Tesla registers new high-res radar. Could Tesla be changing its position on radar and LiDAR?

A Tesla vehicle equipped with LiDAR sensors

@ManuelRToronto/Twitter

Tesla registered a new high resolution radar unit with the U.S. Federal Communications Commission (FCC). Tesla's intended use for these radar units is unknown, but it appears they are intended for imaging, similar to how LiDAR uses lasers to map surroundings.

While Tesla's FSD software has used radar in the past, Elon Musk has a rather unfavorable stance on LiDAR. For the purposes of autonomous driving, Musk sees LiDARs as a "fool's errand." Yet, people have been spotting Tesla prototypes with LiDAR sensors since last year.

Tesla files a patent for a high-res radar sensor

The latest instance of Tesla using LiDAR comes from Twitter user @ManuelRToronto who spotted a LiDAR-mounted Tesla in downtown Toronto, only a few weeks after the release of FSD Beta in Canada.

He took a video of the LiDAR-mounted Model Y with manufacturer license plates from California.

@elonmusk Spotted in Toronto. A @Tesla Model Y with #LiDAR and CA Manufacturing (MFG) Plates. It cut me off!, I guess it doesn’t have FSD or it may be camera shy, what’s the deal ? @NotATeslaApp pic.twitter.com/FYOdjFA1gq

— Manuel Rodriguez (@ManuelRToronto) May 16, 2022

There has been no official announcement from Tesla about these LiDAR-mounted vehicles, but it is safe to assume that Tesla will not use LiDAR on any production vehicles.

Tesla is likely using LiDAR to help train their machine learning algorithms, using it as the ground truth when checking for accuracy. Unlike cameras, LiDAR captures extremely accurate 3D depth measurements.

LiDAR could be used to train these algorithms to accurately interpret depth by relying on precise, non-interpretive LiDAR sensors.

Cameras are limited to 2D data combined with computer vision algorithms to interpret 3D depth. The downside to this approach is that it requires a computational process versus having precise 3D depth measurement from a LiDAR sensor.

However, LiDAR sensors are expensive; the benefit of relying solely on cameras is that it makes Teslas much more affordable.

LiDAR can't be the only sensor used in a vehicle since it can only build a wireframe 3D environment. Without cameras it wouldn't be able to read traffic signs, traffic lights or anything that doesn't have depth.

Vehicles with LiDAR also rely on camera data and fuse the two outputs of the two sensors together to build a virtual representation of the real world.

Musk believes that self-driving cars should navigate the world in the same manner as human drivers. Since humans use their eyes and brain to navigate three-dimensional space, cars with cameras and enough computational power should be able to achieve the same thing.

"Humans drive with eyes and biological neural nets, so it makes sense that cameras and silicon neural nets are the only way to achieve a generalized solution to self-driving, " says Elon Musk.

While other self-driving initiatives like Google's Waymo have taken a LiDAR approach, Tesla is outpacing the competition using vision-only, machine learning and the network effect of over 100,000 vehicles in the FSD Beta program.

Tesla's vision-only approach has become smart enough that adding radar data gives the system more information than it needs and disorients the FSD software.

LiDAR and radar may be helpful in training the FSD software, but Tesla wants to avoid using multiple sensors with potentially conflicting perceptions that would overwhelm the system.

With Tesla's recent patent of a high resolution radar, and the recent reported use of LiDAR, it is possible that Tesla's Robotaxi will employ radar and/or LiDAR in order to reach full automation.

Levels of driving automation

Synopsys

Tesla's FSD software could eventually be segmented into consumer and commercial self-driving vehicles with consumer vehicles reaching conditional autonomy (L2/L3) using vision-only and commercial vehicles reaching full autonomy (L4/L5) with the help of radar or potentially even LiDAR sensors.

Commercial robotaxis could even be multi-sensor (cameras, radar, LiDAR), costing much more, while consumer self-driving vehicles would be vision only and more affordable.

Only very high resolution radar is relevant

— Elon Musk (@elonmusk) February 5, 2022

Follow

Follow

Follow

Tesla Update 2025.20 Tear Down Reveals Grok Personalities and Icons

@greentheonly on X

While most automakers are adding basic and un-integrated AI assistants to their vehicles, Tesla appears to be working hand-in-hand with xAI to build out an entire cast of characters for in-vehicle Grok. In the latest dive into Tesla’s firmware, Tesla hacker @greentheonly uncovered a few new details about the upcoming Grok feature.

This discovery, part of a larger batch of changes found in Tesla update 2025.20, also offers a hint at the hardware required for the Grok.

A Dozen Groks

While we knew from previous firmware teardowns that Tesla was adding various Grok personalities to the vehicle UI, this update introduces a new one called Language Tutor, which may allow users to learn and practice a new language. 

These are the different personas that will be included in Grok:

• Argumentative

• Assistant

• Conspiracy

• Doctor

• Kids’ Stories

• Kids’ Trivia Games

• Meditation

• Motivation

• Romantic

• Sexy

• Storyteller

• Therapist

• Language Tutor

• and the Grok Classic - Unhinged Mode

Release Date

Icons for these personalities have been added to the firmware for the first time, leading us to think Tesla is getting close to releasing the feature. However, even after the feature is developed and included in vehicle software, Tesla may only enable it selectively — such as for select employees for testing.

Grok is expected to be one of the largest vehicle features added via a software update, so it’ll be a big deal when it’s finally released. While we know more or less what to expect from Grok, what we don’t know is about vehicle requirements or whether it’ll require a subscription beyond Premium Connectivity.

Grok Requirements

While subscriptions required are anyone’s guess, vehicle requirements may be a little clearer now, thanks to Green’s discovery that Grok is only being added to AMD-based vehicle software builds.

Unfortunately, this likely means that older, Intel-based vehicles will not receive Grok support, at least for the time being. When Tesla introduced a voice assistant in China, they also started off with AMD-only support but later added Intel support, so it’s possible that the same could happen with Grok.

Energy Saving

Green also found a new undocumented navigation feature in 2025.20.3. This one focuses on leveraging Tesla’s vast amounts of data in an interesting way and offers drivers proactive advice to save energy on a well-traveled route. 

In the Energy App, your vehicle will display, “This route is typically driven at X mph. Slow down by Y mph to save Z% for the rest of this trip.’ 

As you can see in the photo below, Tesla recognizes that vehicles typically drive at 66 mph on the route being driven and offers the driver the option to go five mph slower to save 1% of range. While this example doesn’t provide much incentive to slow down, it could be useful for someone with a low state of charge or if the savings are more significant.

The new line in the Energy App

Not a Tesla App

In the future, Tesla could even use this, alongside the road surface data they’re gathering, to help plan routes for Robotaxi and Unsupervised FSD.

Follow

Follow

Follow

NHTSA to Streamline Approvals for Control-Free Vehicles Like Tesla’s Cybercab

Not a Tesla App

In a letter to industry, the National Highway Traffic Safety Administration (NHTSA) has announced that it is overhauling its approvals process for vehicles designed without human controls.

The change addresses a regulatory bottleneck that has slowed down American companies like Tesla from deploying purpose-built Robotaxis, rather than relying on using traditional vehicles with steering wheels and pedals. The policy shift is outlined in a letter posted to the NHTSA’s website, which you can find here.

Reducing Approvals From Years to Months

Under the existing rules today, any vehicle that is built without a steering wheel or brake pedals must receive a special exemption from federal safety standards.

Obtaining exemptions for a particular vehicle was a time-consuming process for both the companies requesting exemptions and the NHTSA. The process was often a black box—nobody knew when an exemption might be granted, and approvals could take years.

The NHTSA, under the new administration’s guidelines for autonomous vehicle development, is now committed to streamlining this process. The agency will be implementing a new, faster approach immediately for receiving exemptions for autonomous vehicles without standard controls. The NHTSA expects decisions on exemption requests to be determined within months rather than years. 

Accelerating the Cybercab

This change has massive implications for Tesla, which is banking on the production of the simplified and easy-to-maintain purpose-built Cybercab. The Cybercab is developed from the ground up as an autonomous Robotaxi and will be one of the key beneficiaries of this move by the NHTSA.

Knowing that a final design won't be caught in a multi-year regulatory limbo provides a level of certainty that has been missing. It allows Tesla to confidently plan the manufacturing, development, and deployment processes without worrying whether the project will get stuck in regulatory approvals.

According to the letter, the agency will publish its improved instructions for the streamlined process "shortly." With Tesla already having begun Cybercab pre-production and the goals for its deployment as soon as late 2026, there’s still a lot to be done to make autonomy a part of Tesla’s new sustainable abundance mission statement.

Follow

Follow

Follow