile driven, real-world owners are contributing to the improvement and increased complexity of the suite.
Tesla introduced the Beta testing group in October following the Q3 2020 Earnings Call. The current FSD Beta is only accessible through some owners and employees who Tesla has selected themselves.
Perhaps the largest change that Tesla will make to the FSD Beta is the transition to “Pure Vision” rather than reliance on vision and radar, as Musk described in the Tweet. Tesla went into detail regarding this strategy in the Q1 2021 Update Letter.
The automaker wrote:
“We believe that a vision-only system is ultimately all that is needed for full autonomy. Our AI-based software architecture has been increasingly reliant on cameras, to the point where radar is becoming unnecessary earlier than expected. As a result, our FSD team is fully focused on evolving to a vision-based autonomous system and we are nearly ready to switch the US market to Tesla Vision.”
Tesla has long relied on both cameras and radar to accurately depict surroundings to ensure safety while operating the vehicle with FSD. However, it is looking to shift to a completely camera-based approach, which could align with the eventual rollout of the Dojo Supercomputer.
Dojo was announced by Tesla last year, and Musk said it would transition the FSD suite from 2.5D to 4D. 4D is “video essentially,” Musk said. “It’s capable of things that if you just look — looking at things as individual pictures as opposed to video — basically, like you could go from like individual pictures to surround video, so it’s fundamental. So the car will seem to have just like a giant improvement.”
Tesla’s plan to utilize Dojo would involve switching to 4D, which would require video instead of any radar detection. This seems to be Tesla and Musk’s ultimate strategy to attain the elusive Level 5 Autonomy rating, requiring drivers to no longer pay attention to the road and the vehicle’s surroundings. While Tesla has not yet accomplished this feat, there is no indication that it cannot achieve it eventually, especially as the FSD system becomes more complex over time.