Elon tweeted that v9 of the FSD beta would remove its reliance on radar completely and instead determine decisions based purely on vision. Humans don’t have radar after all, so it seems like a logical solution and tells us Tesla is feeling much more confident in their vision AI.
Radar and vision each have their advantages, but radar has thus far been much more reliable in detecting objects and determining speed. If you’ve ever noticed your Tesla being able to detect two vehicles in front of you when you can only see the one directly ahead of you, that’s radar at work.
In this situation the radio waves from the radar sensor are bouncing underneath the car in front of you and are able to continue traveling and detect that there is another object ahead even though it could never “see” it.
It really is one of those wow moments where you can feel the future and the ability for AI-powered cars to drive better than humans one day. It’s baby steps and slowly we’ll see more and more of these situations where the vehicle simply sees or does something we could never do.
There’s no doubting that more sensors could provide a more reliable and accurate interpretation of the real world as they each have their own advantages. In an ideal world a vehicle with radar, lidar, vision, ultrasonic sensors and even audio processing would provide the best solution. However, more sensors and systems come at a price, resulting in increased vehicle cost and system complexity.
After all humans are relatively safe drivers with two “cameras” and vision alone. If Tesla can completely solve vision, they’ll easily be able to achieve superhuman driving capabilities. Teslas have eight cameras, facing in all directions. They’re able to analyze all of them concurrently and make much more accurate interpretations then we ever could in the same amount of time.
Tristan on Twitter recently had some great insight into Tesla vision AI and how they’re going to replace radar. Here’s what Tristan had to say:
"We recently got some insight into how Tesla is going to replace radar in the recent firmware updates + some nifty ML model techniques
From the binaries we can see that they've added velocity and acceleration outputs. These predictions in addition to the existing xyz outputs give much of the same information that radar traditionally provides
(distance + velocity + acceleration).
For autosteer on city streets, you need to know the velocity and acceleration of cars in all directions but radar is only pointing forward. If it's accurate enough to make a left turn, radar is probably unnecessary for the most part.
How can a neural network figure out velocity and acceleration from static images you ask?
They can't!
They've recently switched to something that appears to be styled on an Recurrent Neural Network.
Net structure is unknown (LSTM?) but they're providing the net with a queue of the 15 most recent hidden states. Seems quite a bit easier to train than normal RNNs which need to learn to encode historical data and can have issues like vanishing gradients for longer time windows.
The velocity and acceleration predictions is new, by giving the last 15 frames (~1s) of data I'd expect you can train a highly accurate net to predict velocity + acceleration based off of the learned time series.
They've already been using these queue based RNNs with the normal position nets for a few months presumably to improve stability of the predictions.
This matches with the recent public statements from Tesla about new models training on video instead of static images.
To evaluate the performance compared to radar, I bet Tesla has run some feature importance techniques on the models and radar importance has probably dropped quite a bit with the new nets. See tools like https://captum.ai for more info.
I still think that radar is going to stick around for quite a while for highway usage since the current camera performance in rain and snow isn't great.
NoA often disables in mild rain. City streets might behave better since the relative rain speed is lower.
One other nifty trick they've recently added is a task to rectify the images before feeding them into the neural nets.
This is a common in classical CV applications so surprised it only popped up in the last couple of months.
This makes a lot of sense since it means that the nets don't need to learn the lens distortion. It also likely makes it a lot easier for the nets to correlate objects across multiple cameras since the movement is now much more linear.
For more background on LSTMs (Long Short-Term Memory) see https://towardsdatascience.com/illustrated-guide-to-lstms-and-gru-s-a-step-by-step-explanation-44e9eb85bf21
They're tricky to train because they need to encode history which is fed into future runs. The more times you pass the state, the more the earlier frames is diluted hence "vanishing gradients".
Tesla’s FSD beta v9 will be a big improvement forward from what FSD beta users have been using where the system was still relying on radar. And it’ll be an even bigger leap from what non-beta testers currently have access to. We can’t wait. Now where’s that button?
Almost ready with FSD Beta V9.0. Step change improvement is massive, especially for weird corner cases & bad weather. Pure vision, no radar.
Following the successful launch of Robotaxi on Sunday, June 22nd, Tesla has begun moving to the next phase of its Robotaxi rollout. They have finally begun sending out a second, larger wave of invites, expanding the early access program to more members of the Tesla community across the United States.
This has moved them past the initial 20 or so users that were offered access on Sunday. That also means Tesla is on the hunt for something crucial: more real-world data.
More Riders ASAP
The initial launch was a tightly controlled event, with access granted to a small and curated group of influencers. While this approach was ideal for generating initial buzz for the launch and collecting feedback from high-quality testers, it also presented logistical challenges.
With only a handful of authorized riders and vehicles, the demand for rides would inevitably dry up as influencers begin their journeys back home. Without a public release, that would leave Tesla’s Robotaxi fleet idle, unable to gather additional data.
To rapidly improve on Robotaxi’s FSD, Tesla needs its vehicles to be constantly navigating real-world scenarios, encountering edge cases, and logging miles. The second round of invites is needed to keep Robotaxis learning and on the road.
Austin Users Next?
This new wave of invites isn’t an open door for members of the public quite yet. By continuing to send invites to trusted community members, Tesla is executing a slow and deliberate rollout by inviting members who know and love Tesla. This allows them to scale the program gradually, increasing the number of users and the diversity of ride requests without overwhelming the relatively small initial fleet of about 10 cars.
Future phases will likely involve opening access to Tesla owners within Austin, which would open up a regular flow of rides. Once that’s done, Robotaxi will likely open up to the public.
Sign of Confidence
The expansion of the early access program is a sign that Tesla is happy and confident with the rollout so far. While Tesla can gather plenty of data around Austin from Tesla owners using FSD, they also need to continue testing features that are exclusive to the Robotaxi, such as the Robotaxi app, support, and remotely control the vehicles when needed.
We expect a full launch to potentially still be months out, but this methodical expansion will likely see more users gradually gain access to the Robotaxi network in the coming weeks.
Omead Afshar, who was previously Elon Musk’s “Fixer” and the Head of Operations for North America and Europe, has left the company, according to reports from Forbes and Bloomberg.
While some sources have claimed he was fired, others say he voluntarily left, but his exit isn’t exactly an isolated event.
Afshar’s departure is the second high-level exit this month, following Optimus' lead, Milan Kovac. When viewed together, alongside Elon's full-time return to Tesla, these changes may offer some insight into the pressures the Tesla executive team is facing during a transitional period.
Transition from what, you may ask? Well, from the world’s largest EV company to an AI and robotics-first company. This transition has been looming for years, and with Elon’s vision of a future powered by autonomous vehicles and humanoid robots. It’s the path that Tesla is determined to forge, ahead of anyone else, and despite the immense challenges of real-world AI.
Two Competing Narratives
Two primary theories have emerged to explain the timing of Afshar’s exit, and each paints quite a different picture.
The first, supported by the reporting from Forbes, frames him as a casualty of Tesla’s current sales issues. With sales having declined for five consecutive months in Europe and dropping in the US, the second quarter of 2025 has been rough for Tesla. In conjunction with recent factory shutdowns, a lot is happening behind the scenes, with Robotaxi taking the limelight and the missing Affordable Model in the backseat. Afshar’s departure could be the result of a move to show accountability for the performance drop of the core business he managed.
The second narrative is one of “mission accomplished.” Just days before his abrupt exit, Afshar posted a celebratory message on X about the successful launch of the Robotaxi Network.
Absolutely historic day for Tesla.
This has been years of hard work and focus by so many people within the company.
He followed up with a second celebratory-styled message the day after - it was a project he was deeply involved in as the do-it-all executive for Elon. This has led to speculation that his departure was planned, and potentially tied to compensation vesting with the launch of the Robotaxi Network, allowing him to leave on a high note after seeing the kick-off of one of Tesla’s most critical projects. This follows other recent departures of Tesla’s executive team, many of whom have gone to full-time retirement following years of hard work.
The Bigger Picture: What Is Tesla, really?
While both theories are plausible, the truth may be that Afshar’s departure is the symptom of a much larger challenge. Tesla is balancing two very different corporate identities.
On one hand, it's a manufacturing and sales powerhouse, responsible for the world’s best-selling electric vehicles, a business facing intense competition and brand perception challenges that even Elon has acknowledged.
On the other hand, Tesla is the only company shipping real-world AI for consumers, and betting its future on robotics and AI with massive investments in capacity for both future businesses.
The recent executive churn suggests that this balancing act is creating some strain, especially for Tesla’s senior executives. The departure of Milan Kovac signaled pressure on the future side of the business, where progress has been slow but consistent. Now, the exit of Afshar, who ran the “legacy” automotive side of the business, shows there’s pressure there, as the automotive business navigates a period of flattening growth and intense global competition.
So, we ask again - What is Tesla, really? Is it an AI and Robotics company? Kind of, but not really. Is it an EV company? Once again, kind of.
In our eyes, it is no longer just an EV company, but it’s at a critical point where it is transitioning to an AI and robotics company.
Tesla’s messaging to the outside world is similarly conflicted. On the one hand, the launch of the refreshed Model Y, a massive boost for the business, went seemingly unnoticed by Elon, who only posted a single update on the Model Y after its launch. On the other hand, we’ve seen consistent and non-stop posts about Robotaxi, which is likely years away from generating a significant portion of Tesla’s profits.
A Company in Transition
Ultimately, Omead Afshar’s departure is more than a single personnel change; it’s a reflection of Tesla navigating a crucial and challenging transition. The evidence of an abrupt halt, with internal sources reporting his account has been removed from internal company directories, suggests that there’s more to this than meets the eye.
Whether he was fired for declining sales or chose to leave after the successful launch of the Robotaxi Network, the outcome is the same. A key leader, tasked with managing the core business of the present, is gone at the very moment when the company is changing its path towards AI and robotics.
Being both a car company in a tough market and an AI company on the verge of a breakthrough is a monumental challenge, and the path forward is likely to see even more changes.
![First Recorded Tesla Robotaxi Intervention: UPS Truck Encounter [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2025/robotaxi_model_y.jpg/3036d8b53214c2d071c978c42911e451/robotaxi_model_y.jpg)
![First Look at Tesla's Robotaxi App and Its Features [PHOTOS]](https://www.notateslaapp.com/img/containers/article_images/tesla-app/robotaxi-app/robotaxi-app-tips.webp/e643a61975bf712d18dc9aa9a48fdb01/robotaxi-app-tips.jpg)
![Tesla’s New Camera Cleaning Feature and the Future of Cleaning Robotaxis [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2024/windshield-rain-droplets.jpg/8335f3020509dab3cdb56c1a91d054a9/windshield-rain-droplets.jpg)
![Tesla Launches Robotaxi: Features, Robotaxi App, Command Center and First Impressions [VIDEO]](https://www.notateslaapp.com/img/containers/article_images/2025/robotaxi_rear_screen.jpg/bf5ea088bdebda8ca7e0aa1503b69f4e/robotaxi_rear_screen.jpg)
_300w.png)
