Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Tesla's self driving algorithm's overlay [video]

tesla.com

Post reply on HN
Print view View original

631–640 of 658 posts

Re: Tesla's self driving algorithm's overlay [video]

#631

Post by bdamm »

sib wrote: post #464
xkjkls wrote: post #294

Earlier quoted context omitted.

Given that in many countries GPS barely works enough to order an Uber with a human driver, I'm highly skeptical of self-driving taxis.

I'd like to understand this better. Intentional interference with satellites? Too mountainous or too heavy tree cover? I can imagine navigation services not working, but I've not been in places outside of the high Arctic (~82'N) where GPS itself wasn't very reliable.

Deep in large cities (New York, San Francisco, etc) with all the RF reflections can actually be quite challenging for GPS. Challenging == actually terrible and everyone knows it. Off by blocks, and definitely no help at all for vertical location.

And inaccuracy at start-up is also surprisingly challenging; think a person requesting a car within 5 seconds of opening the app, before the location service of the device has really resolved the location, thus ending up with a pick-up pin that is a hundred feet wrong or more. And maybe on the wrong side of a street, fence, etc.

Re: Tesla's self driving algorithm's overlay [video]

#632

Post by thedance »

a_bonobo wrote: post #520
thedance wrote: post #391

Earlier quoted context omitted.

These can make neat demos but what’s the false negative rate?

I don't think that data exists (outside of Honda's internal servers), does similar data exist for Teslas?

I doubt that even Honda knows.

Re: Tesla's self driving algorithm's overlay [video]

#633

Post by hau »

tantalor wrote: post #395
ipunchghosts wrote: post #122

The amount of jitter in the estimates makes me nervous, especially when the model thinks something is present in one frame and not there in the next.

Your human eyes+brain do the same thing.

Humans and many other animals have a persistent world model. My eyes+brain reckons things don't disappear instantly even when I don't have a direct line of sight.

Re: Tesla's self driving algorithm's overlay [video]

#635

Post by tw04 »

ggreer wrote: post #487
tw04 wrote: post #258

Earlier quoted context omitted.

Really? By your logic Minnesota, Iowa, North Dakota, South Dakota, Colorado, Montana, Idaho, Wisconsin, etc. should shut down for the winter? Businesses don't shut down just because the forecast says it might snow. Plows can't get out fast enough to clear the road to a point the lines would be readable/visible for a self-driving car. Humans may not be perfect but we find a way to get home in the snow without the mass…

Most drivers don’t live in Minnesota, Iowa, North Dakota, South Dakota, Colorado, Montana, Idaho, Wisconsin, etc. If you want to see how the average driver performs on icy roads, look at videos from Portland and Seattle. Both of those cities practically shut down when there is snow on the roads.

Ok - Illinios, Michigan, Pennsylvania, New York, etc.

Seattle and Portland shut down because they rarely get snow. You might as well have listed Atlanta.

Re: Tesla's self driving algorithm's overlay [video]

#636

Post by travisporter »

exabrial wrote: post #158

What's the FPS rate of the algorithm? It says on the OSD: `13.3 FPS`, which seems very low: 50mph = 73 feet per second / 13 frames per second = 5 feet per frame. This still way faster than a human I'm guessing, but seems very slow.

Short of hardware, is there any way to speed up this classification by "pruning" the neural network without losing accuracy?

As an aside, how do they get training data from their existing sold vehicles? over cell connection probably is too expensive I assume, so maybe via wifi?

Re: Tesla's self driving algorithm's overlay [video]

#637

Post by grey-area »

Slartie wrote: post #362
grey-area wrote: post #352

Earlier quoted context omitted.

Are computers better than the best human drivers in all circumstances? No, maybe they never will be, but that doesn't matter. Are they better than average humans in average conditions already? Yes. They don't need to be all powerful AGI which can replace humans in all circumstances to be useful and save lives.

What doesn't matter is who wins in average conditions. Because averages are just that: averages. But actual driving is full of non-average situations, whether they are created by weather, other human participants in traffic, animals, whatever...there's millions of surprising non-standard situations happening each day in traffic, and current technology isn't even able to reliably detect when it's facing such a situati…

And yet autopilot is doing millions of miles a year with fewer incidents than humans, and expanding in capability (for example taking lane changes and turns), all while constantly lowering the level of accidents.

I think average conditions do matter, and supervised computers will continue to take over driving until humans are simply not required. Of course they will not replace humans this year or next, but at some point humans will be passengers, not drivers.

Re: Tesla's self driving algorithm's overlay [video]

#638

Post by Dylan16807 »

RugnirViking wrote: post #609
Dylan16807 wrote: post #585

Earlier quoted context omitted.

...but if it starts braking hard in 250ms that's still a very superhuman reaction time.

As humans we know our reaction times - you naturally slow down as you get to a junction or navigate crowded or tricky traffic conditions to give yourself as much of a chance as possible to react. This is the thinking behind many types of speed control street layouts. You should also know where to look to anticipate where danger is most likely to come from, and be ready with some kind of action. This is why we do haza…

It's very easy to configure a program to slow down before intersections. Also if we want to be realistic here, you're going to be able to see that the other car isn't slowing properly for much longer than 200ms. You'd either already be braking when you hit that pause, or you'd be so early on that the delay doesn't make a real difference.

And if you're not hovering your foot over the brake pedal, you're not getting 250ms.

Re: Tesla's self driving algorithm's overlay [video]

#639

Post by xkjkls »

sib wrote: post #464
xkjkls wrote: post #294

Earlier quoted context omitted.

Given that in many countries GPS barely works enough to order an Uber with a human driver, I'm highly skeptical of self-driving taxis.

I'd like to understand this better. Intentional interference with satellites? Too mountainous or too heavy tree cover? I can imagine navigation services not working, but I've not been in places outside of the high Arctic (~82'N) where GPS itself wasn't very reliable.

Have you ever used Google Maps in a country like Costa Rica? Because the country isn't mapped to nearly the same degree (also, they have a habit of not even naming their roads), it becomes barely useful. I'm not talking about the technology of global positioning, I'm referring to all of what we take for granted with it for.

Re: Tesla's self driving algorithm's overlay [video]

#640

Post by xkjkls »

bdamm wrote: post #631
sib wrote: post #464

Earlier quoted context omitted.

I'd like to understand this better. Intentional interference with satellites? Too mountainous or too heavy tree cover? I can imagine navigation services not working, but I've not been in places outside of the high Arctic (~82'N) where GPS itself wasn't very reliable.

Deep in large cities (New York, San Francisco, etc) with all the RF reflections can actually be quite challenging for GPS. Challenging == actually terrible and everyone knows it. Off by blocks, and definitely no help at all for vertical location. And inaccuracy at start-up is also surprisingly challenging; think a person requesting a car within 5 seconds of opening the app, before the location service of the device h…

There's also issues like Australia, which because of plate tectonics the maps corresponding to GPS coordinates had to recently be moved close to a meter.

We think of GPS as just the positioning part, but its just as important to remember that there is a large amount of work to translate that position into a meaningful data point within each given country. Just knowing someones exact GPS coordinates isn't helpful.

Post reply on HN