Last month Tesla shared a roadmap with its progress on FSD and its goals for the coming months. Since we’re coming to the end of October and Tesla had yet to release the two items listed under October, we asked Tesla if they could provide an updated roadmap to help keep everyone’s expectations in line.
We’re not sure whether Tesla saw our message or already had plans to provide an updated roadmap, but today Tesla published an update to its initial roadmap.
Instead of focusing on timelines, Tesla has now simply published what their AI team is working on and what customers could expect next.
Tesla’s Original Timeline
The roadmap Tesla provided in early September focused on FSD improvements, releasing Actually Smart Summon, FSD on Cybertruck, FSD v13, and the expansion of FSD outside of North America.
This was Tesla’s initial roadmap which was provided on September 5th.
September 2024
v12.5.2 with ~3x improved miles between necessary interventions
v12.5.2 on AI3 computer (unified models for AI3 and AI4)
Actually Smart Summon
Cybertruck Autopark
Eye-tracking with sunglasses
End-to-End network on highway
Cybertruck FSD
October 2024
Unpark, Park and Reverse in FSD
v13 with ~6x improved miles between necessary interventions
Q1 2025
FSD in Europe (pending regulatory approval)
FSD in China (pending regulatory approval)
Elon Musk also replied to Tesla’s post, saying that, hopefully, right-hand drive markets will also get FSD in late Q1 or early Q2.
Goals Tesla Met
While we’re only at the end of October, Tesla managed to check off their September goals with a perfect score, nailing all of their goals such as eye-tracking with sunglasses, FSD on the Cybertruck and releasing Actually Smart Summon in the United States and Canada.
They also released the unified FSD model for HW3 and AI4, although it seems like the good news may stop there for HW3 owners. At least Tesla has recently said HW3 owners will get a free upgrade to more capable hardware if Tesla isn’t able to achieve unsupervised FSD on those vehicles.
Goals Tesla Is Still Working On
Although the company met its September milestones, the October goals have been delayed. Initially targeting the release of unpark, park, and reverse features and FSD v13 for October, Tesla now plans to integrate these features with FSD v13 in November.
The delay isn’t surprising given the ambitious goals, but we’re thrilled to see that Tesla is keeping the communication lines open.
The goals Tesla set to release FSD outside of North America are still to be determined, but we presume they may shift slightly due to the delay of FSD v13.
What’s Coming
While Tesla avoided dates and timelines for their upcoming features, they actually provided a lot more detail on what they’re working on and what we can expect in FSD v13. Unfortunately for HW3 owners, most of these improvements appear to be destined for Hardware 4 (AI4).
Complete Rollout of End-to-End
Tesla’s first item on its updated list is to complete the rollout of its end-to-end highway stack. Tesla’s current highway stack is based on FSD v11 and doesn’t feature end-to-end AI, meaning that AI is only used for input and not to control the vehicle. End-to-end AI essentially has AI managing everything in the vehicle, from detecting objects and lane markers to the steering and brake pedals.
Tesla started including end-to-end for highway driving in FSD v12.5.5 for the Cybertruck and then opened it up to other AI4 vehicles with FSD 12.5.6. The latest public FSD version is FSD 12.5.6.1, but it’s only available for AI4 vehicles.
The majority of vehicles with FSD are still on version 12.5.4, which doesn’t include the new highway stack. Tesla aims to release the updated highway stack to all AI4 vehicles next week, which will also include improvements to stop smoothness and improved bad weather notifications.
Actually Smart Summon
While Actually Smart Summon was released in September in North America, most of the world is still waiting. Tesla now says that A.S.S. will be available in other regions but didn’t provide a timeline. Users who bought or subscribe to Enhanced Autopilot or FSD in Europe should expect to receive this feature as part of Tesla’s normal feature releases instead of being a part of a special FSD build. It’s possible this could come in Tesla’s next major update, possibly 2024.44.
It’s not clear whether Tesla’s list was in any sort of order, but if it is, we could expect Actually Smart Summon sooner rather than later.
Improved FSD for HW3
Tesla’s updated list was largely focused on FSD for AI4, but HW3 did get mentioned in one bullet point item. Tesla says that HW3 should receive improved FSD v12.5.x models for city driving. Unfortunately, this almost sounds like bad news. AI4 mentions in the roadmap talk about FSD v13 and end-to-end highway support, while HW3 specifically states improved “city-driving,” possibly saying that end-to-end highway driving is not coming to HW3 vehicles soon.
Given that a new version of FSD v12.5.4.2 just started rolling out for HW3 vehicles, it looks like it may be a while before HW3 owners have access to the new highway stack. Earlier this month, Musk said that HW3 owners should receive an update that will increase FSD’s smoothness, so it seems like this is what Tesla is referring to in their roadmap.
FSD V13
The rest of Tesla’s post was dedicated to FSD v13. Tesla provided a lot of specifics such as FSD v13 unlocking the full resolution of Tesla’s HW4 cameras. The computer will now process full-resolution video at 36 FPS instead of using lower frames per second or scaling the video down.
FSD v13 will also increase the AI model by three times and data by 4.2 times. Tesla expects this to provide better collision avoidance, improved traffic controls and navigation.
FSD Unsupervised Feature Complete
Tesla’s VP of AI, Ashok Elluswamy, is just as excited about v13. He reposted Telsa’s post and said that a lot of work is going into the FSD v13 release and that Tesla expects v13 to make FSD Unsupervised feature complete. This is far from saying that FSD v13 will achieve autonomy, but simply that all the pieces of the puzzle are now in place with v13. The car will be able to navigate from a garage to its parking spot at a destination without any human input. Each of these pieces will likely still need to be refined over time to achieve unsupervised FSD.
Release Date for FSD V13
Tesla is targeting the release of FSD v13 to employees by the end of this week. Tesla expects the update to go through several iterations before it’s released to customers in FSD v13.3. Tesla says that the target launch for a public version of FSD v13.3 is around Thanksgiving for AI4 vehicles.
FSD Arrival Options
In addition to FSD v13 including the ability to “unpark,” reverse and park itself, Tesla will also add various options for when the vehicle arrives at its destination. Users will be able to choose from simply pulling over, parking in a parking spot or driveway or even a garage.
We believe that “unpark” in this statement refers to the ability for the user to engage Autopilot while the vehicle is still parked. The vehicle will automatically shift from Park to Drive and drive or reverse out of its parking spot before proceeding to its destination.
Detecting Emergency Vehicles
One other item Tesla pointed out in their roadmap is that FSD v13 will process audio inputs to better handle emergency vehicles. FSD now appears to rely only on detecting emergency vehicles visually, but with FSD v13, Teslas will be able to detect them audibly as well. Unfortunately, all Teslas only have microphones inside the cabin, which are currently used for phone calls and voice commands, but Tesla will soon continuously process the audio to detect emergency vehicles and potentially other things.
Outlook
Tesla has already integrated some v13 improvements and reports a 4x increase in miles between necessary interventions compared to v12.5.4. It’s clear that Tesla’s focus is on AI4 and reaching its goal of Unsupervised FSD. They appear very focused on this goal and will do whatever it takes to get there. Right now, that means focusing on AI4, but if at any point they run out of compute power needed there, they could shift to AI5, but that’s not expected to happen any time soon.
AI5, which is included in the Cybercab, isn’t expected to be released until the end of the year. We expect Tesla to continue marching toward achieving autonomy, regardless of the power required. Once they can figure out FSD, they can work backwards to get it working on older hardware.
Subscribe
Subscribe to our newsletter to stay up to date on the latest Tesla news, upcoming features and software updates.
Over the last few days, we’ve seen some exceptionally smooth performance from the latest version of FSD on Tesla’s Robotaxi Network pilot. However, the entire purpose of an early access program with Safety Monitors is to identify and learn from edge cases.
This week, the public saw the first recorded instance of a Safety Monitor intervention, providing a first look at how they’re expected to stop the vehicle.
The event involved a complex, low-speed interaction with a reversing UPS truck. The Safety Monitor intervened to stop the Robotaxi immediately, potentially avoiding a collision with the delivery truck. Let’s break down this textbook case of real-world unpredictability.
The Intervention [VIDEO]
In a video from a ride in Austin, a Robotaxi is preparing to pull over to its destination on the right side of the road, with its turn signal active. Ahead, a UPS truck comes to a stop. As the Model Y begins turning into the spot, the UPS truck, seemingly without signaling, starts to reverse. At this point, the Safety Monitor stepped in and pressed the In Lane Stop button on the main display, bringing the Robotaxi to an immediate halt.
This is precisely why Tesla has employed Safety Monitors in this initial pilot. They are there to proactively manage ambiguous situations where the intentions of other drivers are unclear. The system worked as designed, but it raises a key question: What would FSD have done on its own? It’s not clear whether the vehicle saw the truck backing up, or what it would do when it finally detected it. It’s also unclear whether the UPS driver recognized that the Robotaxi was pulling into the same spot at the exact same time.
It’s possible this wouldn’t result in a collision at all, but the Safety Monitor did the right thing by stepping in to prevent a potential collision, even one at low speed. Any collision just a few days after the Robotaxi Network launch could result in complications for Tesla.
Who Would Be At Fault?
This scenario is a classic edge case. It involves unclear right-of-way and unpredictable human behavior. Even for human drivers, the right-of-way here is complicated. While a reversing vehicle often bears responsibility, a forward-moving vehicle must also take precautions to avoid a collision. This legal and practical gray area is what makes these scenarios so challenging for AI to navigate.
Would the Robotaxi have continued, assuming the reversing truck would stop?
Or would it have identified the potential conflict and used its own ability to stop and reverse?
Without the intervention, it’s impossible to say for sure. However, crucial context comes from a different clip involving, surprisingly, another UPS delivery truck.
A Tale of Two Trucks
In a separate video posted on X, another Robotaxi encounters a remarkably similar situation. In that instance, as another UPS delivery truck obstructs the path forward, the Robotaxi comes to a stop to let its two passengers out just a few feet from their destination.
Once they depart, the Robotaxi successfully reverses and performs a three-point turn to extricate itself from a tight spot. That was all done without human intervention, by correctly identifying the situation.
This second clip is vital because it proves that the Robotaxi's FSD build has the underlying logic and capability to handle these scenarios. It can, and does, use reverse to safely navigate complex situations.
Far from being a failure, this first intervention should be seen as a success for Tesla’s safety methodology. It shows the safety system is working, allowing monitors to mitigate ambiguous events proactively.
More importantly, this incident provides Tesla’s FSD team with an invaluable real-world data point.
By comparing the intervened ride with the successful autonomous one, Tesla’s engineers can fine-tune FSD’s decision-making, which will likely have a positive impact on its edge case handling in the near future.
This is the purpose of a public pilot — to find the final edge cases and build a more robust system, one unpredictable reversing truck at a time.
With the launch of Tesla’s Robotaxi service, Tesla also introduced the new Robotaxi app. The app is currently only available to influencers who have access to the service, but it’s expected to roll out to everyone once the service is available to the general public.
Let’s have a look at all the features available in the current version of the app.
Sign In
From the moment you open the Tesla app, you’re greeted with a photo of the Model Y robotaxi. Although Tesla is using Model Ys in a variety of colors, the app theme uses the gold Cybercab color.
Similar to the Tesla app, you can sign in with your Tesla account or create a new account. Once you sign in, Tesla will automatically pull data from your Tesla account, including your profile photo and payment information.
This ends up being a really nice experience, similar to Supercharging. Whenever you reach your destination, there’s nothing to pay or do except to grab your belongings and exit the vehicle.
Search and Select Destination
Rob Maurer
Once you’re logged in, you get a map of your current location. You can see your current location on the map and the Robotaxi geofence.
Underneath, you have a search box to add a destination or filter for nearby places such as food and shopping. Tesla also includes your previously searched for destinations below that.
Before you even type anything in, Tesla lets you know the wait time for a Robotaxi at your location. Tesla also currently displays the fee even before you select a destination, as it’s currently a flat fee of $4.20. However, in the future, this will likely be displayed after you choose your destination.
Waiting For Your Ride
Sawyer Merritt / DirtyTesla
Once you’ve chosen a pickup location and destination, Tesla will show you the status of your taxi. You can track it in real-time on a map, and it’ll display a visualization of the vehicle and its ETA at your pickup location. It’ll also provide an estimate of when you’ll reach your destination.
A nice touch is that the app displays your vehicle’s color in the visualization and license plate, making it easier to find the vehicle when it arrives.
While you’re waiting, you can cancel the pickup or report an issue.
When Your Vehicle Arrives
@BLKMDL3
When your Robotaxi finally arrives, you’ll have access to some of the vehicle's controls, such as sounding the horn, flashing its lights, locking and unlocking it, and opening the trunk.
Live Activities
Tesla is also providing a Live Activity while you’re waiting for your ride, so that you can continue to track the vehicle even if you’re not in the Robotaxi app.
@DirtyTesla
Joe Tegtmeyer on X
Robotaxi Tips
@DirtyTesLa on X
The exterior lights pulse prompt in the app.
@DirtyTesLa on X
Tesla provides several tips in the app while you’re waiting for your vehicle. It’ll show you how to use the Model Y's handles, in case you’re not familiar with them. It’ll also remind you that the vehicle’s lights will pulse when it arrives at your pickup location, helping differentiate it from other Teslas on the road.
You can swipe left and right for additional tips.
Menu
Sawyer Merritt
Similar to the Tesla app, the Robotaxi app features a menu with similar options. It includes options we’re already familiar with, such as Security & Privacy and Payment. New to the Robotaxi app are Data Sharing, Ride History, Support, and Appearance.
Ride History: The Ride History section shows you all of your previous rides. It’ll display all of your rides broken down by date and destination. It’ll also include the fee and the time you were picked up.
If you tap into any ride, you’ll be able to see the route the Robotaxi took for that ride, as well as your pickup time, arrival at destination, distance, and fee.
On this screen, you can also report a lost item, but we have yet to see what that looks like.
Appearance: Unlike the Tesla app, which uses a dark theme throughout the app, the Robotaxi app lets you switch between light and dark modes. Unlike other apps, there isn’t an option for Auto to have it reflect what you’re using in the OS.
Sawyer Merritt
Data Sharing: The Data Sharing section includes an option to turn off device location, although Tesla requires it to be enabled to book a ride. Your location is tracked through the app even when the app isn’t running in the foreground. While Tesla said that cabin camera and microphone use would only be used when a rider agrees, they are requiring these optiosn to be turned on to actively details during the early-access period.
Support: Support currently has options to report a lost item or report a found item. While you can reach out to Tesla Robotaxi support in the vehicle, it doesn’t look like you can do it after the ride has completed.
Sawyer Merritt
Adjust Vehicle Settings
If you open the app while you’re in an active ride, you’ll be able to adjust various vehicle settings. This includes the cabin temperature, music controls, and volume.
Sawyer Merritt
Call Support or Pull Over
Similar to the controls on the rear screen of the vehicle, you can also call support or have the vehicle pull over directly from the Robotaxi app. While the safety monitor has additional controls, such as Stop in Lane, users are limited to these two buttons.
Tipping
Sawyer Merritt / DirtyTesla
At the end of your ride, you’ll need to tap Finish Ride and Tesla shows you how to exit the vehicle. You’ll also be able to open the trunk or reach out to Tesla support.
You’ll be given a chance to rate your ride and even tip the driv— car. However, Tesla has a little easter egg for anyone looking to tip, which can be seen in the video below:
The Robotaxi app is currently being offered to 20 influencers who were invited to the event through a special link. Unfortunately, it’s not yet available in the App Store. While influencers could bring one guest with them, only the invitee could download and use the Robotaxi app.
The app is currently only available for Apple devices, but it’s expected to have an Android counterpart when, or shortly after, it launches to the public.
![First Recorded Tesla Robotaxi Intervention: UPS Truck Encounter [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2025/robotaxi_model_y.jpg/3036d8b53214c2d071c978c42911e451/robotaxi_model_y.jpg)
![First Look at Tesla's Robotaxi App and Its Features [PHOTOS]](https://www.notateslaapp.com/img/containers/article_images/tesla-app/robotaxi-app/robotaxi-app-tips.webp/e643a61975bf712d18dc9aa9a48fdb01/robotaxi-app-tips.jpg)
![Tesla’s New Camera Cleaning Feature and the Future of Cleaning Robotaxis [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2024/windshield-rain-droplets.jpg/8335f3020509dab3cdb56c1a91d054a9/windshield-rain-droplets.jpg)
![Tesla Launches Robotaxi: Features, Robotaxi App, Command Center and First Impressions [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2025/robotaxi_rear_screen.jpg/bf5ea088bdebda8ca7e0aa1503b69f4e/robotaxi_rear_screen.jpg)
