Anyone else concerned about fog without radar?

Crissa

Well-known member
First Name
Crissa
Joined
Jul 8, 2020
Messages
5,932
Reaction score
7,798
Location
Santa Cruz
Vehicles
2014 Zero S, 2013 Mazda 3
Country flag
I see brake lights in the video before the Autopilot alert. You can see them through and around the small car in front.

Even if I didn't see lights in the video, there is no evidence in the video of how the AI decided to alert. Why? Because the video only shows us a forward view from the car, and lets us hear the audio alert. We're not, in that video, privy to any of the decision prcess of the AI. It doesn't give a different chime for visual or radar alerts.

Yes, the radar Tesla was using could see through cars in front of it. This is because radar bounces around; it's like a flashlight - you're not the only one who can see the beam, and it's not only things directly in the beam that's lit up. Things get lit up bey reflections and refractions, too. Worse, with radar, most objects are semi-transparent to the beam, so it's like shining a flashlight through a room filled with different glass boxes. Refections and refractions go everywhere, and the observer is left trying to figure out what is in the beam not just by the angular position and intensity, but the timing of when the waves return to the sensor.

It's a mess. Which is why Tesla has ceased using it for their AI.

-Crissa
Advertisement

 
Last edited:

FullyGrounded

Well-known member
Joined
Nov 18, 2020
Messages
324
Reaction score
327
Location
blah
Vehicles
blah
Country flag
One thing. Cameras don't necessarily outperform people, it's the computer behind them. that outperforms the human brain (computations per second, etc). If a human can at all drive in foggy conditions, cameras will do it much more efficiently and safely, as they can take the input of an approaching vehicle and immediately react 1 billion times. You, notice, decide how to react, then react very... much... slower..., on a good day. Have a nice day.
 

rr6013

Well-known member
First Name
Rex
Joined
Apr 22, 2020
Messages
676
Reaction score
603
Location
Piedras Gordas Panama
Website
shorttakes.substack.com
Vehicles
1997 Tahoe 2 door 4x4
Occupation
Retired software developer and heavy commercial design builder
Country flag
A dream I'm physically working on with the evtols in our workshop. The rail setup will also be a part of the eco-park we're building. Good ideas have to start somewhere.

I agree, that creating a new market sometimes requires substantially more effort than changing an existing one.

Tesla was always beholden to the idea of EV cars because of the need of currency to fulfill that idea. They did it because they understood what makes money to persue their overarching goal. But at somepoint its better to leave the old constraints behind and leapfrog horsepower driven car-riages. :giggle:
eVTOL has its place, purpose and applications. Time is currency. eVTOL hacks those problem domains.

Pray FAA doesn’t destroy eVTOL as it did to Gen’l Aviation. eVTOL‘s worst case is to avoid the niche cult scenario.
 

Donald Trump

Member
First Name
Donald
Joined
Dec 9, 2019
Messages
6
Reaction score
3
Location
Tempe, Az
Vehicles
Ford f250
Country flag

tidmutt

Well-known member
First Name
Daniel
Joined
Feb 25, 2020
Messages
234
Reaction score
322
Location
Somewhere hot and humid
Vehicles
Golf R, Tesla Model 3
Occupation
Software Architect
Country flag
A dream I'm physically working on with the evtols in our workshop. The rail setup will also be a part of the eco-park we're building. Good ideas have to start somewhere.

I agree, that creating a new market sometimes requires substantially more effort than changing an existing one.

Tesla was always beholden to the idea of EV cars because of the need of currency to fulfill that idea. They did it because they understood what makes money to persue their overarching goal. But at somepoint its better to leave the old constraints behind and leapfrog horsepower driven car-riages. :giggle:
A dream I'm physically working on with the evtols in our workshop. The rail setup will also be a part of the eco-park we're building. Good ideas have to start somewhere.

I agree, that creating a new market sometimes requires substantially more effort than changing an existing one.

Tesla was always beholden to the idea of EV cars because of the need of currency to fulfill that idea. They did it because they understood what makes money to persue their overarching goal. But at somepoint its better to leave the old constraints behind and leapfrog horsepower driven car-riages. :giggle:
What I think is fascinating is Tesla’s evolution of the horsepower driven car-riages is pushing related tech. Would we have powerwall? Solar roofs? Megapacks? Virtual power stations?

I believe millennials and gen z are less interested in car ownership. If that trend continues we may see a shift in personal transportation… if someone produces level 5 autonomy the number of cars on the road will drop significantly. An outcome you will cheer on, yes?

So Tesla’s investment in cars is really driving a lot of other things. See what I did there? :)
 

ajdelange

Well-known member
First Name
A. J.
Joined
Dec 8, 2019
Messages
2,950
Reaction score
3,145
Location
Virginia/Quebec
Vehicles
Tesla X LR+, Lexus SUV, Toyota SR5, Toyota Landcruiser
Occupation
EE (Retired)
Country flag
Identifying objects is a small part of what the forward facing cameras are tasked with. After identifying moving vehicles they use their superior angular resolution to estimate velocity, trajectory and range (by processing portions of the image through time (multiple frames).
Yes they can do that in the plane perpendicular to camera's axis and that is useful information. But they cannot do it in range or more accurately, they can't do it very well. AzDOP and ElDOP (DOP - DIlution of Precision) are very good relative to radar. r(DOP) is very poor because range is orthogonal to the things you can measure well.



Actually, a telephoto lens naturally has higher angular resolution than a wide angle lens because it has more pixels for each degree of vision in both the X and Y directions. This makes the estimation of range and velocity more accurate because it has more pixels on the areas of interest.
Your misunderstanding is based on your lack of familiarity with Geometric Dilution of Precision (GDOP).



Angular accuracy isn't worth much for measuring range if the opposite is orthogonal to the adjacent (range). The following picture shows the rDOP as a function of off axis distance for the camera and range to the target. The numbers represent the logarithm of meters of range error per radian of angular measurement error.

rDOP.jpg



As a life-long photographer I can tell you there is not really any difference between a wide angle lens and a telephoto lens except for the number of pixels (or amount of film) used to record each degree of view.
And as a life long (started with a Kodak Brownie)I can tell you that there are dramatic differences in things like distortions, depth of field aperture size, diffraction limits etc. I would expect a life time photographer to be aware of these. But I would not expect him to be familiar with the concept of GDOP.

This of course assumes both lenses, the telephoto and the wide angle, are corrected to be perfectly rectinlinear (which is never the case exactly but close enough for our purposes).


Your misunderstanding of the differences between wide angle and tele lenses...
∂hi = -(ho*f/S^2)∂S
∂hi/hi = -(ho/hi)*(f/S)*(∂S/S) = -(∂S/S)
???
What you don't understand is that the ability to measure angle precisely is only half the story. The variance of the range estimate is found by multiplying the angle measurement variance by the GDOP. This has to be taken into account.



It's true that some radar have very high angular resolution. And the highest resolution radars are monstrosities (in physical size).
Nope. The apertures just need to be many wavelenghs. To acheive that one must go to high frequency.



But automotive radar are compact as far as radar goes and are well known to have low resolution (even though that resolution is being gradually improved with newer frequencies and designs).
Tesla was considering a mm wave radar. Don't know anything about it but it doubtless had better resolution than and X-band radar would have. But in any case a radar, being an active device, has great DOP in the direction of propagation. It's the same principle as with the cameras. They have good DOP in the direction perpendicular to the normal to the target and thus don't measure well along the normal - its orthogonal. The radar is just the opposite. It takes superbly accurate measurements along the normal but isn't so good in the orthogonal directions.






Yes, high resolution radar is a thing, it just hasn't made it's way to a compact device that would be suitable for a sensor in a car. They are improving but a camera with a telephoto lens absolutely blows away any automotive radar out there when it comes to angular resolution.
Yep. Too bad that's worthless (or not very helpful) for range and range rate.


If it is telephoto it has narrow field of view. It is poor at judging range and range rate and even poorer in the
This is absolutely incorrect. See above for the reason why.
It's absolutely true. See the above for the reasons why. If you can interpret the plot you will be able to see that if you want to use cameras without radar you can do so by using the hi res camera to identify points of interest on the target or perhaps just center of mass of the target and then use the more widely spaced cameras, which have better rDOP. to meausre the distance. It doesn't matter that their angular resolution is worse because their DOP is better. Plus you have 2 of them. That decreases the DOP by another factor of sqrt(2).


As far as vision in very low light, digital cameras have a huge advantage over human vision in that the gain of the sensor can be turned way up.
I wonder if you have ever done this. If not, try it sometime.


This is the equivalent to using a faster film (except digital cameras are far more versatile in this regard).
I wonder if you have ever "pushed" film.

Yes, you lose some resolution but the cameras have far more resolution than is required to simply drive safely. So, the cameras end up being able to see in much lower light than a human with fully dark adapted eyes can see anything, let alone drive a car.
You just have to get past this notion that resolution gets you range. It does help of course but it is geometry that you must satisfy. As to the sensitivy of the human eye: it can detect single photons!. You can demonstrate this to yourself. And again you ignore geometry.


However, I'll add that much of the way the system responds is not as mechanistic as you appear to believe. Through training with the neural net the system becomes capable of reacting properly to all sorts of situations that it doesn't fully understand in a mechanistic manner. Much like a human.
I haven't said anything about the mechanics of how the state vectors are estimated. What I tried to get across is that given the characteristics of the sensors and thier locations and the number of them you will get a state vector covariance matrix that depends on the noise (error) characteristics of the sensors and their geometry (geometry has broader meaning than just x,y and z but that's included).



I do know a team that knows more about radar, how it works in various situations and what it's strengths and weaknesses are than anyone participating in this discussion.
Suggest you talk to some of these guys.
 
Last edited:

JBee

Well-known member
First Name
JB
Joined
Nov 22, 2019
Messages
434
Reaction score
435
Location
6000
Vehicles
Cybertruck
Country flag
What I think is fascinating is Tesla’s evolution of the horsepower driven car-riages is pushing related tech. Would we have powerwall? Solar roofs? Megapacks? Virtual power stations?

I believe millennials and gen z are less interested in car ownership. If that trend continues we may see a shift in personal transportation… if someone produces level 5 autonomy the number of cars on the road will drop significantly. An outcome you will cheer on, yes?

So Tesla’s investment in cars is really driving a lot of other things. See what I did there? :)
Tesla wasn't by far the first to do powerwalls, solar roof, megapacks or VPS.
But I agree they are pushing their adoption and giving customers options.
I'm off grid but don't use them because of a) their cost b) they are locked up systems and lack of functionality 3) availability.

I'm not saying the pathway Tesla took via cars is wrong per se, just that there are different options, of which some will most likely result in the demise of the car as we know it, and whatever "freedoms" we enjoy whilst using them now.

FSD L5 will definitely be one of those things, and I've mentioned that before in another thread, that FSD will get drivers out of their driving seat, and they will have to take a back seat. 😋 (see what I did there?)

With that, transport will be less of a ego trip, and result in a far more pragmatic and less emotional transport system. The implications of having a) dispatchable driverless EVs that can also self charge and operate as couriers 2) sharing those cars between users to maximize time of use is a unfathomably large increase in the efficiency of vehicle use. Meaning less vehicles doing lots more, with less and less private ownership, because that will actually become less convenient and more expensive. But that is also true for wide spread use of overhead monorail. Plus some.
 

rr6013

Well-known member
First Name
Rex
Joined
Apr 22, 2020
Messages
676
Reaction score
603
Location
Piedras Gordas Panama
Website
shorttakes.substack.com
Vehicles
1997 Tahoe 2 door 4x4
Occupation
Retired software developer and heavy commercial design builder
Country flag
Computers do not deny data, when not enough input to drive safely they wont. Would T FSD vision drive into the sandstorm? Does not help you when the 20 ton semi behind you keeps going.

Will the powers in charge in 2035 allow non computer assisted driving? I will tell you in 2045 it will not be allowed on Mars.


https://www.theguardian.com/us-news/2021/jul/26/killed-in-20-car-pileup-in-utah-sandstorm
These unpredictable Wasatch front-range microbursts are a mountain valley air-exchange phenomenon that also occurs out on the Great Salt Lake as Toele Twisters. Salt Lake International Airport shutsdown. Out of “clear blue skies“ they burst downward, invisible, hit and spread like your fingers spread, palm down, on a tabletop then march exactly like Catabatic winds fullforce for miles. It will blast paint finish off a car. Sailboats either knockdown or must run dead downwind(DDW) for miles until wind pressure relieves enough to pull sails down. These are 70+ kts typical exploding mast mounted weathervane windspeed cups upon impact. Tornadoes don’t strike with the impact these microbursts do. I’ve been in three different scenarios. Microburst == horror; that’s if you live to tell about it.

Radar would have been no assistance. Lidar equally useless. TeslaVISION blinded. Heresay, a blinded Autopilot w/o FSD shutsdown the Tesla along side last known roadway held in memory, IDK that is true, in fact. Def. if it hasn’t struck ground yet to pickup dirt FSD will drive right into a windswept highway. The ONLY advance warning is commercial pilots aloft reporting windshear. NOAA will occasionally cross broadcast these reported windshear as warnings.

Total chaos – fatal calamity with ~80,000 lbs. tractor-trailers of rolling mass that’s further pushed by 80mph wind all over the road. Neither 20 drivers nor passengers stood any chance of avoiding an initial blast. Follow-on traffic is unavoidable. UHP and DOT operate high wind warning signs at the point of the mountain if it was windy. That’s only chance for Southbound traffic since this occurred in Provo near Utah Lake. Northbound traffic does not see wind warnings until North of where this happened.
 

rr6013

Well-known member
First Name
Rex
Joined
Apr 22, 2020
Messages
676
Reaction score
603
Location
Piedras Gordas Panama
Website
shorttakes.substack.com
Vehicles
1997 Tahoe 2 door 4x4
Occupation
Retired software developer and heavy commercial design builder
Country flag
<Snip>

I'm not saying the pathway Tesla took via cars is wrong per se, just that there are different options, of which some will most likely result in the demise of the car as we know it, and whatever "freedoms" we enjoy whilst using them now.

FSD L5 will definitely be one of those things, and I've mentioned that before in another thread, that FSD will get drivers out of their driving seat, and they will have to take a back seat. 😋 (see what I did there?)

With that, transport will be less of a ego trip, and result in a far more pragmatic and less emotional transport system.

<Snip>
tl:dr
Elon Musk disrupted the last Industrial Revolution(ICE) by use of solar power. A solar abstraction layer provided Tesla electrical power that enabled de-coupling from petroleum as an embedded power dependency and it afforded individual control over self-production at will.

Tailpipes account for ~25% total CO2 emissions. Tailpipes was Elon’s second choice to loft a startup VC company to disrupt an economic sector. Elon’s car roadmap was insane hubris the likes of established entrenched automakers could not take seriously. Each transmogrification of Tesla Motors to Tesla then subsidiary solar embracing energy( as in battery storage) now grid utility array is creating another abstraction layer that de-couples the utility generated power detrimental reliance that society has withstood enabling a mix of Renewable Energies(RE) co-production, grid tie and software defined utilities that can include individual residential solar aggregated to earn hard dollar offsets if they choose.

Cybertruck is only the latest disruption to provide a vehicle that is more easily applied to a CO2-free RE powered BEV culture, battery-supported utility infrastructure and solution to global warming that nudges into the commercial sector.

FSD is in response to this problem that Tesla et. al. face - paying customers! Roughly 70% of world population lives on less than $35USD/da.
7389B93E-5827-4AEF-A897-808B07A4E67F.jpeg


Tesla wants to invent FSD to provide autonomous vehicles that enable Robotaxis(driverless) transportation. Read affordable! If Elon can establish that abstraction layer Tesla owns the ride-hail, autonomous vehicle(Bus) and last-mile cargo problem where Fedex, DHL and AMAZON thrive. Side-effect unintended consequences Tesla owners can make money - if they want, when and where.

Synergies are the Motherf of Competition and innovation is the stepping stone that enables a company to capture geometric progressions. Seque SpaceX Starship Point-to-Point(P2P) global freight. SpaceX reuse, SS and P2P dovetail into Tesla last-mile delivery layer in-process of emerging next decade.

Elon is not interested in putting a BEV in every garage. 70% of world cannot afford a cheap Tesla but they can still use one!

As far as ego trips the population of the world has bigger problems! Just Today Headlines: 26JUL’21

Counting DownResearcher Stands by Prediction of 2040 Civilization Collapse9:51 AMRead More

https://www.nytimes.com/live/2021/0...ods-again-england-is-battered-by-wild-weather

https://www.nytimes.com/live/2021/0...r-a-sandstorm-in-utah-causes-a-highway-pileup

https://www.nytimes.com/live/2021/07/26/us/climate-change/flooding-waters-southwest

https://www.nytimes.com/live/2021/0...d-of-sardinia-in-a-disaster-without-precedent

https://www.nytimes.com/article/hea...pe=LegacyCollection&variant=show&is_new=false

https://www.nytimes.com/interactive...pe=LegacyCollection&variant=show&is_new=false

https://www.nytimes.com/interactive...pe=LegacyCollection&variant=show&is_new=false
 

tidmutt

Well-known member
First Name
Daniel
Joined
Feb 25, 2020
Messages
234
Reaction score
322
Location
Somewhere hot and humid
Vehicles
Golf R, Tesla Model 3
Occupation
Software Architect
Country flag
Tesla wasn't by far the first to do powerwalls, solar roof, megapacks or VPS.
But I agree they are pushing their adoption and giving customers options.
I'm off grid but don't use them because of a) their cost b) they are locked up systems and lack of functionality 3) availability.

I'm not saying the pathway Tesla took via cars is wrong per se, just that there are different options, of which some will most likely result in the demise of the car as we know it, and whatever "freedoms" we enjoy whilst using them now.

FSD L5 will definitely be one of those things, and I've mentioned that before in another thread, that FSD will get drivers out of their driving seat, and they will have to take a back seat. 😋 (see what I did there?)

With that, transport will be less of a ego trip, and result in a far more pragmatic and less emotional transport system. The implications of having a) dispatchable driverless EVs that can also self charge and operate as couriers 2) sharing those cars between users to maximize time of use is a unfathomably large increase in the efficiency of vehicle use. Meaning less vehicles doing lots more, with less and less private ownership, because that will actually become less convenient and more expensive. But that is also true for wide spread use of overhead monorail. Plus some.
Oh I know, but Tesla brings an awareness and an apple-esq coolness to those products that helps drive adoption. Not to mention the potential synergies of producing a bunch of mobile battery packs, power walls, solar roofs and utility scale batteries combined with one of Tesla’s most underrated capabilities, a world class software organization. All of that gives them scale as well. They are uniquely position to make huge changes that few companies could accomplish. That’s not even mentioning the Musk factor.

And yes, FSD has the potential to completely change transportation. That was my point. 👍🏻
 

ajdelange

Well-known member
First Name
A. J.
Joined
Dec 8, 2019
Messages
2,950
Reaction score
3,145
Location
Virginia/Quebec
Vehicles
Tesla X LR+, Lexus SUV, Toyota SR5, Toyota Landcruiser
Occupation
EE (Retired)
Country flag
With that, transport will be less of a ego trip, and result in a far more pragmatic and less emotional transport system.
But who wants a pragmatic and emotion free transportation system? One of the advantages of old age is that one remembers the heady days of youth spent in the 50's and 60's and what the automobile represented to us and our parents. The Sunday Drive was an American tradition available to a large segment of the population. We didn't worry about carbon footprint, or that it wasn't available to certain "communities" or groups with particular mental aberrations. We had fun and the country prospered. Today the pragmatisms imposed by huge population and the strictures imposed by the social problems this has caused have removed many freedoms and much enjoyment from life.

And tech has taken a lot away too. I remember days when you could fix your car or mod it and many enjoyed doing that. No Canbus reader or logic analyzer was needed. Just a set of inch sockets and spanners.

The advantages of youth are that you never knew these joys and thus don't miss them.
 

HaulingAss

Well-known member
First Name
Mike
Joined
Oct 3, 2020
Messages
671
Reaction score
1,133
Location
Washington State
Vehicles
2010 Ford F-150, 2018 Tesla Model 3 Performance
Country flag
Suggest you talk to some of these guys.
It's pretty hard to talk to the Tesla Vision/FSD team as they are quite busy making FSD drive without human intervention in a wide variety of conditions and environments. Currently, no other FSD system is at a state of development that can handle the wide variety of environments and conditions that Tesla's beta FSD already handles with limited to no interventions.

So I suggest you look at what they are doing and saying publicly. Because you can learn a lot from that.

A few comments on your other comments I deleted:

Your image did not show up so I have no idea what you are going on about. But that's OK.

You avoided addressing the main point of my post which is that a wide angle image that is cropped to a telephoto perspective is identical to the telephoto image (except with fewer pixels). Thus your claim that a telephoto image has inferior depth information compared to a wide angle image is absolutely false. Instead, you tried to muddy the discussion by introducing meaningless differences like lens aberrations, etc. Not cool.

The Tesla Vision team has disseminated a lot of good info on how they extract depth information (and thus speed and trajectory information) from 2D images. I suggest you read and absorb it. Because the depth information they are able to extract witjh cameras alone is superior to any estimation that a human driver can make. They have published videos with the point of view moving through 3D scenes that have been accurately reconstructed from 2D images. So your claims that cameras cannot provide accurate enough 3D information for FSD is directly contradicted by the evidence. It is many times more accurate than the FSD computer requires to drive safely through the scene. Millimeter accuracy is not needed to drive safely.

You seem to have an unusual propensity to delve into extreme detail of mostly irrelevant and arcane subject matter in an apparent attempt to appear knowledgeable. I don't care to take the time to address and dissect such extraneous attempts to evade the actual points under discussion. In most instances it shows you are either not grasping the points under discussion or are simply trying to avoid addressing the actual points. In some cases your response is not even applicable to the specific points under discussion. At least not to any material degree. Not cool. This leads me to believe you are not carrying on this discussion in good faith, with the goal to bring out the truth, but rather to be evasive and preserve an air of superior knowledge. It's not productive.
 
Advertisement

 
Advertisement
Top