Tesla Reveals How It Tests FSD - A Series of Videos

Not a Tesla App

Tesla has published a 16-post series covering a wide range of unique scenarios against which the company tests each FSD release. Tesla’s VP of AI, Ashok Elluswamy, also provided some additional context, which we’ll cover below.

These scenarios could be difficult for a regular driver to respond to and are a good demonstration of FSD’s capabilities. Let’s take a look at all the different scenarios that Tesla regularly tests against. According to Ashok, these tests are only one of 10 ways Tesla validates their software. These tests were done against FSD v12.5.6.3, the HW4 build that’s on approximately 20% of the fleet.

We’ve embedded each video below and also provided some additional information.

1. Reverse Cut-in (Occluded)

Every FSD release is rigorously tested, including rare and adversarial scenarios on closed courses — Here's 16 examples:

1. Reverse Cut-in (Occluded) pic.twitter.com/VWBKDgVuUc

— Tesla AI (@Tesla_AI) November 24, 2024

This first test is for a car reversing out of a parking space, while occluded (vision blocked) by another car or obstacle. In the test, the Model Y notices the incoming car and then brakes with space left over.

2. Peeking (Occluded)

2. Peeking (Occluded) pic.twitter.com/DO3RBhahdy

— Tesla AI (@Tesla_AI) November 24, 2024

In this video, it's hard to even spot the car on the right that’s “peeking” forward—it's occluded by bushes on the side of the road. FSD notices and stops in time to let the other vehicle safely pass.

3. Left Turn Cut-in

3. Left Turn Cut-In pic.twitter.com/ie7VQ9Smtj

— Tesla AI (@Tesla_AI) November 24, 2024

An incoming vehicle that takes a left turn to enter the same lane of travel as FSD - spotted, stopped, and then continuing smoothly. In the second shot, you can see FSD left a considerable amount of space to let the vehicle cut in.

4. Parallel Cut-in (Occluded)

4. Parallel Cut-In (Occluded) pic.twitter.com/RbstvLU7Vo

— Tesla AI (@Tesla_AI) November 24, 2024

This is honestly one of the most common scenarios on a highway - someone cuts in while obscured into your lane of travel. Once again, FSD does its thing with plenty of space to spare.

5. Yield for Oncoming During Overtake

5. Yield for Oncoming During Overtake pic.twitter.com/hXWLCIEHu2

— Tesla AI (@Tesla_AI) November 24, 2024

FSD’s path planner plans an overtake around a stationary vehicle here, sees the oncoming traffic, and politely waits its turn to continue. This is another everyday scenario, especially on urban and suburban streets.

6. Stop Sign Right-of-Way Violator

6. Stop Sign Right-of-Way Violator pic.twitter.com/OHfvzP9t6A

— Tesla AI (@Tesla_AI) November 24, 2024

There are a surprising number of people who don’t know how stop signs work. However, FSD does know how they work and also knows what to do if others act unpredictably. This is one of the best demonstrations of FSD’s capability to react quickly and effectively to unpredictable behavior on the roads.

7. Door Opening During Overtake

7. Door Opening During Overtake pic.twitter.com/ZMDd3BWXI7

— Tesla AI (@Tesla_AI) November 24, 2024

Another overtake scenario, but this time the vehicle being overtaken throws open its door into traffic. Not necessarily the wisest of moves, but humans are unpredictable. Good to see Tesla working to save its vehicles from both hitting the door or having the door hit with its new Blind Spot Monitoring While Parked feature.

8. Right Turn Harsh Braking

8. Right Turn Harsh Braking pic.twitter.com/s4PldABmhK

— Tesla AI (@Tesla_AI) November 24, 2024

This scenario is another common one - someone is taking a right turn, and you expect them to complete the turn, but instead, they slam on the brakes. Here, you can see the vehicle’s Forward Collision Warning goes off due to the sudden reduction of distance between the Tesla and the vehicle in front of it. FSD still manages to brake in time before Automatic Emergency Braking kicks in.

9. Left Turn Across Path

9. Left Turn Across Path pic.twitter.com/MYKj4Z352f

— Tesla AI (@Tesla_AI) November 24, 2024

This one is pretty clean-cut - someone takes a left turn even though you’re on your way through the intersection. This particular accident is one of the most common - 53% of cross-path accidents involve a left turn through an intersection where a side impact will be lethal. FSD can make a big difference - over 8,000 people die in North America alone in this particular scenario.

10. Cut-Out to Static Cone

10. Cut-Out to Static Cone pic.twitter.com/l4OYzLK6XB

— Tesla AI (@Tesla_AI) November 24, 2024

Here, FSD smoothly reacts to an object on the road as the vehicle ahead dodges it. We’d love to see this scenario done with different types of objects or debris, as this is another common item - especially with roadkill on country roads. A good demo of FSD’s collision avoidance maneuvers too!

11. Dynamic Debris (Dropped Cone)

11. Dynamic Debris (Dropped Cone) pic.twitter.com/BMOKmrx9Ds

— Tesla AI (@Tesla_AI) November 24, 2024

Taking it one step further, FSD successfully notices, slows down, stops itself from hitting the bouncing cone, and then makes it around safely. If you’ve ever seen someone strap something down in the bed of a pickup and forget to say “This ain’t going anywhere” - this is that exact scenario.

12. U-Turn Cut-in (Occluded)

12. U-Turn Cut-In (Occluded) pic.twitter.com/gp7H720mJd

— Tesla AI (@Tesla_AI) November 24, 2024

Another high-speed occluded cut-in, this time for a vehicle making a U-Turn from an oddly shaped intersection. FSD started braking the moment the first couple pixels of the Model Y were beyond the bush occluding vision. With a human’s reaction time, this would have resulted in a T-bone.

Ashok Elluswamy mentioned that this is possible because of low latency and high intelligence - combined together, it enables FSD to make a threat assessment and decide what to do, very quickly. It also considers the potential of a rear-end collision - and there is collision avoidance baked into that decision-making.

13. High-Speed Cut-out to Stationary Vehicle

13. High Speed Cut-Out to Stationary Vehicle pic.twitter.com/qC8JQU4WH1

— Tesla AI (@Tesla_AI) November 24, 2024

Similar to the cone cut-out, this one happens at 73mph (117km/h)! FSD sees the car dodging, notices there’s an obstacle, and moves out of the way without dropping speed.

14. High-Speed Harsh Braking

14. High Speed Harsh Braking pic.twitter.com/YD76gh5b2m

— Tesla AI (@Tesla_AI) November 24, 2024

Another common scenario - in fact, the number one reason why pileups occur on highways is the harsh, sudden braking of vehicles in front. FSD once again notices and comes to a safe stop here.

15. High-Speed Stationary Child

15. High Speed Stationary Child pic.twitter.com/sh8xoMo8eF

— Tesla AI (@Tesla_AI) November 24, 2024

Tesla has been previously greatly criticized for its ability to come to a safe stop for children playing on the road. Here, Tesla is demonstrating its capability of doing so - once again with highway speeds of 73mph. 

16. High-Speed Crossing Child

16. High Speed Crossing Child pic.twitter.com/t6bxJpZOZn

— Tesla AI (@Tesla_AI) November 24, 2024

And to really make the point - it can do it with a crossing child too. Tesla has made a strong commitment to safety for vulnerable road users, and this is a good way to show how it works.

That’s a lot of unique scenarios that Tesla tests against - and each and every build has to be vetted against this huge list of different safety tests in order to ensure that the build that ends up in customer hands is as safe as possible. With FSD v13 looking like it's coming soon, we’re excited to see where this takes Tesla next. 

With Musk announcing that FSD v13 is coming soon, it really is starting to feel like Unsupervised FSD and Robotaxi could be pushed out sometime next year.

Follow

Follow

Follow

NHTSA Probes Tesla’s Robotaxi Plans; Seeks Answers on FSD in Poor Weather

Not a Tesla App

As anticipation builds for Tesla’s Robotaxi network debut in Austin, potentially just a few short weeks away, the National Highway Traffic Safety Administration (NHTSA) is turning its official eye onto Tesla. The ask? How will Tesla’s FSD handle the unpredictable realities of challenging weather?

The NHTSA Request

The NHTSA has sent a formal letter to Tesla, which was made public on May 12th, requesting detailed information about Tesla’s Robotaxi service. The NHTSA inquiry centers specifically on the safety and performance of FSD when faced with reduced visibility conditions like rain, fog, and sun glare. The request is tied to an ongoing NHTSA investigation, which was initiated in October 2023, examining Tesla’s FSD and Autopilot suite following incidents in poor visibility.

Tesla’s executives, including Elon Musk, have previously stated that the company is full steam ahead to launch Robotaxi in Austin this June. However, NHTSA’s pointed questions come even as Tesla has recently discussed its plans to work on region-specific and weather-specific FSD training.

Tesla’s executive leadership acknowledged the need to adapt the system to diverse environmental and weather conditions. Now, regulators want specifics on how Tesla intends to address environmental conditions and how that translates to operational safety for the fleet.

Request Breakdown

NHTSA’s letter outlines a need for detailed information from Tesla before the service launches and covers several key areas. We’ve broken this down into various sections below:

Deployment Scale

NHTSA is looking for the exact number of vehicles and models that will be part of the initial Austin fleet, and what the projected service availability times would be for said fleet. Tesla has previously said it’d launch with 10-20 Model Ys, but looks like NHTSA is looking for additional details.

Oversight

In terms of oversight, NHTSA is looking to confirm whether the Robotaxis will operate under real-time supervision of Tesla’s employees, either remotely or in-vehicle.

This is a question on our minds as well. A recent app update suggested that Tesla could have a driver in the vehicle, but it wasn’t clear whether this was referring to Tesla’s own fleet or customer-owned vehicles. The only thing we have heard officially from Tesla is that Tesla “may” use remote support, but that they were still looking into it.

Adverse Weather Capabilities

This is the meat and potatoes of the request - how will Tesla ensure safety during sun glare, fog, heavy rain, snow, or dust? What specific protocols are triggered if poor visibility is encountered mid-trip? Will the vehicle pull over or call home and cancel rides?

Sensor Technology

Surprisingly, NHTSA is looking for details regarding the vehicle the Robotaxi sensor suites and how Tesla intends to use those sensors to ensure safe operation under varied conditions. NHTSA has had previous submissions from Tesla in regard to its sensor suite and how it uses the technology, so it feels odd that they are requesting another batch - but this could be related to the use of the next generation of FSD (Unsupervised).

Compliance

Does Tesla’s FSD system adhere, either fully or partially, to established industry standards for autonomous driving? This likely refers to the NHTSA Automated Vehicles for Safety guidebook, which lays out the “L0 to L5” driver assistance vs automation system.

Future Expansion

Finally, NHTSA is looking for the timeline for enabling Robotaxi functionality on vehicles not directly owned or controlled by Tesla. Tesla has already come out and said that customer-owned vehicles wouldn’t be allowed on the robotaxi network until 2026, but obviously, NHTSA wants to hear directly from Tesla and likely has more specific questions covering a wide variety of potential issues.

These questions will likely have to be answered with considerable amounts of data and justification for the NHTSA. Once all that is done, Tesla will be in a better position to receive regulatory approval at a larger scale than just within the city of Austin or the state of Texa with the NHTSA’s backing.

Successfully addressing this letter will be the key for Unsupervised FSD moving forward, but Tesla hasn’t issued a public response to the agency’s letter, and likely won’t in a public manner. So we’ll have to wait and see how the launch of the Robotaxi network pans out next month.

Follow

Follow

Follow

FSD V13.2.9 Rolls Out for HW4 as Part of Tesla’s 2025.14.6 Update

Not a Tesla App

After an 84-day wait since the last FSD update, Tesla has finally begun rolling out a new version of FSD V13 to its AI4-equipped vehicles. This new release, V13.2.9, is rolling out to all vehicles, including the Cybertruck.

Unfortunately, since it’s a minor point release (from V13.2.8), the release notes are the same, and Tesla hasn’t included a change log or changed what’s coming in the future.

Software Update 2025.14.6

The FSD update is rolling out with Tesla software update 2025.14.6. Interestingly, update 2025.14.6 is seeing a wider distribution and is also being made available to vehicles without FSD and outside North America. For those vehicles, this update just includes bug fixes.

TCU Fix

There’s one fix in particular that’s expected to be included in this update, according to a message from Tesla Service. In earlier 2025.14 updates, there was a bug in some vehicles that prevented some vehicles from falling asleep properly due to a Telematics Control Unit (TCU) issue. This bug caused additional battery drain since some of the vehicle’s systems remained on.

Tesla Service said they planned to include a bug fix in update 2025.14.6, but it hasn’t been confirmed whether the fix actually made it out in this release.

Early Access Users and More

FSD v13.2.9 was first rolled out to Tesla’s standard Early Access group, including well-known community members and content creators. It has also reached participants in the newer, Texas-based Early Access Program, suggesting that the update is relatively stable and may serve as a foundation for upcoming FSD releases.

Tesla could be intending to use the Texas Early Access Program to test various features, perhaps related to the upcoming Robotaxi network launch in Austin. While this is plausible, it is merely speculation, and we’ll be keeping a close eye on that group to see what exactly Tesla does.

HW3 Users

While Tesla has recently been including FSD updates for HW3 and HW4 in the same release, this update does not include any changes for HW3 users. HW3 vehicles that are receiving this update are staying on FSD V12.6.4, which means that whichever fixes this update includes they’re specific to FSD V13 or HW4.

Point Release - Not Much New

Being a point release, V13.2.9 isn’t expected to introduce any major new capabilities. Tesla hasn’t provided specific release notes detailing changes from V13.2.8.

Hopefully, Tesla has taken into account recent user feedback on V13.2.8 about lane centering and lane selection, and this update addresses some of those issues. However, early feedback is that those issues are still present.

There is always potential for a more substantial update in the near future, so keep your fingers crossed, but after such a long wait, we expected more to be included. It seems like Tesla may have felt the need to address a bug in this release instead of waiting for the next major release, which is expected to either be FSD V13.3 or FSD V14.

Roll Out

The fact that Software Update 2025.14.6 is going out wider than the Early Access audience suggests that Tesla is confident in this release and that it likely only includes very minor changes. We expect this update to continue going out over the coming days.

Follow

Follow

Follow