Donate to Remove ads

Got a credit card? use our Credit Card & Finance Calculators

Thanks to johnstevens77,Bhoddhisatva,scotia,Anonymous,Cornytiv34, for Donating to support the site

Musk endeavours

The Big Picture Place
BobbyD
Lemon Half
Posts: 7814
Joined: January 22nd, 2017, 2:29 pm
Has thanked: 665 times
Been thanked: 1289 times

Re: Musk endeavours

#461420

Postby BobbyD » November 27th, 2021, 3:59 pm

onthemove wrote:I mean, take for example that video I linked where the Tesla wanted to pull out in front of an approaching car.

The driver tried to explain it by saying the approaching road isn't straight, so the cars are coming from a little further left than normal.

To be honest, I'm doubtful that that was simply the reason in that case, but it's good to illustrate my point...


If I recall correctly from reading FSD threads there's an issue with Tesla's angle of view for cross traffic. This is on their website, but not linkable so via electrek.

Image

-https://electrek.co/2016/10/20/tesla-new-autopilot-hardware-suite-camera-nvidia-tesla-vision/

- https://www.tesla.com/autopilot

ISTR that the fov of that camera is 150°, which would mean it is very possible for a car to be approaching from 'too far left', in the area covered only by short range ultrasonics.


onthemove wrote:
How do you decide that it's 'ready'?


The answer is when the lawyers tell you you aren't going to have to refund the vast majority of your FSD takings on the grounds that it doesn't fulfill the requirements under which it was sold, but a better question might be do you ever decide that is ready...?

onthemove wrote:With the progress being more logarithmic than exponential, how do Tesla get from here, to releasing a proper self driving - 'hands off the wheel' - as per Waymo?


When they license a working system designed as a top down AD from a competitor and quietly retire their precoscious cruise control.

onthemove wrote:So this isn't what I'm talking about in deciding whether to release an FSD.

I'm talking about the criteria for deciding whether the software can be trusted enough to roll out to millions of owners, such that they could go to sleep on the journey.


There's long been a disagreement on this board about whether statistical safety will be enough to clear regulatory hurdles, and if Tesla were the only company to make it to FSD that might have a chance, but in the company of systems which have been built with regulation and oversight in mind from the beginning in contrast to Musk's cavalier attitude to regulation they are going to have real problems even if they can produce a functional product which their lawyers and insurers will let them release...

onthemove wrote:
I mean, Tesla aren't going to release FSD final release just because one guy on youtube had his first drive without any disengagements!


It wouldn't surprise me. Whilst looking for info on a question addressed below I came across another video on the Tesla website of a Tesla car driving on public roads with the disclaimer that the driver was only present for legal reasons emblazoned across the screen... It's here: https://www.tesla.com/autopilot

onthemove wrote:I actually think Tesla will probably 'cope' 'better' with obscured roads and non-existent road markings. Things like roads covered in leaves, or roads covered in snow and such like. At least in terms of deciding where the road should be.


Surely the advantage here lies with the much maligned mapping used by the likes of Waymo? Since they already know what the road should look like extrapolating what they can't see from what they can see should be easy enough.

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461451

Postby odysseus2000 » November 27th, 2021, 7:18 pm

There are two aspects to a successful robotic car: Dealing with the asymptotic approach caused by various edge cases to what is considered acceptable and the rate of improvement of the software to get to the point where it can drive better than a human.

One can argue that the former is a logarithmic progress, but the experience of alpha-go in becoming world go champion suggests that the learning function is capable of exponential improvement. It was, prior to alpha go, believed that the rate of increase of the capability of the neural net would not allow it to quickly overcome the logarithmic nature of each decade being 10x more difficult to get through. This was why, as I understand it, there were so many predictions that computers would not reach human standard in Go for a very long time, but we know that didn’t happen. We also know that neural nets easily defeat computational algorithms in the game of chess, requiring less power and less computation to defeat the probabilistic approaches.

The neural net approach results are very like what one sees when humans try to learn something new. At the beginning progress is terrible, but with repeated practice the student gets better and better and finally achieves what is needed, their intelligence defeating the each decade gets 10x harder. If one believe in evolution one can clearly see how nature uses natural selection to allow small changes from what ever source to give one creature an advantage over its peers and over multiple iterations the genes that gave this advantage become dominant. As I understand the neural nets they do the same. When one computation of the weights of all the probable actions begins to be more successful it becomes more influential in determining weights. This is all handwaving but what we do know is that humans are capable of getting good at things and can learn to drive albeit with a probability of an accident that leads to 3000 dead or seriously injured per year. In my view the important point here is that humans with all their limits create a private car system that works well enough for insurers to take the market.

One of the arguments that has raged is whether Waymo with its radars and lidars is better than vision only Tesla. Given the potential of these to see through obstructions I would still think that waymo ought to do better even when the lines are gone, but that Tesla vision may be good enough and better with good lines as there are no lidar and radar overheads.

Regards,

onthemove
Lemon Slice
Posts: 540
Joined: June 24th, 2017, 4:03 pm
Has thanked: 722 times
Been thanked: 471 times

Re: Musk endeavours

#461501

Postby onthemove » November 28th, 2021, 12:43 am

odysseus2000 wrote:One can argue that the former is a logarithmic progress, but the experience of alpha-go in becoming world go champion suggests that the learning function is capable of exponential improvement. It was, prior to alpha go, believed that the rate of increase of the capability of the neural net would not allow it to quickly overcome the logarithmic nature of each decade being 10x more difficult to get through. This was why, as I understand it, there were so many predictions that computers would not reach human standard in Go for a very long time, but we know that didn’t happen. We also know that neural nets easily defeat computational algorithms in the game of chess, requiring less power and less computation to defeat the probabilistic approaches.


I haven't looked in depth at how they did the alpha go, although I have just done a quick google, and from quick skim reading it looks like the main advantage that the AlphaGo effort had was reinforcement learning through self-play.

That's something that you can do with games (clearly defined rules as to what a legal move is, narrow 'world' in which it operates, and a clearly defined 'win'), but doesn't work so well (understatement) with self driving cars.

I won't dwell too much on this specific topic as I'm not intimately familiar with the details of alphago, but I'm reasonably confident that the alphago team weren't getting 'exponential' improvement, at least nothing like in the way that I think you have in mind from what you're describing.

I believe the main things that results like these (and earlier ones with other games) show, is really demonstrating how much computing power the teams behind them have available.

For the alphago, it looks like it was (in part) a combination of being able to learn from 'self play' coupled with a huge amount of computing resources.

odysseus2000 wrote:The neural net approach results are very like what one sees when humans try to learn something new. At the beginning progress is terrible, but with repeated practice the student gets better and better and finally achieves what is needed, their intelligence defeating the each decade gets 10x harder. If one believe in evolution one can clearly see how nature uses natural selection to allow small changes from what ever source to give one creature an advantage over its peers and over multiple iterations the genes that gave this advantage become dominant. As I understand the neural nets they do the same. When one computation of the weights of all the probable actions begins to be more successful it becomes more influential in determining weights. This is all handwaving but what we do know is that humans are capable of getting good at things and can learn to drive albeit with a probability of an accident that leads to 3000 dead or seriously injured per year. In my view the important point here is that humans with all their limits create a private car system that works well enough for insurers to take the market.


Hmmm... this could be tricky to respond to... a lot of what you say there, on the face of it, I totally agree with it - it could be considered a good description of what is going on. At least the sentences taken in isolation.

But on the other hand, I think there is also a misunderstanding buried in there, or at least an absence of a crucial aspect that isn't mentioned.

It's true that neural nets are inspired by biological neurons, and work in a manner believed to be (crudely) similar to biological neural networks. ... It sounds like you're on the right sort of track with this ... "When one computation of the weights of all the probable actions begins to be more successful it becomes more influential in determining weights." .. although it's perhaps thinking about it the wrong way around... neural network training works (as you say) by applying the network, but rather the 'error' in the result is 'back-propogated' through the network, and the weights in the network that contributed to the error are adjusted a little to lessen the amount of error... and this process is repeated many, many times with different training examples, so that eventually the network settles on a set of weights that (hopefully) reduces the error in all cases as much as possible. So in a way, you're right when you say the more successful becomes more influential, but it's more by reducing error rather than enhancing success. But really this is more a case of well it just depends how you think about it.

But then there's the critical aspect that you haven't mentioned, and this is the more important one...

The similarity with how people learn only goes so far.

As this is where the massive divergence comes about, that you don't mention above.

Artificial neural networks (ANNs, CNNs, etc) all do the low level stuff very well, much as you describe as above.

But it's well recognised by most AI researchers, and I believe neuroscientists, etc, that there is something more going on in the human brain.

In fact, when I studied AI at university, the course was actually more oriented to what was (and probably still is) called 'good old fashioned AI'. This is in contrast to 'Connectionist AI' which deals with neural networks and such like.

And the difference here is crucial... 'Good old fashioned AI' is / was based on the recognition that people 'think' at quite a 'high' level... things like logical reasoning, inference, and so on. And there have been a whole host of techniques proposed over many decades now, that attempt to create AI at that sort of level. But while there may be a few useful things in a few narrow areas, there never has been any outstanding success. This area of AI is still very much in the domain of the nerds with the promise of useful results sometime never.

But I don't think it's particular contentious to say that everyone recognises that humans do very successfully use reasoning and (what some at least think to be) logic (even though when analysed formally what many people think is 'logical' doesn't actually turn out to be true; something that AI textbooks raise - should AI be properly Spock like logical or human-like 'flawed logical' .. but I digress).

The key point, is that when you're learning to drive, you have this higher level understanding of the world. For sure, your neural networks, particularly between the retina all the way through the various optic nerve pathways all the way through to the visual cortex at the back of the brain, are doing processing very, very much on a par with the processing being done by the neural networks in (I would expect) all the self driving car projects. (The text books I had at uni detailed the experiments that were done in the middle of the last century sticking electrodes into live monkey's brains and observing how the neurons respond to different patterns of light or motion, vertical lines, horizontal lines, etc in images presented to the monkeys ... :shock: ... and the observations tally quite well with what we see in the layers in at least the first layers in convolutional neural networks.. they tend to respond to similar types of low level features as is observed in the optic nerve, and pathways through to the visual cortex, etc)

But once we reach the visual cortex, that's where we hit a blank. As far as I'm aware, scientists aren't really any significantly closer to understanding how those signals that have been processed by the 'low level' neural networks, then get aggregated and processed by higher level 'reasoning and logic'. And none of the advancements in AI (or neuroscience) that I'm aware of, yet show any promise of remotely bridging that gap (it's still more like a big dark chasm).

So for now, and for the foreseeable future, self driving car development doesn't have the luxury that a human learner driver does, of being able to be told something once, and then use reasoning to apply that more generally.

For now, we're stuck with just throwing a very large number of training examples at a neural network, and hope that that process you describe above - of adjusting the weights, etc - does eventually settle on something that is desirable, rather than for example, learning to read the weather in photographs of tanks, instead of recognising the presence of a tank which is what you are really interested in .... you could tell a human in a few seconds that the tank is what you're interested in... but the only way to tell a neural network is to give it so many pictures that hopefully it eventually recognises that that is what you are after!

In a way, this is why I'm very surprised that Tesla, and also Waymo from what I've seen in some of the later Waymo technical videos, seem to be pushing to use AI all the way up the stack.

To be honest, I would have anticipated that the higher you get up the stack - i.e. the more processed the raw data becomes as it's being analysed - I would have expected it would transition to more traditional programming.

If nothing else, you would expect that they are going to want to be able to easily adapt these cars to different rules in different countries, and such like, and be able to quickly and reliably make changes when the rules change in a country in which they might already have cars on the road... and to be quite honest, I would have thought the programming the 'top level' rules via more regular software engineering would be the preferred method to achieve that. Sure, perhaps using weightings and inputs from the lower level neural networks, etc, but I wouldn't think they'd 'implement' the rules of the road via neural networks. I'd have thought the rules of the road would surely be integrated in a more symbolic / easily configurable manner, than a training neural network.


odysseus2000 wrote:One of the arguments that has raged is whether Waymo with its radars and lidars is better than vision only Tesla. Given the potential of these to see through obstructions I would still think that waymo ought to do better even when the lines are gone, but that Tesla vision may be good enough and better with good lines as there are no lidar and radar overheads.

Regards,


The thing is, I get the impression from watching the Tesla videos that the Tesla is focused more on identifying where it thinks the edge of the road is, and it looks like they have trained some quite generalised neural nets to do this. That (I believe) is why from what I've seen in some of the earlier Tesla videos, the Tesla still seems to be able to identify the edge of the road when it is just a step change in the level of the snow - it seems to be seeing a shadow roughly where it would expect the edge of the road, and seeing that shadow extend along where it would expect the edge to roughly be, so it seems to be thinking, OK that's probably the edge of the road.

I just get the impression from watching how the Waymo behaves in the JJ Ricks videos that the Waymo are very much more focused of identifying the line markings - perhaps not unreasonably, after all, the line marking generally 'label' the rules of how we should behave... which lane we should be in, whether we are permitted to cross the central line and overtake, etc. I just get the impression that the Waymo are focussed more heavily on that aspect.

I guess the impression I have, is that the Tesla approach seems to be more a case of identifying where it physically could drive, whereas Waymo seems (to me) to be focussed on more where it should drive.

And I guess that's why I'm left with the feeling that Waymo might struggle more, if the identifiers of where it should drive are obscured, leaving only an evaluation of where the car could physically drive to guide it.

Though as a previous poster said, Waymo does have the detailed maps.

Yup, that's true, but as I've mentioned before, they are only good up to a point. Yes, they're great for knowing if you're going to need to be in a different lane up ahead to go the route you want, and such like - something the Tesla's really could have done with in a few of those 10.5 videos!

But let's be realistic, an updated high definition map could tell you where a pot hole is - if something's been that route before and seen it. So you could know to avoid it if driving through water, snow or leaves that might be obstructing it at this time.

But, let's be realistic ... things change... there might now be a big stone hidden under those leaves, or a new pothole. Or there might be road accident ahead that means you no longer want to be in the normal lane that you thought you needed to be in.

Sure the Waymo could use a prior map of the road to help guide it, but road layouts do change. There is always the possibility that the road markings / road layout have been changed since any Waymo car was last there ...

...tell me about it... one day several years ago when going to work I nearly got caught out because overnight, without any notice, workmen had been out and shifted the curb a few inches into the road, narrowing the road just a little and making the pavement just a little wider, to make it easier for pedestrians to cross. There were no signs to say they'd done this, and I very nearly hit the curb! It took several takes looking back before I realised what had happened.

If a Waymo and Telsa both drove down that same bit of road, after that change but when it was now covered in snow, I suspect the Tesla would handle it better than the Waymo.

Realistically the Waymo cannot just assume that the road layout is as per it's map. It absolutely needs some degree of confirmation from the sensors (video, lidar, etc) at the time it is driving along it. There's absolutely no way a self driving car can drive 'blind' - i.e. solely on the basis of internal and potentially out of date mapping..

There are sometimes situations - particularly in snow - where the normal lanes change and drivers create their own lanes. For example you sometimes find on motorways, when they get covered in snow, that drivers might create two lanes in the snow, that don't quite align with the 3 lanes marked underneath the snow, for example to give a bit more separation between vehicles in case anyone loses traction and slides. The Tesla would probably recognise these. Would Waymo? Or would Waymo try to stay in one of the 3 lanes that it knows from it's map are marked underneath the snow?

Just to be clear, on the whole, I'm far more impressed by the Waymo poject than Tesla (though Telsa is still impressive, just Waymo more so :D ). I was just saying that in this one case, I get the feeling that Tesla's more gung ho (almost what feels at times like a 'best guess') approach could work in it's favour in degraded road conditions. The only concern is whether it could decide if the road situation is too degraded, and it would be more appropriate not to proceed at all, or whether it would just carry on gung ho regardless with its best guess..

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461601

Postby odysseus2000 » November 28th, 2021, 1:22 pm

Some excellent posts with some of the best information and discussion that I have seen anywhere.

There are several themes which I will attempt to summaries and comment on.

No way can a robot ever manage central London traffic.

Yes, at the moment that is true, but a more interesting question is: Is it impossible from what we know that a robot will ever be able to drive in London traffic. As of now the answer seems to be that there is no fundamental reason why it can’t be done. Yes, it is practically difficult and seems impossible, but forbidden by some fundamental limitation of science, no.

The vision field of the Tesla system isn’t good enough.

Maybe, but humans do drive with a much reduced view of the road. May more or better cameras improve Tesla driving while keeping the processing of those cameras to an acceptable overhead? No idea, but the folk inside the Tesla fsd team don’t seem to think so.

Waymo will be more confused by leaves, snow etc obscuring lane markings than will Tesla which will adapt and attempt to work it out on the fly as humans do.

I have seen various videos of systems using lidar to look through foliage to detect hidden structure, often for archaeological investigations or military purposes, but I am unclear if the Waymo system has similar capabilities, or if the lane markings would only become visible if something like iron-oxide was mixed with the paint. However, for a truly general robotic driving the system would not need line markings which is what the Tesla system is designed to be.

The human brain is much more than a neural net

This I believe is the fundamental issue. Sir Roger Penrose argues that the brain is more than computation, that there are other things going on, which he suggests are quantum mechanical. Others have said that the neural net is easy, but beyond that there is something far more complex and impossible to recreate with current technology. I liked this argument a lot and was pretty convinced that humans would remain well ahead of machines for a long time, maybe for ever, but when alpha-go won at Go I had to ditch that idea. Clearly in at least this small subset of endeavours the human brain is inferior to a machine. There are many other examples, such as a pocket calculator being able to do sums super quickly that an unaided human brain would take a much longer time to do. One can cite very many other things, but can a machine think and reason better than a human? I would like to think no, to believe that humans will forever remain superior to machines in higher functions, but I am continually drawn back to alpha-go. This is not the mindless banter of talking heads, but a data point. The alpha-go that became world champion is now a long way ago in this rapidly evolving technology with neuromorphic chips now replicating the human brain and doing complicated tasks with low power consumption just as does the human brain. This technology has awesome potential, not all good and I am reminded of Churchill’s warning:

“If to these tremendous and awful powers is added the pitiless subhuman wickedness which we now see embodied in one of the most powerful reigning governments, who shall say that the world itself will not be wrecked, or indeed that it ought not to be wrecked? There are nightmares of the future from which a fortunate collision with some wandering star, reducing the earth to incandescent gas, might be a merciful deliverance.

https://winstonchurchill.org/publicatio ... t-suicide/

Tesla fsd is the canary for a lot of this. If it can be got to work then Tesla longs will make a fortune, but whether we will be able to enjoy the money I don’t know.

To my mind we can speculate as much as we want and it is fun to do so, but it is the experimental results that matter. As of now Tesla FSD or Waymo and probably some of the Chinese versions (but I am far from clear how good some of the claimed Chinese level 5 are) are telling me that humans are better at driving than machines. The experimental results also tell me that machines are better than humans as GP’s, lawyers and a whole host of well paid professionals governed by laws, but not yet better at manual tasks like say a dentist, gardener, assembly worker…

As I see things, the progress of Tesla fsd will tell us far more than most humans expect and is the canary we need to stay focused on.

Regards,

BobbyD
Lemon Half
Posts: 7814
Joined: January 22nd, 2017, 2:29 pm
Has thanked: 665 times
Been thanked: 1289 times

Re: Musk endeavours

#461648

Postby BobbyD » November 28th, 2021, 5:08 pm

Volkswagen has hired two high-profile managers for its battery programme. One of them is said to be Apple’s head of battery development Soonho Ahn, while solid-state cell expert Jörg Hoffmann is also to join VW from BMW.

Soonho Ahn had been working for Apple since 2019, before that the South Korean manager had worked for the cell manufacturers Samsung SDI and LG Energy Systems (formerly LG Chem). Initially, Manager Magazin had reported on the personnel matter, but in the meantime the report has been confirmed by Volkswagen.


- https://www.electrive.com/2021/11/26/vw ... and-apple/

Soonho Ahn

CTO, Battery Division, VW Group Components


- https://de.linkedin.com/in/soonho-ahn-2 ... earch-card

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461884

Postby odysseus2000 » November 29th, 2021, 5:16 pm

VW have now retraced their share price to what it closed at in January:

https://twitter.com/0_ody/status/146536 ... 68326?s=20

What ever VW may say, investors are not showing much confidence in the company.

Regards,

BobbyD
Lemon Half
Posts: 7814
Joined: January 22nd, 2017, 2:29 pm
Has thanked: 665 times
Been thanked: 1289 times

Re: Musk endeavours

#461896

Postby BobbyD » November 29th, 2021, 5:55 pm

odysseus2000 wrote:VW have now retraced their share price to what it closed at in January:

https://twitter.com/0_ody/status/146536 ... 68326?s=20

What ever VW may say, investors are not showing much confidence in the company.

Regards,


Whilst I couldn't care less, VW Ords are still up 53% on the year...

onthemove
Lemon Slice
Posts: 540
Joined: June 24th, 2017, 4:03 pm
Has thanked: 722 times
Been thanked: 471 times

Re: Musk endeavours

#461922

Postby onthemove » November 29th, 2021, 7:45 pm

odysseus2000 wrote:No way can a robot ever manage central London traffic.


Not quite central London, but this video should start at the point that gives me hope...

https://youtu.be/XzLMTR5ACG0?t=118

And the rest of the video ain't bad either - in fact looks pretty good.

I've just watched it all the way through, and to be honest, I think it's a fair assessment in the title that there were no disengagments - the driver didn;t (at least acknowledge) pressing the accelerator or dialing in different speeds. And even the couple of things the driver said that he flagged to Tesla as needing improvement, I didn't think it handled them too badly.

Caveat: Apart from that manoeuvre at where the link above should start, it doesn't really encounter very much traffic otherwise.

A couple of observations:

It does seem to be pretty confident now at handling those 4 way stops, which I must admit, when I've driven in the US, they felt so alien to me. I mean, you've got to watch who arrives when, and hope that your judgement agrees with the other drivers, etc. Quite nerve racking when you're not familiar - other drivers can get quite annoyed if you don't go when they judge that it's your turn (trust me :) )! The Tesla's driving at this quite busy 4-way stop I was particularly impressed with - https://youtu.be/XzLMTR5ACG0?t=607 - the oncoming traffic was in two lanes! And even the others, the Tesla seemed to be judging quite well (based on the absence of any reactions from the other drivers arriving at the stop from the other directions!).

This part seems to have improved - https://youtu.be/XzLMTR5ACG0?t=199 - I think I've commented about this turn in a previous video where the Tesla driver had to slam on the brakes because the car was going to try and drive into the tent! This time, changing it's mind and going a different route seems perfectly good driving. Caveat: This could just be luck! As I've mentioned before, the problem that I see with the Tesla is that small variations in what it sees, etc, can make a huge difference between success and failure. Perhaps this time was just luck.

But overall - minimal traffic to confuse it aside - it did look like quite a reasonable drive. Can't all have been down to just luck ;)

Doesn't change my view that there's still a heck of a long way to go though! Like I say, it'll take a lot more than 1 or 2 youtube videos without an intervention, on largely quiet back streets outside of rush hour, that the driver has just put in to create a Tesla video, before you could release FSD to all Tesla vehicles and let people go to sleep!

But it's making progress. Still a long journey ahead, but it is making progress.

I do have concerns about those camera fields of view that someone posted earlier up the thread. The tesla is pretty much relying on the cameras to establish depth, and it doesn't look like there's an awful lot of coverage to monitor traffic coming from the side. In fact, in another video I watched yesterday, the car started to cut even across oncoming traffic, and the driver hit the brake and was not impressed. I couldn't help notice the oncoming traffic was actually approaching on a curve. I wonder if the Tesla is having problems predicting the path of cars if they're not following a either perfectly inline, or perfectly at right angles. On top of struggling with poor camera coverage at the sides.

And just a final thought - clearly a lot of effort has gone into handling those 4 -way stops. But 4-way stops are a quirk of the US, not in Britain.

This does raise the question... how much of the progress that we're seeing will travel over to the UK?

Youtube seems to have stopped recommending me any of the UK based Tesla videos... in fact, I think the last one I saw a while back, the driver seemed to indicate that he'd given up on the FSD in the UK, as it didn't seem to be particularly improving on UK roads, so wasn't going to keep putting regular videos out. I wonder if Tesla are just prioritising the US at the moment?

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461939

Postby odysseus2000 » November 29th, 2021, 9:22 pm

onthemove
Not quite central London, but this video should start at the point that gives me hope...

https://youtu.be/XzLMTR5ACG0?t=118

And the rest of the video ain't bad either - in fact looks pretty good.

I've just watched it all the way through, and to be honest, I think it's a fair assessment in the title that there were no disengagments - the driver didn;t (at least acknowledge) pressing the accelerator or dialing in different speeds. And even the couple of things the driver said that he flagged to Tesla as needing improvement, I didn't think it handled them too badly.


My first thought was this guy is spoofing things, its too good, but there was no indication of disengagements on the display that I saw and no audio till the very end when he deliberately took it out of auto pilot.

It looks to me that Tesla FSD has learned and like a young human driver it has got a lot better in very little time, the sort of exponential progress that I have thought was possible.

Other 10.5 fsd that I have watched have not been as good which makes me wonder if the car body has some effect. This looks like an X from what I can see but I am not confident in that identification. Nonetheless what ever it is, assuming it is genuine, this looks extraordinarily good and very close to being the FSD that has been advertised.

Clearly we need to see more videos in different cars with different drivers, but if this is now how the FSD cars are going to drive then Tesla stock is about to leap upwards by a large amount.

Regards,

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461941

Postby odysseus2000 » November 29th, 2021, 9:29 pm

onthemove
Youtube seems to have stopped recommending me any of the UK based Tesla videos... in fact, I think the last one I saw a while back, the driver seemed to indicate that he'd given up on the FSD in the UK, as it didn't seem to be particularly improving on UK roads, so wasn't going to keep putting regular videos out. I wonder if Tesla are just prioritising the US at the moment?


Yes, as far as i understand it 10.5 is just in the US, but I can't definitely find that anywhere on the net.

Regards,

onthemove
Lemon Slice
Posts: 540
Joined: June 24th, 2017, 4:03 pm
Has thanked: 722 times
Been thanked: 471 times

Re: Musk endeavours

#461949

Postby onthemove » November 29th, 2021, 11:24 pm

odysseus2000 wrote:My first thought was this guy is spoofing things, its too good, but there was no indication of disengagements on the display that I saw and no audio till the very end when he deliberately took it out of auto pilot.

It looks to me that Tesla FSD has learned and like a young human driver it has got a lot better in very little time, the sort of exponential progress that I have thought was possible.

Other 10.5 fsd that I have watched have not been as good which makes me wonder if the car body has some effect. This looks like an X from what I can see but I am not confident in that identification. Nonetheless what ever it is, assuming it is genuine, this looks extraordinarily good and very close to being the FSD that has been advertised.


The video certainly looks good, but let's not jump ahead of ourselves. It's not an exponential improvement. A noticeable step up, but not exponential... and like you say, other 10.5 videos haven't been so good.

In my view, what made this particular drive look so good is what I mentioned in my earlier posts about where I think Tesla is likely to do better than Waymo ... specifically most of the roads the guy drives down in the video are back streets with very few road markings - in fact, many only have the "Stop" markings at the end, and are otherwise free of paint. The car is only needing to recognise the curb and pass any oncoming vehicles on the RHS of them.

I think for me, thinking about it more, what made it stand out for me is the 'confidence' it now seems to display.

I mean, that merge where I put the initial link to start at... it was the confidence in which the car.. (1) recognised that it needed to merge into the traffic to its left, (2) then slowed down appropriately putting its indicators on in order not to push in, but then (3) within around half a second to 1 second, judged that the car behind to it's left was letting it pull in, then (4) confidently executed the merge without hanging around - it didn't dither and the car behind get fed up. It (appropriately) saw the opportunity and just took it.

Bearing in mind that the road markings weren't in its favour (its lane was blocked) and the rules (I presume they're the same as in the UK) wouldn't give the Tesla any 'right' to push in ... it was (I presume) entirely on the good will of the car that allowed it to merge... I think this is why I felt it gave hope that it could eventually work for central London. Clearly a long way to go before doing that in much more complex traffic, but I think it did demonstrate the basic behaviour of what is needed to driving in more busy city traffic.

But the speed at which it was making judgements seemed markedly improved - particularly when arriving at the 4-way stops and deciding whether it was its turn. All the other drivers seemed completely 'in tune' with it. None of the other drivers seemed to be waiting unduly for the Tesla to move, and nor did the Tesla set off at the same time as others and have to abort its move. And that was with some of the vehicles arriving almost at exactly the same time, making it quite ambiguous (at least for me) as to who's turn should be next. But the Tesla seemed to ace it.

It was also fairly impressive how quickly it decided that it needs to go around parked or stationary vehicles.

On the whole though, that's the first video I've watched where it didn't feel the presence of jeopardy all the time. It's the first Tesla video I've watched where I could believe that maybe one day - eventually - you will be able trust a Tesla to be driving "keep your hands off the steering wheel" in the manner that Waymo already can do (albeit geofenced).

But like I say, taken in the context of the other 10.5 videos, I reckon that it's largely down to the roads being fairly wide, free for the most part of road markings that need to be interpreted and obeyed, and very much empty of other vehicles and people.

For sure something seems to have 'clicked into place' with that drive that almost enables us to anthropomorphise the driving to a small degree. But as I detailed above, it's probably only in a few small areas.

Actually, I've just watched it again while putting together this post, and another thing I've just noticed... it seems a lot better now at stabilising its planned path through a junction when there are other cars currently traversing the junction. In earlier versions while the Tesla is waiting, you could see the predictive path often curving around cars already on the junction as though it is planning to drive around them .. which makes no sense, because the Tesla isn't allowed to go until those cars clear the junction. Whereas, now in 10.5 the path seems to stay planned appropriately, staying going through the cars on the junction recognising that when it does eventually move, those cars will no longer be there. (The next step of the challenge is then recognising when one of the cars on the junction has broken down, and that actually it is now appropriate to go around it).

But that path planning through junction behaviour looks like a definite improvement.

Overall, I don't agree that these things are anything like exponential. But the guys in Tesla developing the system can certainly be pleased with the progress. Definitely worth the boss bringing them some celebratory donuts. There are definitely a few small aspects of the FSD that have gone from 'early development' to 'you know what, this part could actually work'.

The challenge now is the rest of it. Still a very long way to go. And can the rest be done without undoing the behaviours / aspects that now seem to be working reasonably well? It's certainly not guaranteed.

But this is the first video I've watched where I now feel that someone in the development team is on the ball. For the first time I get the feeling that perhaps just maybe there is someone on the team, now in a place where they can make their mark, who actually has a plan as to how they might get to a final FSD - i.e. how it might all fit together.

Up until now, I've just felt the Tesla team were a bunch of enthusiastic and clever people, but amateurs really without a plan. Lot's of potential ideas, along the lines of "oh, boss, boss, we could try this"... and "oh, oh, and how about this boss?"... and "boss, boss, what about this".... but no real plan of how it would all fit together, or arrive at a final cohesive product that could be release to the public.

And I very much had the impression of Musk as the sort of boss who thinks that's fine, that you just throw a whole load of money at such a group of people and say "there you go guys, make it happen".

But for the first time, I get the feeling that some aspects really are now starting to properly fit into place... it does now feel like there actually could be a plan or road map forming in the Tesla development team.

Whether or not the existing hardware will be adequate to see it through, that's still a big question. The other big question is how long will it still take. Don't underestimate how much more they yet need to achieve before this could be released properly.

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#461952

Postby odysseus2000 » November 29th, 2021, 11:44 pm

onthemove
But for the first time, I get the feeling that some aspects really are now starting to properly fit into place... it does now feel like there actually could be a plan or road map forming in the Tesla development team.

Whether or not the existing hardware will be adequate to see it through, that's still a big question. The other big question is how long will it still take. Don't underestimate how much more they yet need to achieve before this could be released properly.


Yes.

I was becoming discouraged with the performance and beginning to feel that there was a near random nature to how well the FSD worked. I did not expect anything like this to emerge for years.

There are many caveats, but I am getting the same sort of feelings as when I heard about Alpha Go becoming world Go champion, a complete mindset shift about what neural nets could do.

10.5 is doing things, at least in this video, that the previous versions could not and, as you say, it is doing it confidently in situation with human drivers and complicated 4 way stops.

This kind of surprise (at least to me) suggests an emerging real capability that I thought impossible a week ago.

Dunno, I think something significant has changed and that is what is bringing on the emotions that came when I heard about alpha-go victory. The neural net has suddenly jumped forwards a long way in almost no time and I find that exciting.

Regards,

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#462067

Postby odysseus2000 » November 30th, 2021, 1:50 pm

Interesting lab results showing that concrete can be used as a battery:

https://youtu.be/OJxU3fKMdaw

Regards,

ReformedCharacter
Lemon Quarter
Posts: 3120
Joined: November 4th, 2016, 11:12 am
Has thanked: 3590 times
Been thanked: 1509 times

Re: Musk endeavours

#462178

Postby ReformedCharacter » November 30th, 2021, 9:39 pm

Musk claims risk of Spacex bankruptcy in an email to his employees:

In an email sent to SpaceX employees, Elon Musk addressed the ‘crisis’ of Starship Raptor engine production and said, the company could face a ‘genuine risk of bankruptcy’ if the company is unable to achieve a Starship flight rate of once every two weeks next year. The company is having trouble with the production of its Raptor engine – a full-flow staged combustion Methane engine – for the Starship vehicle.

The production issues have become even more pronounced, as Musk outlined in a recent email. Unfortunately, the Raptor production crisis is much worse than it had seemed a few weeks ago. As we have dug into the issues following the exiting of prior senior management, they have unfortunately turned out to be far more severe than was reported. There is no way to sugar-coat this.

Musk continued the email asking employees for all hands-on deck: Unless you have critical family, matters or cannot physically return to Hawthorne, we will need all hands on deck to recover from what is, quite frankly, a disaster.

The consequences for SpaceX, if we cannot get enough reliable Raptors made is that we then can’t fly Starship, which means, we then can’t fly Starlink Satellite V2 (Falcon has neither the volume nor the mass to orbit needed for satellite V2). Satellite V1, by itself, is financially weak, while V2 is strong. In addition, we are spooling up terminal production to several million units per year, which will consume massive capital, assuming that satellite V2 will be on-orbit to handle the bandwidth demand. These terminals will be useless otherwise. These newer satellites are larger. SpaceX has been flying V1.5 satellites recently.

SpaceX has been able to save money by being its own launch provider, however, Musk’s statement that “Satellite V1 by itself is financially weak” is important to note. Even on Starlink user terminals alone, the company was losing almost $1,000 per customer at first. The company has since brought costs down and launched a new user terminal, but it was operating at a major up-front loss in order to build a customer base for the satellite internet constellation in low-Earth-orbit. That’s not even considering the millions per Falcon 9 launch and the actual cost of the satellites in orbit, which Musk is saying will improve with V2 and Starship.

Musk closed out the email with a dire message:
What it comes down to, is that we face a genuine risk of bankruptcy if we can’t achieve a Starship flight rate of at least once every two weeks next year.

Thanks,
Elon


https://www.youtube.com/watch?v=wowwMV9NP_I

RC

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#462195

Postby odysseus2000 » November 30th, 2021, 10:48 pm

Another theme running around the net is that Tesla can't get Starship launch approval without a significant water reserve to cool the launch area and protect against fires etc if there is a failure. The argument goes that although SpaceX is on the coast this does not help as the water needed has to be sans salt and they therefore need a huge de-salination plant costing many billions. I have no idea if this is true.

Regards,

tjh290633
Lemon Half
Posts: 8208
Joined: November 4th, 2016, 11:20 am
Has thanked: 913 times
Been thanked: 4096 times

Re: Musk endeavours

#462270

Postby tjh290633 » December 1st, 2021, 10:26 am

odysseus2000 wrote:Another theme running around the net is that Tesla can't get Starship launch approval without a significant water reserve to cool the launch area and protect against fires etc if there is a failure. The argument goes that although SpaceX is on the coast this does not help as the water needed has to be sans salt and they therefore need a huge de-salination plant costing many billions. I have no idea if this is true.

Regards,

I can't think of any scientific reason why the water has not to be salty. If the site is coastal, the surplus water can be run off back into the sea. If not, you might end up with a localised salt Marsh, which might already be there.

TJH

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#462298

Postby odysseus2000 » December 1st, 2021, 11:34 am

tjh290633 wrote:
odysseus2000 wrote:Another theme running around the net is that Tesla can't get Starship launch approval without a significant water reserve to cool the launch area and protect against fires etc if there is a failure. The argument goes that although SpaceX is on the coast this does not help as the water needed has to be sans salt and they therefore need a huge de-salination plant costing many billions. I have no idea if this is true.

Regards,

I can't think of any scientific reason why the water has not to be salty. If the site is coastal, the surplus water can be run off back into the sea. If not, you might end up with a localised salt Marsh, which might already be there.

TJH


The argument is that some components of the rocket would be troubled by corrosion from salt in the water. Clearly not the body which is stainless, but there are lots of bits in the engines or perhaps the tiles that may be. I have no idea if this is true. The angry astronaut on Youtube has a video about it, but there is so much misinformation and uncertainties about things on the internet that it is difficult to know what is true. I have not heard Musk or anyone from SpaceX talk about it, which makes me think it is false, but there have not been any Starship tests for a while and one of the arguments put forward is that the authorities require that SpaceX have a large amount of water to be available. Dunno. I did see rocket motor tests for the shuttle at Nasa Marshall, from quite a way back so I didn't see what happened down where the rocket exhaust went, but after wards there was a huge cloud of steam suggesting they were using water to cool the area.

Regards,

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#462302

Postby odysseus2000 » December 1st, 2021, 11:42 am

I think this is from Elon on potential bankruptcy of SpaceX:

https://twitter.com/elonmusk/status/146 ... 69063?s=20

I can't be certain this is definitely from him, but if it is and the billions needed for a desalination plant are also true this may be part of his new fears for the financial safety of SpaceX.

As things now are he should easily be able to raise billions, but things can change very quickly in a business with as many risks as rocket launching, especially, as seems to be the case, that senior managers, who are now out of the company, have not been honest with their reports.

Regards,

ReformedCharacter
Lemon Quarter
Posts: 3120
Joined: November 4th, 2016, 11:12 am
Has thanked: 3590 times
Been thanked: 1509 times

Re: Musk endeavours

#462314

Postby ReformedCharacter » December 1st, 2021, 12:23 pm

odysseus2000 wrote:
The argument is that some components of the rocket would be troubled by corrosion from salt in the water. Clearly not the body which is stainless, but there are lots of bits in the engines or perhaps the tiles that may be. I have no idea if this is true. The angry astronaut on Youtube has a video about it, but there is so much misinformation and uncertainties about things on the internet that it is difficult to know what is true. I have not heard Musk or anyone from SpaceX talk about it, which makes me think it is false, but there have not been any Starship tests for a while and one of the arguments put forward is that the authorities require that SpaceX have a large amount of water to be available. Dunno. I did see rocket motor tests for the shuttle at Nasa Marshall, from quite a way back so I didn't see what happened down where the rocket exhaust went, but after wards there was a huge cloud of steam suggesting they were using water to cool the area.

Regards,

The Shuttle launches used large quantities of water to attenuate the sound of the rocket motors as well as prevent damage to the flame buckets. The first launch - a test really - caused acoustic damage to one of the control surfaces on the Shuttle, basically bent beyond design specifications, and the loss of a number of heat tiles. They were fortunate that the flight was successful. That required a redesign of the water release system (which provided 1.1 million litres during launch). Apparently there is a large water tank amid the methane and oxygen tank farm at Spacex's Boca Chica facility but I have heard that the first launches are to be used without a water deluge system which I find hard to believe, given that the thrust will be c. 1.5 x that of the Saturn 5. If there is a launch failure I cannot see that the use of sea water as a fire control measure would be much of a problem to the rocket or motors which would presumably have suffered some sort of catastrophic damage anyway, a little corrosion would be the least of their problems I would think :) But we shall see, hopefully in January.

RC

odysseus2000
Lemon Half
Posts: 6361
Joined: November 8th, 2016, 11:33 pm
Has thanked: 1530 times
Been thanked: 958 times

Re: Musk endeavours

#462331

Postby odysseus2000 » December 1st, 2021, 1:33 pm

This is where I first learned about the deluge system, from approx 7 minutes:

https://youtu.be/k1w3-PKKdrc

There are many other bits and pieces references. This is what Angry Astronaught references:

https://techcrunch.com/2021/10/08/the-m ... ssing-gas/

but its light on the desalination, mostly about the gas powerstation that SpaceX want to build to power the desalination plant, make fuel etc and there are environmental regulations about this that may be part of why folk are suggesting it must be salt free water.

There are other articles/videos but things are often brief on details and written more for sensation that imparting useful knowledge.

Regards,


Return to “Macro and Global Topics”

Who is online

Users browsing this forum: No registered users and 3 guests