How Tesla’s FSD Works - Part 2

March 3, 2025

By Karan Singh

Not a Tesla App

We previously dived into how FSD works based on Tesla’s patents back in November, and Tesla has recently filed for additional patents regarding its training of FSD.

This particular patent is titled “Predicting Three-Dimensional Features for Autonomous Driving” - and it’s all about using Tesla Vision to establish a ground truth - which enables the rest of FSD to make decisions and navigate through the environment.

This patent essentially explains how FSD can generate a model of the environment around it and then analyze that information to create predictions.

Time Series

Creating a sequence of data over time - a Time Series - is the basis for how FSD understands the environment. Tesla Vision, in combination with the internal vehicle sensors (for speed, acceleration, position, etc.,) establishes data points over time. These data points come together to create the time series.

By analyzing that time series, the system establishes a “ground truth” - a highly accurate and precise representation of the road, its features, and what is around the vehicle. For example, FSD may observe a lane line from multiple angles and distances as the vehicle moves through time, allowing it to determine the line’s precise 3D shape in the world. This system helps FSD to maintain a coherent truth as it moves forward - and allows it to establish the location of things in space around it, even if they were initially hidden or unclear.

Author’s Note

Interestingly, Tesla’s patent actually mentions the use of sensors other than Tesla Vision. It goes on to mention radar, LiDAR, and ultrasonic sensors. While Tesla doesn’t use radar (despite HD radars being on the current Model S and Model X) or ultrasonic sensors anymore, it does use LiDAR for training.

However, this LIDAR use is for establishing accurate sensor data for FSD - for training purposes. No Tesla vehicle is actually shipped with any LiDAR sensors. You can read about Tesla’s use for its LIDAR training rigs here.

Associating the Ground Truth

Once the ground truth is established, it is linked to specific points in time within the time series - usually a single image or the amalgamation of a set of images. This association is critical - it allows the system to predict the complete 3D structure of the environment from just that single snapshot. In addition, they also serve as a learning tool to help FSD understand the environment around it.

Imagine FSD has figured out the exact curve of a lane line using data from the time series. Next, it connects this knowledge to the particular image in the sequence where the lane line was visible. Next, it applies what it has learned - the exact curve, and the image sequence and data - to predict the 3D shape of the line going forward - even if it may not know for sure what the line may look like in the future.

Author’s Note

This isn’t part of the patent, but when you combine that predictive knowledge with precise and effective map data, that means that FSD can better understand the lay of the road and plan its maneuvers ahead of time. We do know that FSD takes into account mapping information. However, live road information from the ground truth is taken as the priority - mapping is just context, after all.

That is why when roads are incorrectly mapped, such as the installation of a roundabout in a location where a 4-way stop previously existed, FSD is still capable of traversing the intersection.

Three Dimensional Features

Representing features that the system picks up in 3D is essential, too. This means that the lane lines, to continue our previous example, must move up and down, left and right, and through time. This 3D understanding is vital for accurate navigation and path planning, especially on roads with curves, hills, or any varying terrain.

Automated Training Data Generation

One of the major advantages of this entire 3D system is that it generates training data automatically. As the vehicle drives, it collects sensor data and creates time series associated with ground truths.

Tesla does exactly this when it uploads data from your vehicle and analyzes it with its supercomputers. The machine learning model uses all the information it gets to better improve its prediction capabilities. This is now becoming a more automated process, as Tesla is moving away from the need to manually label data and is instead automatically labeling data with AI.

Semantic Labelling

The patent also discusses the use of semantic labeling - a topic covered in our AI Labelling Patent. However, a quick nitty-gritty is that Tesla labels lane lines as “left lane” or “right lane,” depending on the 3D environment that is generated through the time series.

On top of that, vehicles and other objects can also be labelled, such as “merging” or “cutting in.” All of these automatically applied labels help FSD to prioritize how it will analyze information and what it expects the environment around it to do.

How and When Tesla Uploads Data

Tesla’s data upload isn’t just everything they may catch - even though they did draw an absolutely astounding 1.28 TB from the author’s Cybertruck once it received FSD V13.2.2. It is based on transmitting selective sensor information based on triggers. These triggers can include incorrect predictions, user interventions, or failures to correctly conduct path planning.

Tesla can also request all data from certain vehicles based on the vehicle type and the location - hence the request for the absurd 1.28 TB coming from one of the first Canadian Cybertrucks. This allows Tesla to collect data from specific driving scenarios - which it needs to help build better models that are more adaptable to more circumstances while also keeping data collection focused, thereby making training more efficient.

How It Works

To wrap that all up, the model applies predictions to better navigate through the environment. It uses data collected through time and then encapsulated in a 3D environment around the vehicle. Using that 3D environment, Tesla’s FSD formulates predictions on what the environment ahead of it will look like.

This process provides a good portion of the context that is needed for FSD to actually make decisions. But there are quite a few more layers to the onion that is FSD.

Adding in Other Layers

The rest of the decision-making process lies in understanding moving and static objects on the road, as well as identifying and reducing risk to vulnerable road users. Tesla’s 3D mapping also identifies and predicts the pathing of other moving objects, which enables it to conduct its path planning. While this isn’t part of this particular patent per-say, it is still an essential element to the entire system.

If all that technical information is interesting to you, we recommend you check out the rest of our series on Tesla’s patents:

We’ll continue to dive deep into Tesla’s patents, as they provide a unique and interesting source to explain how FSD actually works behind the curtains. It’s an excellent chance to get a peek behind the silicon brains that make the decisions in your car, as well as a chance to see how Tesla’s engineers actually structure FSD.

Tesla FSD in Europe: June Update

June 14, 2025

By Karan Singh

Not a Tesla App

The road to bringing FSD to Europe has been a long and complex one and filled with regulatory and bureaucratic hurdles. Elon Musk, as well as other members of Tesla’s AI team, have previously voiced their grievances with the regulatory approval process on X.

However, it appears that there is finally some progress in getting things moving with recent changes to upcoming autonomy regulations, but the process still seems slow.

Waiting on the Dutch

Elon commented on X recently, stating that Tesla is waiting for approval from Dutch authorities and then the EU to start rolling out FSD in Europe. Tesla is focusing on acquiring approvals from the Dutch transportation authority, which will provide them with the platform they need to gain broader acceptance in Europe. Outside of the Netherlands, Tesla is also conducting testing in Norway, which provides a couple of avenues for them to obtain national-level approval.

The frustration has been ongoing, with multiple committee meetings bringing up autonomy regulation but always pulling back at the last second before approving anything. The last meeting on Regulation 157, which governs Automated Lane Keeping Systems, concluded with authorities from the UK and Spain requesting additional time to analyze the data before reaching a conclusion.

Tesla, as well as Elon, have motioned several times for owners to reach out to their elected representatives to move the process forward, as it seems that Tesla’s own efforts are being stymied.

This can seem odd, especially since Tesla has previously demoed FSD working exceptionally smoothly on European roads - and just did it again in Rome when they shared the video below on X.

FSD Supervised testing in Rome, Italy

Pending regulatory approval pic.twitter.com/TXh3uQIfrx
— Tesla Europe & Middle East (@teslaeurope) June 12, 2025

DCAS Phase 3

While the approval process has been slow, Kees Roelandschap pointed out that there may be a different regulatory step that could allow FSD to gain a foothold in Europe.

According to Kees, the European Commission is now taking a new approach to approving ADAS systems under the new DCAS Phase 3 regulations. The Commission is now seeking data from systems currently operational in the United States that can perform System-Initiated Maneuvers and don’t require hands-on intervention for every request.

This is key because those are two of the core functionalities that make FSD so usable, and it also means that there may not be a need to wait years for proper regulations to be written from scratch. Now, the Commission will be looking at real-world data based on existing, deployed technology, which could speed up the process immensely.

What This Means

This new, data-driven regulatory approach could be the path for Tesla to reach its previous target of September for European FSD. While the cogs of bureaucracy are ever slow, sometimes all it takes is a little data to have them turn a bit faster in this case.

Alongside specific countries granting approval for limited field testing with employees, there is some light at the end of the tunnel for FSD in Europe, and hopes are that a release will occur by the end of 2025. With Europe now looking to North America for how FSD is performing, Tesla’s Robotaxi results could also play a role.

Tesla Launches 'TeslaVision' Contest With Big Prizes — See Last Year’s Winner [VIDEO]

June 13, 2025

By Karan Singh

Not a Tesla App

Tesla’s marketing has always been relatively unconventional, relying on word-of-mouth rather than traditional advertising. The passion of the owner’s community is always massive, but it is especially high now with the launch of the Robotaxi network just around the corner.

Tesla is now tapping into that spring of fan creativity and announced the TeslaVision video contest, with some seriously impressive prizes up for grabs.

Announcing the TeslaVision fan video showcase

Tesla owners & supporters have always been able to see our products & mission for what they truly are.

Your word of mouth has made Tesla what it is today.

The OGs will remember that in 2017, we held our first video contest. 8 years… pic.twitter.com/6pPpkqmqOH
— Tesla (@Tesla) June 10, 2025

The Contest

The core of the contest is simple. Create a video that shows how your Tesla gives you more in life. Tesla is looking for submissions that highlight themes of freedom, safety, fun, and convenience.

Prizes

The prizes definitely make this contest worth entering if you’re good with a camera and have some basic video editing abilities.

For North America, the prizes include a brand new Model Y AWD Long Range, alongside an all-expenses-paid trip to Austin for a tour of Giga Texas. The grand prize winner will also be able to custom order their Model Y, allowing them to select their preferred wheels and color.

The two runners-up won’t get a Model Y, but they’ll also enjoy an all-expenses-paid trip to Giga Texas for a tour of the factory.

The travel and tour include lodging in Austin for 2 nights, as well as economy-class round-trip tickets from anywhere in North America. Tesla will also provide a vehicle for use during the trip.

Hopefully, these winners will also have the opportunity to experience the Robotaxi network while they’re in Austin, as it’s expected to be opened to the public later this month.

Project Loveday

For long-time followers of Tesla, this contest may feel familiar. The contest is a direct throwback to the 2017 Project Loveday contest, which was inspired by a letter to Tesla from a 10-year-old aspiring marketer. That contest was won by MKBHD, with his submission below:

How to Enter

If you’re ready to start filming, here are the key pieces of information you’ll need to know:

Video must be 90 seconds or less
Video must be uploaded to YouTube with a public URL
Make a post on X and Instagram tagging “@Tesla” and include the words “TeslaVision contest” in the post.
Provide links to both social media posts in your submission to Tesla’s form
Provide your personal details in the form
You have until July 17th, 2025, or until Tesla receives 10,000 entries, whichever comes first.

You can find the official submission form and all region-specific details on Tesla's website.