Tesla's FSD hardware 4.0 to use cameras with LED flicker mitigation

January 13, 2022

By Nuno Cristovao

At Tesla's AI Day event last summer, Elon answered some questions during the Q&A portion of the event that revealed Tesla's plans for FSD hardware.

Elon informally announced that Tesla is already researching the next major hardware revision for full self-driving.

Tesla's camera housing

Elon said that he expects the current hardware in today's vehicles to be capable of "super-human" driving, but Tesla will continue to update their cars to have the most powerful hardware available.

Elon guessed that Tesla may release FSD hardware 4.0 with the introduction of the Cybertruck. Since the Cybertruck won't be released until the end of this year at the earliest, we may even see new hardware before its arrival, although this is unlikely.

In another question related to new hardware, Elon also said that Tesla is looking into new cameras. He was clear that the current cameras aren't a hindrance, but if Tesla can do better, then they will.

Elon didn't go into details about whether the new cameras would be tied to the Cybertruck or hardware 4.0. He also didn't mention specifically whether the new cameras would be higher resolution, contain larger sensors, or possibly even be placed in different locations.

Tesla currently utilizes three separate front-facing cameras in the housing at the top of the windshield. The camera unit contains wide-angle, standard, and narrow view lenses with three separate CMOS sensors.

Each sensor has a resolution of 1280x960 or about 1.2 megapixels.

New Camera

According to Chris Zheng on Twitter, who has connections with some Tesla suppliers, Tesla is planning to use Sony's new IMX490 automotive sensor in their upcoming hardware 4.0 revision.

Wide-angle camera comparison

This new sensor offers many benefits over the current sensors that Tesla uses in their vehicles.

The new sensors support a much higher resolution of 2896x1876. That's 5.4 megapixels compared to the 1.2 megapixels that Tesla's current front-facing cameras support.

At more than four times the resolution of current sensors, these new sensors will allow Tesla to more accurately detect objects that are required for FSD.

Detecting road edges and lane markings that are further away are especially difficult. Due to the angle of the road and the current image resolution, Tesla often has to make assumptions based on just a few pixels.

The increased resolution will offer a more detailed image and should improve the accuracy in these situations.

The new wide-angle sensor may also allow Tesla to drop the number of cameras used in the front-facing module. Due to the higher resolution in these sensors, Tesla may be able to use this wide-angle sensor to interpret objects that previously required the use of the standard or telephoto lenses before. This may allow Tesla to reduce the number of cameras that are required in the front of the vehicle from three down to two or even a single lens.

The new camera sensor also supports HDR shooting at 10 bit and 40 FPS, offering better contrast and richer colors. It's not clear whether Tesla would take advantage of HDR as it would require more power to process, but it's something Tesla may consider depending on the compute power available.

LED flicker mitigation

More importantly, the new sensor will also support LED flicker mitigation. Camera sensors often have a hard time capturing the light emitted from LED lights in a constant fashion. Since LEDs are widely used in electronic signs and traffic lights this will be an important feature and should make it easier for Tesla to interpret such signs.

Tesla is working closely with Samsung to produce their next-generation chips that will be used in FSD hardware 4.0. Tesla will likely launch updated cameras at the same time they introduce a new FSD computer.

It makes sense for Tesla to introduce this new hardware in a new model first before retrofitting new camera modules into existing models.

Tesla’s Optimus Robot Learns to Walk Without Vision [VIDEO]

December 13, 2024

By Karan Singh

Optimus Falls - but catches itself!

Not a Tesla App

Tesla recently showed off a demo of Optimus, its humanoid robot, walking around in moderately challenging terrain—not on a flat surface but on dirt and slopes. These things can be difficult for a humanoid robot, especially during the training cycle.

Daily walks help clear your mind pic.twitter.com/dUsW58trS6
— Tesla Optimus (@Tesla_Optimus) December 9, 2024

A Look Behind the Curtain

Most interestingly, Milan Kovac, VP of Engineering for Optimus, clarified what it takes to get Optimus to this stage. Let’s break down what he said.

Optimus is Blind

Optimus is getting seriously good at walking now - it can keep its balance over uneven ground - even while walking blind. Tesla is currently using just the sensors, all powered by a neural net running on the embedded computer.

Essentially, Tesla is building Optimus from the ground up, relying on as much additional data as possible while it trains vision. This is similar to how they train FSD on vehicles, using LiDAR rigs to validate the vision system’s accuracy. While Optimus doesn’t have LiDAR, it relies on all those other sensors on board, many of which will likely become simplified as vision takes over as the primary sensor.

Today, Optimus is walking blind, but it’s able to react almost instantly to changes in the terrain underneath it, even if it falls or slips.

What’s Next?

Next up, Tesla AI will be adding vision to Optimus - helping complete the neural net. Remember, Optimus runs on the same overall AI stack as FSD - in fact, Optimus uses an FSD computer and an offshoot of the FSD stack for vision-based tasks.

Milan mentions they’re planning on adding vision to help the robot plan ahead and improve its walking gait. While the zombie shuffle is iconic and a little bit amusing, getting humanoid robots to walk like humans is actually difficult.

There’s plenty more, too - including better responsiveness to velocity and direction commands and learning to fall and stand back up. Falling while protecting yourself to minimize damage is something natural to humans - but not exactly natural to something like a robot. Training it to do so is essential in keeping the robot, the environment around it, and the people it is interacting with safe.

We’re excited to see what’s coming with Optimus next because it is already getting started in some fashion in Tesla’s factories.

Is Tesla Close to Licensing FSD? GM Quits Cruise, BMW Praises Tesla

December 13, 2024

By Karan Singh

Not a Tesla App

In a relatively surprising move, GM announced that it is realigning its autonomy strategy and prioritizing advanced driver assistance systems (ADAS) over fully autonomous vehicles.

GM is effectively closing Cruise (autonomous) and focusing on its Super Cruise (ADAS) feature. The engineering teams at Cruise will join the GM teams working on Super Cruise, effectively shuttering the fully autonomous vehicle business.

End of Cruise

GM cites that “an increasingly competitive robotaxi market” and “considerable time and resources” are required for scaling the business to a profitable level. Essentially - they’re unable to keep up with competitors at current funding and research levels, putting them further and further behind.

Cruise has been offering driverless rides in several cities, using HD mapping of cities alongside vehicles equipped with a dazzling array of over 40 sensors. That means that each cruise vehicle is essentially a massive investment and does not turn a profit while collecting data to work towards Autonomy.

Cruise has definitely been on the back burner for a while, and a quick glance at their website - since it's still up for now - shows the last time they officially released any sort of major news packet was back in 2019.

Competition is Killer

Their current direct competitor - Waymo, is funded by Google, which maintains a direct interest in ensuring they have a play in the AI and autonomy space.

Interestingly, this news comes just a month after Tesla’s We, Robot event, where they showed off the Cybercab and the Robotaxi network, as well as plans to begin deployment of the network and Unsupervised FSD sometime in 2025. Tesla is already in talks with some cities in California and Texas to launch Robotaxi in 2025.

GM Admits Tesla Has the Right Strategy

As part of the business call following the announcement, GM admitted that Tesla’s end-to-end and Vision-based approach towards autonomy is the right strategy. While they say Cruise started down that path, they’re putting aside their goals towards fully autonomous vehicles for now and focusing on introducing that tech in Super Cruise instead.

NEWS: GM just admitted that @Tesla’s end-to-end approach to autonomy is the right strategy.

“That’s where the industry is pivoting. Cruise had already started making headway down that path. We are moving to a foundation model and end-to-end approach going forward.” pic.twitter.com/ACs5SFKUc3
— Sawyer Merritt (@SawyerMerritt) December 10, 2024

With GM now focusing on Super Cruise, they’ll put aside autonomy and instead focus solely on ADAS features to relieve driver stress and improve safety. While those are positive goals that will benefit all road users, full autonomy is really the key to removing the massive impact that vehicle accidents have on society today.

In addition, Super Cruise is extremely limited, cannot brake for traffic controls, and doesn’t work in adverse conditions - even rain. It can only function when lane markings are clear, there are no construction zones, and there is a functional web connection.

The final key to the picture is that the vehicle has to be on an HD-mapped and compatible highway - essentially locking Super Cruise to wherever GM has time to spend mapping, rather than being functional anywhere in a general sense, like FSD or Autopilot.

Others Impressed - Licensing FSD

Interestingly, some other manufacturers have also weighed into the demise of Cruise. BMW, in a now-deleted post, said that a demo of Tesla’s FSD is “very impressive.” There’s a distinct chance that BMW and other manufacturers are looking to see what Tesla does next.

BMW chimes in on a now-deleted post. The Internet is forever, BMW!

Not a Tesla App

It seems that FSD has caught their eyes after We, Robot - and that the demonstrations of FSD V13.2 online seem to be the pivot point. At the 2024 Shareholder Meeting earlier in the year, Elon shared the fact that several manufacturers had reached out, looking to understand what was required to license FSD from Tesla.

There is a good chance 2025 will be the year we’ll see announcements of the adoption of FSD by legacy manufacturers - similar to how we saw the surprise announcements of the adoption of the NACS charging standard.