All Tesla FSD Visualizations and What They Mean

By Nuno Cristovao

Updated: September 21st, 2022 as of FSD Beta 10.69.2.2

Tesla has slowly added more visualizations to the car display, showing what the car can detect and respond to in its environment. Tesla initially showed just road markings and some vehicles, but then slowly added more vehicle types, pedestrians and traffic cones.

However, with the release of FSD Beta version 9, Tesla has drastically increased the amount of objects the car can visualize and interact with.

The visualizations in the car aren't tied one-to-one with what the car is capable of detecting and using to make decisions. However, Tesla keeps visualizations and object detection closely coupled so that drivers have a good understanding of what the car can see.

Unidentified Objects

FSD Beta 10.69.2 will now display objects it can not recognize
FSD Beta 10.69.2 will now display objects it can not recognize
Not a Tesla App

As of FSD Beta 10.69.2 the vehicle visualizations will now display unidentified objects or debris. The shape of the visualization will not match the actual object, but it will be displayed as a pile of debris.

This lets the driver know the vehicle is aware of an object in its path or surroundings, but that it can not yet idenfiy what the object is.

Vector-based Lanes

Vector-based lanes
Vector-based lanes
Chazman/Twitter

As of FSD Beta 10.11, your Tesla will now display vector-based lanes. This means that the lanes are not just raster-based lines drawn in a 3D environment, but that Tesla is actually building the lane markings with vector-based graphics.

This gives Tesla additional freedom when choosing how to display the lanes on the car's display.

With this update, Tesla now fills in the lane in blue when your vehicle is changing lanes. This was something Tesla couldn't do before since the lane markings were just drawn lines.

The new vector-based graphics will scale well to any size and reduce blurring and pixelation you normally see on the display with lane markings and road edges.

Since lane markings are now vectors, hopefully, Tesla will soon apply the same process to other markings, such as the road edges.

Scalable Vehicle Models

All vehicles that Tesla displayed were pre-defined static-sized assets. However, in the 10.10.2 FSD update, we are now seeing Tesla scale individual vehicle models so that they represent the calculated size of surrounding vehicles. Contextually this could be helpful in better understanding our car's situation in the world.

Tesla now shrinks or stretches the 3D vehicle models in each dimension so that the 3D model matches the calculated dimensions for each vehicle. This is especially apparent in longer vehicles such as buses, trucks, and tractor-trailers, where the vehicle lengths are more likely to vary, but you can also see it scale other vehicle models such as very small cars.

In this example below, you'll see that Tesla is now able to accurately represent buses of different sizes. Tesla only has a model for a full length bus, but in this case, Tesla detected that the length of one of the buses is considerably shorter than the vehicle model so it chose to reduce the length of the bus to the length Autopilot had calculated. In the image below you can see how the same bus model is shown in two different sizes.

Tesla adds scalable vehicle models to the latest FSD Beta
Tesla adds scalable vehicle models to the latest FSD Beta

You can also read more details or see additional examples of Tesla dynamically scaling vehicle models.

Road Users

Vulnerable road users or VRUs as Tesla calls them are pedestrians and other users of the road that the car must be especially careful with.

Tesla already does a good job displaying some of these, but there is room for improvement here since it’s such a critical area. We hope that Tesla will add additional animals and sidewalk detection in future updates.

Pedestrians

Pedestrians are one of the few objects that feature an animation. If the pedestrian is walking, you'll see them animated on the screen.

Tesla FSD visualizations
FSD Beta visualizations start representing the real world
DirtyTesla/YouTube

Bicycles

Bicycles are visualized separately from motorcycles.

Dogs

Tesla recently added a visualization for a dog which shows up for dogs and other similarly sized animals. It's likely Tesla will add more animals in the future such as squirrels, deer and other common animals seen on roadways.

Tesla FSD visualization of a dog

Objects

Garbage/Recyling Bins

This is an object that's also displayed outside of the FSD Beta.

Traffic Cones

Traffic cones are also displayed outside of the FSD Beta and are displayed in orange. The car will display them for cones, construction barrels or sometimes mailboxes.

Speed Bumps

The car has been reacting to speed bumps for the last few betas, but they're now visualized on the screen with small arrows on them, which is a nice improvement.

Tesla visualization speed bumps
As of beta 10.4, speed bumps now appear in the visualization
Frenchie/YouTube

Poles

These poles can often be seen on the side of some highways and are displayed as short gray sticks at the edge of the road.

Tesla visualization poles
FSD Beta shows a visualization for small poles
Frenchie/YouTube

Vehicles

Tesla displays the most common vehicle types. Obviously, Tesla will need to expand this list once they expand to some other countries where other vehicle types are popular. Elon has said in the past that Tesla will visualize other Teslas specifically in the car. Recent car data shows that Tesla is already identifying whether a car is a Tesla and what model it is. This is a nice addition, but really would likely have little benefit to FSD. Tesla may provide car-to-car communication if it detects there's another Tesla nearby, which could make some situations easier, such as the right way of situations.

Another vehicle type I'd like Tesla to react better to and visualize are trailers. There are many types of trailers and they often have segments you can see through, so this may be a little tougher, but it's an important vehicle type to add.

New Vehicle Models

Vehicle models are now much more detailed
Vehicle models are now much more detailed
Not a Tesla App

FSD Beta 10.12 introduces new vehicle models for almost every vehicle type.

Some of the vehicles have been completely redesigned and are more detailed and realistic looking than the previous models.

For example, a sedan now has wheels, windows and a glass roof, instead of the previous simplistic look that resembled a Model S keyfob.

Vehicle models are now much more detailed
Vehicle models are now much more detailed
Tesla_Raj/Twitter

Tesla currently shows seven different vehicle types, which include:

  • motorcycles
  • sedans
  • minivans/SUVs
  • pickup trucks
  • small trucks
  • tractor trailers
  • buses

Own Vehicle Attributes

When Autopilot is enabled you'll see a single line that determines the path the car is going to take. This is similar to using Navigate on Autopilot on the highway, except in this case the visualization is dotted and changes color.

Creep Visualization

A new visualization was introduced in FSD Beta 10.69 that allows you to visually see how far your vehicle is expected to creep forward. Prior to this visualization it was impossible to determine how far your vehicle was going to creep, which could make the driver feel uncomfortable in busy areas.

You can now visually see until where your vehicle will creep forward
You can now visually see until where your vehicle will creep forward
Chuck Cook/YouTube

Vehicle Path

The vehicle's intended path
The vehicle's intended path
DirtyTesla/YouTube

The line in front of the vehicle denotes the path the car is planning to take. The color of the path will vary, letting you know whether the car will be accelerating or braking at the given location.

As of FSD Beta 10.8, the line is now continous and blue. The darker blue portion of the line denotes that the vehicle will accelerate until it gets to the faded blue portion of the path. The faded blue segment represents when the vehicle will stop.

This is extremely helpful as it lets you know when the vehicle is planning to stop.

Prior to FSD Beta 10.8, the vehicle's path was shown as a dotted gray and teal line. When the dot is teal it shows that the vehicle is planning to continue moving at that location.

Tesla visualization displaying teal dots and what it means
The teal path represents when the car will accelerate
DirtyTesla/YouTube

In contrast to the teal path, the gray line denotes that the vehicle will not be accelerating at that location.

Ultrasonic Sensor Arcs

If the vehicle detects an object through its ultrasonic sensors, it will display an arc on the display in the direction of the object. The arc will change color depending on the distance of the object. The colors range from gray (furthest away), to yellow and red (closer object).

Road markings

There are various markings on the ground that help aid drivers and pedestrians.

Stopping Line

When coming to a red traffic light or a stop sign, you'll see the stopping line displayed. You may see it displayed in the car even if it's not on the road itself.

Crosswalks

Crosswalks have been displayed in FSD Betas for a while, but recently their visualization has been changed to a solid gray area inside of a pair of parallel lines. I'd like to see a texture added on top of these to include the often used crossing stripes on crosswalks.

Tesla displaying crosswalks

Arrows on Road

Arrows on the road which are often used to display which direction you can go in the given lane are displayed in the visualization.

Tesla visualization displaying road arrows

Images on the Road

Tesla FSD railroad crossing
Tesla FSD railroad crossing

Certain roads may contain images directly on the pavement to indicate a special use case. The car can correctly identify bicycle lanes, railroad crossings and handicap parking spots.

Tesla FSD can identify handicap parking spots
Tesla FSD can identify handicap parking spots

Words on the Road

Sometimes words are painted directly on the road. The car will only display a small subset of words that are seen while driving. You may see Stop and some others, but it's important to note that the car is not able to decipher each letter on the road and put together a word. The text shown in visualizations is predetermined.

Road Chevrons

You may occasionally see chevrons displayed in your lane. This visualization is not mimicking a real world object, but is instead used to let you know the car is slowing down because your lane is moving much faster than adjacent lanes.

Object Colors and Attributes

Sometimes you may see an object in the visualization change color. There are various visualization that change color to represent a special meaning.

Red Pedestrian

Similar to when a vehicle turns red, you may see a pedestrian flash red if your car is approaching a pedestrian too quickly.

Tesla warning you about a pedestrian
Tesla warning you about a pedestrian

Red Stopping Line

You'll sometimes see a stopping line turn red if you're approaching a stop sign or red light.

Blue Vehicle

If a vehicle turns blue in the visualization it means that this vehicle is in or will be in the direct path that your vehicle is planning to take. It will return to it's normal shade of gray once it passes.

Tesla visualization displaying blue cars and what it means

Red Vehicle

A vehicle will turn red when immediate action is required, such as in a Forward Collision Warning. The car has deemed that its rate of speed is too high based on the distance and speed of the vehicle in front of you.

Dark Gray Vehicle

A vehicle will turn a darker shade of gray if it's considered a lead vehicle. Your car uses a lead vehicle to help determine what to do. If your car is headed in the same direction as the lead vehicle it will follow it and use the lead vehicle to help determine the path your car should take.

A dark gray vehicle represents a lead vehicle
A dark gray vehicle represents a lead vehicle
DirtyTesla/YouTube

Brake lights

Brake lights are now displayed on other vehicles. This helps give the car another cue of when to slow down instead of basing it on the distance of the vehicle alone.

Elon has already said that Tesla will be expanding this beyond just brake lights and we'll see the car detect and react to turn signals, hazards, hand gestures and more.

The brake lights visualization has been improved
The brake lights visualization has been improved
@FrenchieEAP/Twitter

Traffic control

Traffic Lights

Tesla FSD displays traffic lights with arrows
Tesla FSD displays traffic lights with arrows

Traffic lights are displayed in collections of three and will display solid or flashing colors. The car will also display red, yellow or green arrows. You may see traffic lights displayed in other areas that use flashing lights such as "slow" signs or railroad crossings.

The visualization in the car is currently only capable of displaying the traditional three traffic lights, so regardless of how many lights there are in the object your car is detecting, it'll always display a 3-light traffic light.

Tesla visualization traffic lights

Speed Limit Signs

The car will detect and display various speed limit signs. It's not able to detect arbitrary signs, such as 23 MPH, but it will display predetermined speed limit signs.

Stop Signs

Stop signs are also displayed in red. As Tesla continues to develop FSD, I'd love to see Tesla augment real world data with map data. If the car is at an intersection that it knows there are stop signs in all directions, that's useful data when deciding when to go. It would also be a useful aid when someone is not in Autopilot, warning drivers that the crossing street does not stop.

Lines & Curbs

The car will display major lane markings and display them based on the road width and curvature. The car determines the road edges using only vision and it does not rely on map data to determine where roads are located or configured.

Single/Double Yellow Lines

Tesla visualization red lines showing a curb

The car will display continuous yellow lines and display them in yellow on the display.

Continuous/Dashed White Lines

Continuous white lines are also very accurately displayed

Red Lines

Red lines in the visualization determine the road edge and determine the driveable area for the vehicle. The red line may be at the same location as a yellow or white line if there is no space before the curb. You may also often see a large gap between a white or yellow line and the red line, which can be due to an emergency lane or large space before the curb.

Future Visualizations

Tesla continues to add more objects that the car is able to detect, react to and visualize in every update.

The latest update added speed bumps and improved sidewalks. The car can already detect emergency vehicles, but they're not displayed on the screen yet, but we know they're coming as models have already been found in recent Tesla firmware.

Teslas will soon be able to identify various emergency vehicles, including motocycles. They will also display sirens on the vehicles.

Tesla has come a long way in a short period of time with how many objects they're able to detect, but obviously when you compare the environment the car sees to the real world, there is still a lot missing.

In the short-term we'll likely see a bunch more objects visualized. We'll likely see other common objects added, especially if they appear on the road, such as trailers and gates.

In the future, I think we'll see Tesla display a rich, fuller 3D environment that will display static objects that the car will want to avoid in case of an accident, such as buildings, walls, trees, sidewalks and more.

Have a visualization we missed? Let us know and we'll add it.

Ordering a New Tesla?

Consider using our referral code (karan29050) to get up to $2,000 off your new Tesla and get 3 Months of FSD for free.

Tesla Included FSD V12.6.1 and V13.2.4 in the Same Update: What Caused This and What It Means

By Karan Singh
Not a Tesla App

Tesla launched two FSD updates simultaneously on Saturday night, and what’s most interesting is that they arrived on the same software version. We’ll dig into that a little later, but for now, there’s good news for everyone. For Hardware 3 owners, FSD V12.6.1 is launching to all vehicles, including the Model 3 and Model Y. For AI4 owners, FSD V13.2.4 is launching, starting with the Cybertruck.

FSD V13.2.4

A new V13 build is now rolling out to the Cybertruck and is expected to arrive for the rest of the AI4 fleet soon. However, this build seems to be focused on bug fixes. There are no changes to the release notes for the Cybertruck with this release, and it’s unlikely to feature any changes when it arrives on other vehicles.

While this update focuses on bug fixes, Tesla’s already working on bigger features for FSD V13.3, which we have already confirmed to include improvements to highway following and speed control.

FSD V12.6.1

FSD V12.6.1 builds upon V12.6, which is the latest FSD version for HW3 vehicles. While FSD V12.6 was only released for the redesigned Model S and Model X with HW3, FSD V12.6.1 is adding support for the Model 3 and Model Y.

While this is only a bug-fix release for users coming from FSD V12.6, it includes massive improvements for anyone coming from an older FSD version. Two of the biggest changes are the new end-to-end highway stack that now utilizes FSD V12 for highway driving and a redesigned controller that allows FSD to drive “V13” smooth.

It also adds speed profiles, earlier lane changes, and more. You can read our in-depth look at all the changes in FSD V12.6.

Same Update, Multiple FSD Builds

What’s interesting about this software version is that it “includes" two FSD updates, V12.6.1 for HW3 and V13.2.4 for HW4 vehicles. While this is interesting, it’s less special when you understand what’s happening under the hood.

The vehicle’s firmware and Autopilot firmware are actually completely separate. While a vehicle downloading a firmware update may look like a singular process, it’s actually performing several functions during this period. First, it downloads the vehicle’s firmware. Upon unpacking the update, it’s instructed which Autopilot/FSD firmware should be downloaded.

While the FSD firmware is separate, the vehicle can’t download any FSD update. The FSD version is hard-coded in the vehicle’s firmware that was just downloaded. This helps Tesla keep the infotainment and Autopilot firmware tightly coupled, leading to fewer issues.

What we’re seeing here is that HW3 vehicles are being told to download one FSD version, while HW4 vehicles are being told to download a different version.

While this is the first time Tesla has had two FSD versions tied to the same vehicle software version, the process hasn’t actually changed, and what we’re seeing won’t lead to faster FSD updates or the ability to download FSD separately. What we’re seeing is the direct result of the divergence of HW3 and HW4.

While HW3/4 remained basically on the same FSD version until recently, it is now necessary to deploy different versions for the two platforms. We expect this to be the norm going forward, where HW3 will be on a much different version of FSD than HW4. While each update may not include two different FSD versions going forward, we may see it occasionally, depending on which features Autopilot is dependent on.

Thanks to Greentheonly for helping us understand what happened with this release and for the insight into Tesla’s processes.

Nvidia’s Cosmos Offers Synthetic Training Data; Following Tesla’s Lead

By Karan Singh
Not a Tesla App

At the 2025 Consumer Electronics Show, Nvidia showed off its new consumer graphics cards, home-scale compute machines, and commercial AI offerings. One of these offerings included the new Nvidia Cosmos training system.

Nvidia is a close partner of Tesla - in fact, they produce and supply the GPUs that Tesla uses to train FSD - the H100s and soon-to-be H200s, located at the new Cortex Supercomputing Cluster at Giga Texas. Nvidia will also challenge Tesla’s lead in developing and deploying synthetic training data for an autonomous driving system - something Tesla is already doing.

However, this is far more important for other manufacturers. We’re going to take a look at what Nvidia is offering and how it compares to what Tesla is already doing. We’ve done a few deep dives into how Tesla’s FSD works, how Tesla streamlines FSD, and, more recently, how they optimize FSD. If you want to get familiar with a bit of the lingo and the background knowledge, we recommend reading those articles before continuing, but we’ll do our best to explain how all this synthetic data works.

Nvidia Cosmos

Nvidia’s Cosmos is a generative AI model created to accelerate the development of physical AI systems, including robots and autonomous vehicles. Remember - Tesla’s FSD is also the same software that powers their humanoid robot, Optimus. Nvidia is aiming to tackle physical, real-world deployments of AI anywhere from your home, your street, or your workplace, just like Tesla.

Cosmos is a physics-aware engine that learns from real-world video and builds simulated video inputs. It tokenizes data to help AI systems learn quicker, all based on the video that is input into the system. Sound familiar? That’s exactly how FSD learns as well.

Cosmos also has the capability to do sensor-fused simulations. That means it can take multiple input sources - video, LiDAR, audio, or whatever else the user intends, and fuse them together into a single-world simulation for your AI model to learn from. This helps train, test, and validate autonomous vehicle behavior in a safe, synthetic format while also providing a massive breadth of data.

Data Scaling

Of course, Cosmos itself still requires video input - the more video you feed it, the more simulations it can generate and run. Data scaling is a necessity for AI applications, as you’ll need to feed it an infinite amount of data to build an infinite amount of scenarios for it to train itself on.

Synthetic data also has a problem - is it real? Can it predict real-world situations? In early 2024, Elon Musk commented on this problem, noting that data scales infinitely both in the real world and in simulated data. A better way to gather testing data is through real-world data. After all, no AI can predict the real world just yet - in fact, that’s an excellent quantum computing problem that the brightest minds are working on.

Yun-Ta Tsai, an engineer at Tesla’s AI team, also mentioned that writing code or generating scenarios doesn’t cover what even the wildest AI hallucinations might come up with. There are lots of optical phenomena and real-world situations that don’t necessarily make sense in the rigid training sets that AI would develop, so real-world data is absolutely essential to build a system that can actually train a useful real-world AI.

Tesla has billions of miles of real-world video that can be used for training, according to Tesla’s Social Media Team Lead Viv. This much data is essential because even today, FSD encounters “edge cases” that can confuse it, slow it down, or render it incapable of continuing, throwing up the dreaded red hands telling the user to take over.

Cosmos was trained on approximately 20 million hours of footage, including human activities like walking and manipulating objects. On the other hand, Tesla’s fleet gathers approximately 2,380 recorded minutes of real-world video per minute. Every 140 hours - just shy of 6 days - Tesla’s fleet gathers 20 million hours of footage. That was a little bit of back-of-the-napkin math, calculated at 60 mph as the average speed.

Generative Worlds

Both Tesla’s FSD and Nvidia’s Cosmos can generate highly realistic, physics-based worlds. These worlds are life-like environments and simulate the movement of people and traffic and the real-life position of obstacles and objects, including curbs, fences, buildings, and other objects.

Tesla uses a combination of real-world data and synthetic data, but the combination of data is heavily weighted to real-world data. Meanwhile, companies who use Cosmos will be weighting their data heavily towards synthetically created situations, drastically limiting what kind of cases they may see in their training datasets.

As such, while generative worlds may be useful to validate an AI quickly, we would argue that these worlds aren’t as useful as real-world data to do the training of an AI.

Overall, Cosmos is an exciting step - others are clearly following in Tesla’s footsteps, but they’re extremely far behind in real-world data. Tesla has built a massive first-mover advantage in AI and autonomy, and others are now playing catch-up.

We’re excited to see how Tesla’s future deployment of its Dojo Supercomputer for Data Labelling adds to its pre-existing lead, and how Cortex will be able to expand, as well as what competitors are going to be bringing to the table. After all, competition breeds innovation - and that’s how Tesla innovated in the EV space to begin with.

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