Tesla Announces FSD Roadmap With Dates: Reverse Capability, HW3, FSD in Europe, Banish Autopark, FSD V13

September 5, 2024

By Karan Singh

Not a Tesla App

In response to the many questions the Tesla AI team receives daily, they’ve finally caved in and shared their FSD release roadmap. Release Roadmap. This roadmap outlines the upcoming feature improvements and plans for FSD in the short term, up to about Q1 2025.

We expect this roadmap to be more accurate than some of the timelines we’ve heard from Elon in the past for FSD releases, as it's something that the entire team has presumably had some input in.

Let’s take a look at what we’ve got coming up soon!

September 2024

September looks to be full of improvements for FSD V12.5, and some of them are quite exciting. First off Tesla outlines the improvements that are available with FSD v12.5.2, which recently started going out to HW3 and HW4 vehicles.

FSD 12.5.2 & Reduced Interventions - Tesla says that FSD 12.5.2 brings a 3x improvement between necessary interventions. That will be a great improvement, especially as users on FSD 12.5.1.5 have noted several major issues with the path planner, including braking on green lights and path-planning to the opposite side of traffic.

Larger FSD Model for HW3 - Another big September item is that v12.5.2 is confirmed to be a unified FSD model. The same AI model that powers FSD 12.5 on AI4 is now being shared with the less powerful hardware 3. HW3 was previously running a smaller FSD model that was less intensive, although we were told they would soon run the same model.

This is definitely great news, as v12.5.1 has a different model for HW3 and AI4. We expect HW3 to see a performance boost in capabilities with the newer model. Tesla releasing a unified model shows their commitment to continue developing and supporting older hardware, so we’re happy to see this. If you’re not sure which FSD hardware you have, you can check here.

Actually Smart Summon - The improved Summon was released to early access testers already, (including on HW3), but it’s also on the list for September for a wider release. The feature isn’t available on FSD v12.5.2, but it is on v12.5.3.

Cybertruck Autopark - The Cybertruck which recently received High-Fidelity Park Assist, will be receiving AutoPark this weekend. Later this month Tesla says it will also receive full FSD support. Some Cybertruck owners have been waiting close to a year waiting for FSD capabilities, but with four-wheel steering, steer-by-wire, and cameras in slightly different locations, it’s not surprising it’s taken longer to implement. The Cybertruck is Tesla’s only vehicle with a front bumper camera, so it’ll be interesting to see if Tesla will leverage this camera for FSD in addition to the vehicle’s other 8 cameras.

Vision-Monitoring With Sunglasses - One of Tesla’s latest features, eye tracking, replaces the previous steering wheel torque detection. Tesla confirms that they’ll add support for vision monitoring with sunglasses in September. This feature isn’t available in FSD 12.5.3, so it could be a part of FSD 12.5.4 or FSD 12.6. Newer Tesla vehicles feature infra-red lights near the cabin camera which allows the camera to see at night. It’s not clear whether Tesla will leverage IR lights to help see-through sunglasses or what kind of sunglasses will be allowed.

End-to-end on the Highway - Tesla says they’ll also support end-to-end FSD for highway driving, which should be a huge improvement – as highways are still running the FSD v11 stack. End-to-end allows for AI to control the vehicle’s output like acceleration and steering instead of just input from cameras. When E2E was implemented for city-driving it was a huge boost, and we expect to see similar improvements for highway driving.

End-to-end for highway driving will only be included on the latest FSD versions for now, but at some point we expect the same end-to-end highway support to trickle down to regular Autopilot highway use, even outside of North America. The vehicle may not be more capable, but what it’s allowed to do in other regions will be smoother.

October 2024

Tesla AI seems to be focusing on Unpark, Park, and Reverse in FSD for October 2024. This appears to have been a milestone for a while now which we’re associating with Tesla’s previous comments on Park Seek and Banish Autopark. These two features allow the vehicle to drive around a parking lot by itself, find a parking spot, and finally park itself. These functions are necessary for Robotaxi to function, and with the Robotaxi event taking place in October, it’s a good fit that these features are also coming along for the ride — at least in an internal beta the Robotaxi will be running.

Unpark - Tesla mentions “unpark,” which sounds very much like Actually Smart Summon — essentially having the vehicle remove itself from a parking spot and start driving. These capabilities appear to be coming to FSD. You'll be able to start FSD from a parked position and the vehicle will back up and exit the parking spot before it starts driving to your destination.

Park - “Park,” could see some improvements over what is available today. Right now Tesla’s new AutoPark feature is only capable of backing a vehicle into a parking spot, which actually isn’t allowed in some areas. With improvements to Park, we could see the ability for the vehicle to go nose-in into parking spots or maybe support angled parking spaces.

Parking in FSD is a feature we’ve also been waiting for. Eventually, the car should be able to navigate to a parking lot, cruise around until it finds a parking stall, and then AutoPark should be initiated. Musk said this was coming to FSD back in May, so it seems like we may finally be close. You could see the pieces coming together where Actually Smart Summon can now traverse parking lots and Autopark can park itself. It’s just a matter of piecing these together.

Banish AutoPark is expected to be an upgrade to the current Autopark feature – where the vehicle drops you off near the entrance to your destination and then finds a parking stall autonomously, and parks itself entirely without user intervention. This is one feature we’re super excited about and is pretty much the opposite of Actually Smart Summon.

Reverse in FSD - Reversing capability for FSD will be huge. It’ll allow the vehicle to perform much more complex turns and even back up when it has gone too far into an intersection. Currently, FSD cannot shift into reverse, but users have already noticed that the path planner is capable of thinking about switching to reverse but is unable to. Reverse may already be part of the FSD model, but Tesla has a strict rule that doesn’t allow the vehicle to be put into reverse.

The ability for the vehicle to go in reverse will be critical to get the vehicle moving in and out of parking lots, as well as making tight three-point turns, so we’re excited to see what this will enable FSD to do.

FSD V13 - The final item Tesla lists for FSD in October is FSD v13. Tesla says v13 will bring a 6x improvement in miles between necessary interventions. That’s a huge leap, but we’ve heard similar numbers in the past that didn’t come to fruition, so we’ll have to wait and see. Tesla doesn’t release a major FSD version without large architectural improvements, so we do expect major improvements in capabilities or interventions — or both.

Q1 2025 - FSD Outside of North America

To go along with all the FSD improvements, Tesla also announced its FSD expansion plans and timelines. Tesla specifically outlined that they expect to launch FSD in Europe and China in Q1 of 2025. However, Tesla did say that this is pending regulatory approval. If Tesla has FSD ready for these markets, they should be able to launch at least portions of it in some countries.

This is definitely a slip from Tesla’s original release plan of EOY 2024 for FSD in Europe and China, but it's still a good sign to see the light at the end of the tunnel. We recently found out that the FSD test for China was put on hold, which could explain some of the delays.

Q2 2025 - FSD for Right Hand Drive

This time frame seems a bit more flexible following a comment from Elon on the post, but it seems that right-hand drive markets will take a bit longer than the team initially expected. Musk followed up saying that RHD markets will arrive in late Q1/Q2, pending approval.

The Tesla AI team has been hard at work getting FSD prepared for RHD markets, while other parts of Tesla have been working closely with national and regional governments to get approval for FSD.

Overall, this roadmap looks fantastic, and we’re happy to see Tesla AI providing this information to reduce speculation and help provide real timelines to Tesla owners. This is a super-packed release roadmap, and all the upcoming features and updates are going to be coming in back-to-back until the end of this year, with more around the corner next year!

Tesla Plans Massive 10x Robotaxi Expansion: A Look at the Potential New Area

July 29, 2025

By Karan Singh

Not a Tesla App

With Tesla’s first major expansion of the Robotaxi Geofence now complete and operational, they’ve been hard at work with validation in new locations - and some are quite the drive from the current Austin Geofence.

Validation fleet vehicles have been spotted operating in a wider perimeter around the city, from rural roads in the west end to the more complex area closer to the airport. Tesla mentioned during their earnings call that the Robotaxi has already completed 7,000 miles in Austin, and it will expand its area of operation to roughly 10 times what it is now. This lines up with the validation vehicles we’ve been tracking around Austin.

Based on the spread of the new sightings, the potential next geofence could cover a staggering 450 square miles - a tenfold increase from the current service area of roughly 42 square miles. You can check this out in our map below with the sightings we’re tracking.

If Tesla decides to expand into these new areas, it would represent a tenfold increase over their current geofence, matching Tesla’s statement. The new area would cover approximately 10% of the 4,500-square-mile Austin metropolitan area. If Tesla can offer Robotaxi services in that entire area, it would prove they can tackle just about any city in the United States.

From Urban Core to Rural Roads

The locations of the validation vehicles show a clear intent to move beyond the initial urban and suburban core and prepare the Robotaxi service for a much wider range of uses.

In the west, validation fleet vehicles have been spotted as far as Marble Falls - a much more rural environment that features different road types, higher speed limits, and potentially different challenges.

In the south, Tesla has been expanding towards Kyle, which is part of the growing Austin-San Antonio suburban corridor spanning Highway 35. San Antonio is only 80 miles (roughly a 90-minute drive) away, and could easily become part of the existing Robotaxi area if Tesla obtains regulatory approval there.

In the East, we haven’t spotted any new validation vehicles. This is likely because Tesla’s validation vehicles originate from Giga Texas, which is located East of Austin. We won’t really know if Tesla is expanding in this direction until they start pushing past Giga Texas and toward Houston.

Finally, there have been some validation vehicles spotted just North of the new expanded boundaries, meaning that Tesla isn’t done in that direction either. This direction consists of the largest suburban areas of Austin, which have so far not been serviced by any form of autonomous vehicle.

Rapid Scaling

This new, widespread validation effort confirms what we already know. Tesla is pushing for an intensive period of public data gathering and system testing in a new area, right before conducting geofence expansions. The sheer scale of this new validation zone tells us that Tesla isn’t taking this slowly - the next step is going to be a great leap instead, and they essentially confirmed this during this Q&A session on the recent call. The goal is clearly to bring the entire Austin Metropolitan area into the Robotaxi Network.

While the previous expansion showed off just how Tesla can scale the network, this new phase of validation testing is a demonstration of just how fast they can validate and expand their network. The move to validate across rural, suburban, and urban areas simultaneously shows their confidence in these new Robotaxi FSD builds.

Eventually, all these improvements from Robotaxi will make their way to customer FSD builds sometime in Q3 2025, so there is a lot to look forward to.

Caught on Video: Tesla FSD Tackles a Toll Booth — Here’s How It Pulled It Off

July 29, 2025

By Karan Singh

@DirtyTesLa on X

For years, the progress of Tesla’s FSD has been measured by smoother turns, better lane centering, and more confident unprotected left turns. But as the system matures, a new, more subtle form of intelligence is emerging - one that shifts its attention to the human nuances of navigating roads. A new video posted to X shows the most recent FSD build, V13.2.9, demonstrating this in a remarkable real-world scenario.

Toll Booth Magic

In the video, a Model Y running FSD pulls up to a toll booth and smoothly comes to a stop, allowing the driver to handle payment. The car waits patiently as the driver interacts with the attendant. Then, at the precise moment the toll booth operator finishes the transaction and says “Have a great day”, the vehicle starts moving, proceeding through the booth - all without any input from the driver.

If you notice, there’s no gate here at this toll booth. This interaction all happened naturally with FSD.

FSD 13.2.9 pulls up to a toll booth, waits for me to complete my transaction, then pulls away without a gate. 😳 Incredible. https://t.co/OsH1YAY8Ty pic.twitter.com/9hWAbLNrVa
— Dirty Tesla (@DirtyTesLa) July 27, 2025

How It Really Works

While the timing was perfect, the FSD wasn’t listening to the conversation for clues (maybe one day, with Grok?) The reality, as explained by Ashok Elluswamy, Tesla’s VP of AI, is even more impressive.

It can see the transaction happening using the repeater & pillar cameras. Hence FSD proceeds on its own when the transaction is complete 😎
— Ashok Elluswamy (@aelluswamy) July 27, 2025

FSD is simply using the cameras on the side of the vehicle to watch the exchange between the driver and attendant. The neural network has been trained on enough data that it can visually recognize the conclusion of a transaction - the exchange of money or a card and the hands pulling away - and understands that this is the trigger to proceed.

The Bigger Picture

This capability is far more significant than just a simple party trick. FSD is gaining the ability to perceive and navigate a world built for humans in the most human-like fashion possible.

If FSD can learn what a completed toll transaction looks like, it’s an example of the countless other complex scenarios it’ll be able to handle in the future. This same visual understanding could be applied to navigating a fast-food drive-thru, interacting with a parking garage attendant, passing through a security checkpoint, or boarding a ferry or vehicle train — all things we thought that would come much later.

These human-focused interactions will eventually become even more useful, as FSD becomes ever more confident in responding to humans on the road, like when a police officer tells a vehicle to go a certain direction, or a construction worker flags you through a site. These are real-world events that happen every day, and it isn’t surprising to see FSD picking up on the subtleties and nuances of human interaction.

This isn’t a pre-programmed feature for a specific toll booth. It is an emergent capability of the end-to-end AI neural nets. By learning from millions of videos across billions of miles, FSD is beginning to build a true contextual understanding of the world. The best part - with a 10x context increase on its way, this understanding will grow rapidly and become far more powerful.

These small, subtle moments of intelligence are the necessary steps to a truly robust autonomous system that can handle the messy, unpredictable nature of human society.