Tesla’s Updates FSD Roadmap: Talks FSD V13 and End-to-End Highway

By Not a Tesla App Staff
@BLKMDL3

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.

Tesla Debuts Super Manifold V2 in the New Model Y—But Not Every Car Has It Yet

By Not a Tesla App Staff
Tesla Service Manual

The Super Manifold is Tesla’s solution to reducing the complexity of a heat pump system for an EV. Tesla showed off its engineering chops back with the original Model Y in 2019, where it introduced a new 8-way valve (the Octovalve) and a new heat pump alongside the uniquely designed Super Manifold to improve efficiency.

Now, Tesla is launching an improved version with the refreshed Model Y - the Super Manifold V2. We got to hear about it thanks to Sandy Munro’s interview with Tesla’s Lars Moravy (Vice President of Vehicle Engineering) and Franz Von Holzhausen (Chief of Vehicle Design). You can watch the video further below.

What Is The Super Manifold?

The Super Manifold (get it, Superman?), is an all-in-one package that brings in all the components of a heat pump system into one component. The Super Manifold packs all the refrigerant and coolant components around a 2-layer PCB (printed circuit board).

This Super Manifold would normally have 15 or 20 separate components, but Tesla managed to integrate them all into one nice package. That presented Tesla with a new challenge: how to integrate a heat pump—capable of both heating and cooling—into a single, efficient platform?

Several years ago, Tesla designed the Octovalve. It combines inlets and outlets and can variably change between heating or cooling on the fly - without needing to be plumbed in different directions. This is especially important for EVs, which may need to heat the battery with the waste heat generated from the motors or the heat pump while also cooling the cabin - or vice versa.

Original Super Manifold V1.1

Tesla launched the Super Manifold V1.1 back in 2022, and it provided some minor improvements to the waste heat processing of the heat exchange system. It also tightened up the Octovalve, preventing the leakage of oils into the HVAC loop that could cause it to freeze at extremely low temperatures.

Tesla has been using the V1.1 for several years now, and it has really solved the vast majority of issues with the heat pump system that many older Model Ys experienced.

Super Manifold V2 Coming Soon

Now, Tesla is introducing the Super Manifold V2 in the new Model Y. It will improve the overall cooling capacity provided by the original Super Manifold, but unfortunately, not every single new Model Y will come with it equipped. Tesla will be introducing it slowly across the lineup and at different rates at different factories, depending on part availability.

Eventually, the Super Manifold V2 will also make its way to other vehicles, potentially including the upcoming refresh for the Model S and Model X, but initially, it’ll be exclusive to the new Model Y. Tesla expects to have the new manifold in every new Model Y later this year.

If you’re interested in checking out the whole video, we’ve got it for you below.

Breaking Down Tesla’s Autopilot vs. Wall “Wile E. Coyote” Video

By Not a Tesla App Staff
Mark Rober

Mark Rober, of glitter bomb package fame, recently released a video titled Can You Fool A Self-Driving Car? (posted below). Of course, the vehicle featured in the video was none other than a Tesla - but there’s a lot wrong with this video that we’d like to discuss.

We did some digging and let the last couple of days play out before making our case. Mark Rober’s Wile E. Coyote video is fatally flawed.

The Premise

Mark Rober wanted to prove whether or not it was possible to fool a self-driving vehicle, using various test scenarios. These included a wall painted to look like a road, low-lying fog, mannequins, hurricane-force rain, and bright beams.

All of these individual “tests” had their own issues - not least because Mark didn’t adhere to any sort of testing methodology, but because he was looking for a result - and edited his tests until he was sure of it.

Interestingly, many folks on X were quick to spot that Mark had been previously sponsored by Google to use a Pixel phone - but was using an iPhone to record within the vehicle - which he had edited to look like a Pixel phone for some reason. This, alongside other poor edits and cuts, led many, including us, to believe that Mark’s testing was edited and flawed.

Flaw 1: Autopilot, Not FSD

Let’s take a look at the first flaw. Mark tested Autopilot - not FSD. Autopilot is a driving aid for lane centering and speed control - and is not the least bit autonomous. It cannot take evasive maneuvers outside the lane it is in, but it can use the full stable of Tesla’s extensive features, including Automatic Emergency Braking, Forward Collision Warnings, Blind Spot Collision Warnings, and Lane Departure Avoidance.

On the other hand, FSD is allowed and capable of departing the lane to avoid a collision. That means that even if Autopilot tried to stop and was unable to, it would still impact whatever obstacle was in front of it - unlike FSD.

As we continue with the FSD argument - remember that Autopilot is running on a 5-year-old software stack that hasn’t seen updates. Sadly, this is the reality of Tesla not updating the Autopilot stack for quite some time. It seems likely that they’ll eventually bring a trimmed-down version of FSD to replace Autopilot, but that hasn’t happened yet.

Mark later admitted that he used Autopilot rather than FSD because “You cannot engage FSD without putting in a destination,” which is also incorrect. It is possible to engage FSD without a destination, but FSD chooses its own route. Where it goes isn’t within your control until you select a destination, but it tends to navigate through roads in a generally forward direction.

The whole situation, from not having FSD on the vehicle to not knowing you can activate FSD without a destination, suggests Mark is rather unfamiliar with FSD and likely has limited exposure to the feature.

Let’s keep in mind that FSD costs $99 for a single month, so there’s no excuse for him not using it in this video.

Flaw 2: Cancelling AP and Pushing Pedals

Many people on X also followed up with reports that Mark was pushing the pedals or pulling on the steering wheel. When you tap on the brake pedal or pull or jerk the steering wheel too much, Autopilot will disengage. For some reason, during each of his “tests,” Mark closely held the steering wheel of the vehicle.

This comes off as rather odd - at the extremely short distances he was enabling AP at, there wouldn’t be enough time for a wheel nag or takeover warning required. In addition, we can visibly see him pulling the steering wheel before “impact” in multiple tests.

Over on X, techAU breaks it down excellently on a per-test basis. Mark did not engage AP in several tests, and he potentially used the accelerator pedal during the first test - which means that Automatic Emergency Braking is overridden. In another test, Mark admitted to using the pedals.

Flaw 3: Luminar Sponsored

This video was potentially sponsored by a LiDAR manufacturer - Luminar. Although Mark says that this isn’t the case. Interestingly, Luminar makes LiDAR rigs for Tesla - who uses them to test ground truth accuracy for FSD. Just as interesting, Luminar’s Earnings Call was also coming up at the time of the video’s posting.

Luminar had linked the video at the top of their homepage but has since taken it down. While Mark did not admit to being sponsored by Luminar, there appear to be more distinct conflicts of interest, as Mark’s charity foundation has received donations from Luminar’s CEO.

Given the positivity of the results for Luminar, it seems that the video had been well-designed and well-timed to take advantage of the current wave of negativity against Tesla, while also driving up Luminar’s stock.

Flaw 4: Vision-based Depth Estimation

The next flaw to address is the fact that humans and machines can judge depth using vision. On X, user Abdou ran the “invisible wall” through a monocular depth estimation model (DepthAnythingV2) - one that uses a single image with a single angle. This fairly simplified model can estimate the distance and depth of items inside an image - and it was able to differentiate the fake wall from its surroundings easily.

Tesla’s FSD uses a far more advanced multi-angle, multi-image tool that stitches together and creates a 3D model of the environment around it and then analyzes the result for decision-making and prediction. Tesla’s more refined and complex model would be far more able to easily detect such an obstacle - and these innovations are far more recent than the 5-year-old Autopilot stack.

While detecting distances is more difficult in a single image, once you have multiple images, such as in a video feed, you can more easily decipher between objects and determine distances by tracking the size of each pixel as the object approaches. Essentially, if all pixels are growing at a constant rate, then that means it’s a flat object — like a wall.

Case in Point: Chinese FSD Testers

To make the case stronger - some Chinese FSD testers took to the streets and put up a semi-transparent sheet - which the vehicle refused to drive through or drive near. It would immediately attempt to maneuver away each time the test was engaged - and refused to advance with a pedestrian standing in the road.

Thanks to Douyin and Aaron Li for putting this together, as it makes an excellent basic example of how FSD would handle such a situation in real life.

Flaw 5: The Follow-Up Video and Interview

Following the community backlash, Mark released a video on X, hoping to resolve the community’s concerns. However, this also backfired. It turned out Mark’s second video was of an entirely different take than the one in the original video - this was at a different speed, angle, and time of initiation.

Mark then followed up with an interview with Philip DeFranco (below), where he said that there were multiple takes and that he used Autopilot because he didn’t know that FSD could be engaged without a destination. He also answered here that Luminar supposedly did not pay him for the video - even with their big showing as the “leader in LiDAR technology” throughout the video.

Putting It All Together

Overall, Mark’s video was rather duplicitous - he recorded multiple takes to get what he needed, prevented Tesla’s software from functioning properly by intervening, and used an outdated feature set that isn’t FSD - like his video is titled.

Upcoming Videos

Several other video creators are already working to replicate what Mark “tried” to test in this video.

To get a complete picture, we need to see unedited takes, even if they’re included at the end of the video. The full vehicle specifications should also be disclosed. Additionally, the test should be conducted using Tesla’s latest hardware and software—specifically, an HW4 vehicle running FSD v13.2.8.

In Mark’s video, Autopilot was engaged just seconds before impact. However, for a proper evaluation, FSD should be activated much earlier, allowing it time to react and, if capable, stop before hitting the wall.

A wave of new videos is likely on the way—stay tuned, and we’ll be sure to cover the best ones.

Latest Tesla Update

Confirmed by Elon

Take a look at features that Elon Musk has said will be coming soon.

More Tesla News

Tesla Videos

Latest Tesla Update

Confirmed by Elon

Take a look at features that Elon Musk has said will be coming soon.

Subscribe

Subscribe to our weekly newsletter