Radar documents are up.
OET List Exhibits Report
OET List Exhibits Report
You can install our site as a web app on your iOS device by utilizing the Add to Home Screen feature in Safari. Please see this thread for more details on this.
Note: This feature may not be available in some browsers.
Radar documents are up.
OET List Exhibits Report
That is old text from when they submitted the unit for testing. The important part is the radar specific specs, ID, and powerThanks for posting. So maybe not necessarily for HW4? Or perhaps Tesla reused the HW3 user manual? The "User manual" uploaded along with those documents contains phrases I wouldn't expect to see for HW4.
"Your Model X includes the following Autopilot components that actively monitor the surrounding roadway:
- Ultrasonic sensors are located in the front and rear bumpers
- A camera is mounted in each door pillar
- Three cameras are mounted to the windshield above the rear view mirror"
This is going to date me . . . but that is reminiscent of Token Ring topology. Haven't seen those in quite a while.
On the topic of whether or not HW4 and HW3 can integrate, heres my perspective. I've been coding for 40 years, C++ for 30+ years.
If Tesla have any idea how to do software engineering (and clearly they do), then there is likely a very definite modular break between the neural net code that does object recognition and image-based distance approximation (basically working out what is where), and the NN for deciding what actions to take, which lane to be in, what speed to set, where to face the vehicle etc...
In other words, some code creates a 'world view' likely saying 'object X,Y and Z are at these positions, with this percentage of confidence', and then the decision making code decides how to handle the vehcile given this data.
The second set (decision and driving) can be totally independent of how the first set of data is determined. In fact we KNOW this is how tesla do it, because they used to be pure NN for object recognition and pure C++ for decisions. Now its a bit of NN in the decision code.
I assume HW3 will be able to say 'objects X,Y,Z at these positions, 90% confidence'. HW4 will say 'X,Y,Z with 98% confidence'. As far as the decision code is concerned, it doesn't even have to know if it has HW3 or 4 installed. They MUST work this way, because the number of cameras may decrease in real time due to hardware failure, or blindness/obfuscation of a camera by sunlight or dirt/dust.
So I dont think there is much concern that HW3 will not be able to use a lot of HW4 code. I dont see this as an issue at all. What IS an issue is whether or not the confidence level from HW3 sensors is sufficient to enable hands-free FSD. Thats the only worry, from an investor POV.
In general I think its worth thinking about HW4 and HW3 more as 'sensor suite 3' and 4, as thats likely the biggest real difference.
IANAL.
I assume HW3 will be able to say 'objects X,Y,Z at these positions, 90% confidence'. HW4 will say 'X,Y,Z with 98% confidence'.
Pretty sure that's a placement holder plastic piece for the M3SR+ fog light (i.e. only a yellow marker but no main LED bulb).There's a good video in the replies to that tweet. When you see more angles, it looks more like a reflector for a LED light than a camera:
They talked about it at the AI day in 2022. Ashook believes that some form of occupancy networks or NERFs(not exactly sure what he was implying) will be the foundational model of computer vision like LLMs are the foundational models of language.Does anyone think that they can stitch together a 360 view of the car environment in a common format for HW3 or HW4, that can use a common set of training data?
The alternative is different training data for HW3 and HW4 resolving to a common occupancy network?
My issue with 2 seperate sets of training data is there would also be 2 sets of training, 2 lots of testing, and once the platform diverged would be hard to merge.
Perhaps Dojo allows 2 sets of training to be easily accommodated?
One parallel is 286, 386, 486 and Pentium PC chips the hardware was increasingly capable, but the ability to run software on older machines was retained. It was not necessary to compile and test each program for each generation of chips.
I understand that separate training data and training for HW4 will eventually produce a better result. But initially if might be 5 steps backwards meaning that HW3 out performs HW4 for some time?
Seems to me that HW4 cameras could be downgraded to a HW3 pixel count as an interim solution until better HW4 data was available.
I understand the point on using simulation, but that also seems like something that might take time, and a lot of compute.
The hold up with HW4 and the Cybertruck could have been Dojo? If so, that implies 2 lots of training even if only Tesla staff are testing a HW4 specific version.
This might be legit:
I'm still skeptical of a camera in the headlights, but check out the repeater in the first photo. It appears to have a sideways facing camera as well.
I assume this is the HW4 cameras:
An article:
Tesla Model S/X Builds Spotted with New Autopilot Cameras, No Rear Emblems, Steering Wheels [PICS] - TeslaNorth.com
We’re not sure how The Kilowatts do it but they always seem to be in the right place at the right time, and now they have come across the latest Model S and Model X builds from Tesla’s Fremont Factory, that contains new upgrades. The most interesting discovery by The Kilowatts was new Autopilot...teslanorth.com
So I think we can assume that at least some HW4 Model S/X are in production right now.
Regarding upgrade path: HW4 form factor is different, but potentially adaptable with jumper hoses and harnesses. At least for non air cooled HW2/2.5 vehicles.Today's speculation is that the current cars will get updated cameras (higher res, different viewing angles, etc), but not any ADDITIONAL cameras...the latter will be for Semi and Cybertruck
All cars could, theoretically, get the radar and faster processor.
If true, this doesn't require any huge body changes for S/X/3/Y and means they could all get it pretty quick. It also aligns more with HW3 and HW4 being an evolution.
Today's speculation is that the current cars will get updated cameras (higher res, different viewing angles, etc), but not any ADDITIONAL cameras...the latter will be for Semi and Cybertruck
All cars could, theoretically, get the radar and faster processor.
If true, this doesn't require any huge body changes for S/X/3/Y and means they could all get it pretty quick. It also aligns more with HW3 and HW4 being an evolution.