FSD Beta 10.4 Improvements with images and video

Tesla is slowly rolling out FSD Beta 10.4 to existing beta testers. Tesla hopes to expand the beta to users who have a Safety Score of 98 or higher in the coming days. Beta 10.4 builds upon FSD Beta 10.3 in several key areas.

Tesla now displays speed bumps

@HisandHersTesla/Twitter

The first is the crucial and common maneuver known as an unprotected left turn, where your car may have a green light, but needs to wait for oncoming traffic to pass before taking a left turn. Not only does a maneuver like this leave your car vulnerable, but it can also be complicated to complete.

With 10.4, Tesla improved high speed object detection and now allows for faster acceleration across certain roads. These improvements appear to be helping in making more reliable unprotected left turns.

In James Locke's video below, he shows off an impressive unprotected left turn in this newest beta. Not only does the car wait for oncoming traffic to clear, but the car starts slowly accelerating before the vehicle clears it's path, so that the car is up to speed by the time vehicle passes. It's much more natural and human-like behavior.

@elonmusk #FSDBeta 10.4 handling left turns much better. Both the approach to the turn and the turn itself. Can see how it starts turning to pass behind the oncoming car before it passes. Much more human like. pic.twitter.com/0LusOKEgxF

— James Locke (@arctechinc) November 7, 2021

FSD Beta's visualizations are a big improvement over the visualizations in the public builds, partly due to object permanence.

The software is able to tell the difference between an object moving or disappearing versus it being hidden by another object. If there was a person in front of your car, but then a vehicle slowly drove by, between your car and that person, we'd likely conclude that the person is still there, just hidden behind the car.

That's what Tesla is doing now, not only with visualizations, but what the car sees as its surroundings. Once the car sees an object, it records it's time and position in the world in a semi-permanent state. Even when the car can't see the object any longer, it still knows it's there.

Sure, this could lead to some errors, but it often does in humans as well. In the example above, where the person was obscured by the car, it's possible the person got into another car or left the scene without us seeing because the car was blocking our view.

In this update, we're seeing more complete visualizations thanks to Tesla drastically improving the detection of VRUs (vulnerable road users) such as pedestrians, bicyclists and motorcycles by using a next generation auto labeler.

You can read the complete technical release notes for the FSD Beta 10.4.

New Visualizations

Visualizations also received a small update. The car was already detecting and slowing down for speed bumps, but speed bumps are now shown in the visualizations as well.

Crosswalks also received a minor visualization update. They used to be depicted as two white parallel lines, but they now appear as a filled in dark area on the screen. They're a little more obvious and there are less jagged lines, but they also don't exactly look like crosswalks either. If Tesla added the thick stripes crosswalks usually have, that could prove useful.

FSD Beta now displays clearer crosswalks

There are other smaller improvements in this beta such as improved emergency vehicle detection, improved VRU relevance by using the vehicle's intended path and more.

Improved Warnings

Tesla has greatly improved driver monitoring by not relying solely on steering wheel tension and instead using the interior camera. Tesla apparently started included the interior camera in Model 3s apparently for a robotaxi future, but it appears to have paid off for FSD instead. Relying on steering wheel tension was unreliable and an annoyance for drivers.

With the cabin camera Tesla can closely monitor where the driver is looking and constantly checking whether they're paying attention. An inattentive driver will receive an instant warning to pay attention if they're looking down, staring at their phone or looking to the side if Autopilot is activated.

FSD Beta warning

DCCWrules/Twitter

Early last month Tesla starting enforcing stricter rules when using FSD, where they will kick out beta testers if they're caught not paying attention several times.

In this beta, Tesla appears to have expanded these warnings to being on-screen as well, instead of relying on an email message. These warnings will be crucial to Tesla keeping the FSD Beta program and remaining accident free.

What's Not Included Yet

We know two big features are coming to FSD soon, but they're not yet included in this 10.4 update. The first is using a single stack for city and highway driving. Highway Autopilot is still completely separate and the same as the public build.

We're also anticipating the feature that will give the vehicle the ability to go into reverse. If the vehicle creeps forward for better visibility and decides it's unsafe to proceed, it'll back up to move out of the way of others.

Elon first anticipated this feature to come in FSD Beta 10.1, but we haven't seen it in FSD builds yet.

It's possible we may see both of these features added in the next major FSD release v11, which may come as the next FSD Beta. FSD Beta 10.4 also includes Sentry Mode Live Access for those with a Model 3, Model Y or the new Model S and X.

Follow

Follow

Follow

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

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.

Follow

Follow

Follow

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

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.

Follow

Follow

Follow