Inside Tesla’s FSD: Patent Explains How FSD Works

By Karan Singh
Not a Tesla App

Thanks to a Tesla patent published last year, we have a great look into how FSD operates and the various systems it uses. SETI Park, who examines and writes about patents, also highlighted this one on X.

This patent breaks down the core technology used in Tesla’s FSD and gives us a great understanding of how FSD processes and analyzes data.

To make this easily understandable, we’ll divide it up into sections and break down how each section impacts FSD.

Vision-Based

First, this patent describes a vision-only system—just like Tesla’s goal—to enable vehicles to see, understand, and interact with the world around them. The system describes multiple cameras, some with overlapping coverage, that capture a 360-degree view around the vehicle, mimicking but bettering the human equivalent.

What’s most interesting is that the system quickly and rapidly adapts to the various focal lengths and perspectives of the different cameras around the vehicle. It then combines all this to build a cohesive picture—but we’ll get to that part shortly.

Branching

The system is divided into two parts - one for Vulnerable Road Users, or VRUs, and the other for everything else that doesn’t fall into that category. That’s a pretty simple divide - VRUs are defined as pedestrians, cyclists, baby carriages, skateboarders, animals, essentially anything that can get hurt. The non-VRU branch focuses on everything else, so cars, emergency vehicles, traffic cones, debris, etc. 

Splitting it into two branches enables FSD to look for, analyze, and then prioritize certain things. Essentially, VRUs are prioritized over other objects throughout the Virtual Camera system.

The many data streams and how they're processed.
The many data streams and how they're processed.
Not a Tesla App

Virtual Camera

Tesla processes all of that raw imagery, feeds it into the VRU and non-VRU branches, and picks out only the key and essential information, which is used for object detection and classification.

The system then draws these objects on a 3D plane and creates “virtual cameras” at varying heights. Think of a virtual camera as a real camera you’d use to shoot a movie. It allows you to see the scene from a certain perspective.

The VRU branch uses its virtual camera at human height, which enables a better understanding of VRU behavior. This is probably due to the fact that there’s a lot more data at human height than from above or any other angle. Meanwhile, the non-VRU branch raises it above that height, enabling it to see over and around obstacles, thereby allowing for a wider view of traffic.

This effectively provides two forms of input for FSD to analyze—one at the pedestrian level and one from a wider view of the road around it.

3D Mapping

Now, all this data has to be combined. These two virtual cameras are synced - and all their information and understanding are fed back into the system to keep an accurate 3D map of what’s happening around the vehicle. 

And it's not just the cameras. The Virtual Camera system and 3D mapping work together with the car’s other sensors to incorporate movement data—speed and acceleration—into the analysis and production of the 3D map.

This system is best understood by the FSD visualization displayed on the screen. It picks up and tracks many moving cars and pedestrians at once, but what we see is only a fraction of all the information it’s tracking. Think of each object as having a list of properties that isn’t displayed on the screen. For example, a pedestrian may have properties that can be accessed by the system that state how far away it is, which direction it’s moving, and how fast it’s going.

Other moving objects, such as vehicles, may have additional properties, such as their width, height, speed, direction, planned path, and more. Even non-VRU objects will contain properties, such as the road, which would have its width, speed limit, and more determined based on AI and map data.

The vehicle itself has its own set of properties, such as speed, width, length, planned path, etc. When you combine everything, you end up with a great understanding of the surrounding environment and how best to navigate it.

The Virtual Mapping of the VRU branch.
The Virtual Mapping of the VRU branch.
Not a Tesla App

Temporal Indexing

Tesla calls this feature Temporal Indexing. In layman’s terms, this is how the vision system analyzes images over time and then keeps track of them. This means that things aren’t a single temporal snapshot but a series of them that allow FSD to understand how objects are moving. This enables object path prediction and also allows FSD to understand where vehicles or objects might be, even if it doesn’t have a direct vision of them.

This temporal indexing is done through “Video Modules”, which are the actual “brains” that analyze the sequences of images, tracking them over time and estimating their velocities and future paths.

Once again, heavy traffic and the FSD visualization, which keeps track of many vehicles in lanes around you—even those not in your direct line of sight—are excellent examples.

End-to-End

Finally, the patent also mentions that the entire system, from front to back, can be - and is - trained together. This training approach, which now includes end-to-end AI, optimizes overall system performance by letting each individual component learn how to interact with other components in the system.

How everything comes together.
How everything comes together.
Not a Tesla App

Summary

Essentially, Tesla sees FSD as a brain, and the cameras are its eyes. It has a memory, and that memory enables it to categorize and analyze what it sees. It can keep track of a wide array of objects and properties to predict their movements and determine a path around them. This is a lot like how humans operate, except FSD can track unlimited objects and determine their properties like speed and size much more accurately. On top of that, it can do it faster than a human and in all directions at once.

FSD and its vision-based camera system essentially create a 3D live map of the road that is constantly and consistently updated and used to make decisions.

Tesla Launches New Long Range RWD Model Y in U.S.: More Affordable and Longer Range

By Karan Singh
Not a Tesla App

Tesla has finally launched the refreshed Model Y Long Range Rear Wheel Drive (LR RWD) in the United States. While the refreshed Model Y RWD was available as a Launch-Series option in the Asia-Pacific and European markets, it wasn’t yet available at all in North America. Once the Launch Series stopped being offered, Tesla began shipping non-Launch Edition Model Y LR RWDs in Asia and Europe earlier this year, but didn’t bring it to the United States until now.

The LR RWD is one of Tesla’s most affordable vehicles, starting at $44,990 (or $37,490 after the Federal EV Rebate).

Model Y LR RWD

Spec-wise, the refreshed Model Y LR RWD is a compelling alternative to the AWD model. Tesla has kept the premium interior and audio options on the North American variant, so you get the full experience of the refreshed Model Y. You also get more range and faster charging than the AWD model. The only downside is that it’s two-wheel drive and slower acceleration. However, given the lower price and additional range, those may be worth the tradeoffs.

Vehicle

Range*

0-60mph

Charging Speed (15m)

2025 AWD

501 km / 310 mi

5.0s

239 km / 148 mi

2025 LR RWD

525 km / 326 mi

7.9s

250 km / 155 mi

2026 AWD (Juniper)

526 km / 327 mi

4.3s

266 km / 165 mi

2026 RWD (Juniper)

574 km / 357 mi

5.9s

271 km / 168 mi

*Listed ranges are EPA Ranges.

Pricing

All in all, you get a fantastic deal, given the lower price tag. The refreshed Model Y LR RWD is priced $4,000 less than the AWD version while still offering many of its attractive features.

Model

Price (USD)

Price (CAD)

2026 Model Y LR AWD

$48,990

$84,990*

2026 Model Y LR RWD

$44,990

Not available

*Post-tariff pricing.

Availability

The Long Range RWD is expected to begin shipping immediately in the United States. Tesla has not made the vehicle available in Mexico or Canada yet, likely due to tariff complications. Once the tariff rates settle, Tesla will likely look to export the vehicles from the U.S. to the other two North American countries.

With the arrival of the Long Range RWD variant, the last version we’re waiting for is the refreshed Model Y Performance. That’s likely to be an exciting vehicle, and we’re hopeful it will be in customers’ garages before the end of 2025.

Tesla Introduces New Dynamic Supercharger Pricing

By Karan Singh
Not a Tesla App

Tesla is adjusting its Supercharger prices based on current usage in a new pilot program. Tesla’s pricing structure has typically revolved around traditional time-based peak/off-peak schedules but is now migrating to a more dynamic model based on live Supercharger utilization.

This development, announced officially through the Tesla Charging X account, should make Supercharger pricing more accurately reflect the demand for the specific Supercharger site instead of basing pricing on past usage.

Live Utilization Pricing

The core of this new pilot will launch at just 10 Supercharger sites in North America. The particular sites in question have not been clarified, but one of the locations is the Supercharger located in Davis, California.

Tesla intends to expand the pilot based on feedback and the success of the initial rollout. We could be looking at the future of Supercharger pricing around the globe.

New Chart and Features

Today, Tesla typically offers two or three prices based on peak and off-peak demand, meaning that Supercharger prices are based on the hour of the day. The current Supercharger chart in the vehicle shows the hours and price on the X-axis, while the Y-axis is the typical demand (image below).

The current chart for Superchargers versus the new one at the top of the page
The current chart for Superchargers versus the new one at the top of the page
Not a Tesla App

However, with the new charts that will soon be added to vehicles, Tesla will display the time on the X-axis, and the Y-axis will show the historical demand and the current price (photo at the top of this page).

In theory, the Supercharger's historical demand and real-time usage should be pretty similar, but there will be exceptions, like holidays and other events. Unexpected high and low usage will play a role in the pricing, such as sporting events and natural disasters. If the Supercharger is busy, then pricing will be high; otherwise, it will be low.

This also introduces a new feature, since pricing is now based on actual demand, users could navigate to a Supercharger that is less busy and, therefore, cheaper. In the hero image, we can see that Tesla will add a new “Find Lower Price Charging” button in a future vehicle update. This will likely highlight other nearby Superchargers that are less busy and less expensive.

However, it seems like Tesla may also start charging more for Superchargers than they do today when they’re extremely busy. Judging by the screenshot Tesla shared, the estimated usage never passed the $0.45 per kWh at the Davis, CA Supercharger. However, it seems that there’s a new price of $0.54 per kWh when the Supercharger usage is at its peak.

The good news is that Tesla is being more transparent and indicating whether the price is low or high with new labels. This change will give users more choices in terms of charging prices. If you want to save a few bucks, you can drive to a less busy Supercharger. The price will also be based on actual usage, which seems like a fairer way to determine price.

While Tesla hasn’t updated vehicles yet to show these new charts, the latest version of the Tesla app already incorporates the changes.

What Tesla Says

Max de Zegher, Tesla’s Director of Charging, elaborated on the pilot program on X.

He points out that Tesla Charging’s rates have been consistent, and it has focused on improving the charging experience and availability. Off-peak and on-peak pricing will help to increase both of these.

Tesla has outlined exactly how this new live feedback loop will function. The more accurate real-time station demand can allow Tesla to adjust pricing if a station is experiencing congestion during traditionally “off-peak” hours. On the flipside, if a station is unusually empty, Tesla can reduce the pricing.

This easily incentivizes customers who are keeping an eye on charging costs, as changing your charging destination can be as simple as the tap of a button. Most interestingly, Tesla says that the average price paid by customers is expected to remain the same as with the previous time-based system, even with seasonal and real-time fluctuations.

Crucially, owners can always see the price per kWh on their vehicle’s primary display, as well as in the Tesla app before initiating a charging session. Additionally, Tesla will not change the pricing mid-charge, so there’s no need to worry about it fluctuating up or down while you’re charging.

Supercharger Pricing History

This move to live-based pricing is being presented as Tesla’s latest step towards managing its vast charging network with a more customer-centric approach. Tesla has had some historical progression in its pricing strategy, so let’s take a look at where we were versus where we are going.

kWh-Based Billing: Tesla has long pushed for billing by the kilowatt-hour (kWh) as the fairest method for customers to pay for the exact energy consumed, avoiding session fees that can obscure actual energy costs. This is now standard in most regions, but it wasn’t too long ago that pricing was determined by the minute.

Idle Fees (2017): To address vehicles remaining plugged in after charging was complete at busy sites, idle fees were implemented to improve stall availability – a practice now common across the industry.

80% SoC Limiter (2019): At busy locations, Tesla introduced an automatic 80% state-of-charge (SoC) charging limit (which users can manually override) to encourage faster turnover, as the final 20% of charging is significantly slower.

Time-Based Peak/Off-Peak Pricing (2020): Pricing based on estimated busy times was rolled out to incentivize charging during less congested periods, helping to distribute demand and manage costs.

Congestion Fees (2023): At particularly busy sites, congestion fees were introduced. These combine the principles of idle fees with disincentivizing charging to a very high state of charge when a station is crowded, with the stated goal of improving availability, not generating profit.

Commitment to Affordability

Alongside these pricing changes, Tesla has reiterated its focus on keeping Supercharging affordable for all its users. Tesla points out that, on average, in North America and Europe, Tesla’s Superchargers are 30% cheaper than other fast-charging options while also being far more reliable.

Beyond that, 2025 is set to be Tesla’s largest year for expanding the Supercharger network while also replacing many older V2 charging sites with faster, more capable V4 Supercharger stations.

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