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

Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

bloomberg.com

Post reply on HN
Print view View original

321–330 of 340 posts

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#321

Post by Piskvorrr »

throwaway76543 wrote: post #306
zaarn wrote: post #172

Earlier quoted context omitted.

Machine Learning still confuses Elephants for Cats. While it's quite fun if you pin up a cat dressed up in an elephant costume and surely amuses a few colleagues, a self-driving car is not something that should confuse an Elephant for a Cat. ML is IMO not reliable enough for use in self-driving cars, in complicated situations the driver should take over.

It's not reliable enough now, sure. Similarly, my 6 year old is also not reliable enough to pilot a car. Both will change as they mature.

Sure, multiple decades sounds about right (as opposed to current confusing statements like "has full self driving capabilities").

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#322

Post by Piskvorrr »

justtopost wrote: post #232
darawk wrote: post #164

Earlier quoted context omitted.

It may be that regions with better climates receive these vehicles first. It's relatively straightforward to detect the prevalent conditions and refuse to drive if the weather is outside the scope for which the vehicle is rated. As the technology matures, that scope should broaden.

So road trips are unaccounted for? Not a comforting idea that taking your car to another area will render it functionally unsafe on the (differently designed) roadways.

Essentially the same as "smartphones are about 95% useless without mobile broadband". Except for the tiny detail that lack of mobile coverage is unlikely to kill you...

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#323

Post by graycat »

davchana wrote: post #169
graycat wrote: post #104

Earlier quoted context omitted.

E.g., going down hill in the winter commonly requires putting the transmission in neutral since just the torque to the drive wheels from the engine idling or the engine braking can overwhelm the very tiny traction available. There's a really short description for self-driving cars -- hyperhype.

I have always heard it in opposite; that it will be hard to brake & stop if in neutral as compared to if in appropriate gear.

There can be cases in two wheel drive where the engine is just idling with the transmission in Drive, touch the brakes just a little, and have the drive wheels turning and moving the car while the other two wheels, with so little traction, are not turning but sliding with no directional control.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#324

Post by Piskvorrr »

PopeDotNinja wrote: post #268
btbuildem wrote: post #258

Honestly, it seems like a more workable solution would be to improve the roadways with built-in beacons to indicate where a road is, and where it isn't. The cars would work only on the improved infrastructure, but they would work. I suppose there is a danger of nefarious actors spoofing beacons to make you drive off a bridge, but it seems far-fetched.

To me that removes the "self" in self-driving car. A car that stays on the road because there are magic beacons is like bowling with thise giant bumpers in the gutters. It'd be more like cars with uber cruise control.

That would be a train, essentially. Nothing wrong with that - but some of the stakeholders would need to eat crow. That could prove problematic, as some actors have doubled down on the "full autonomy real soon now™".

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#325

Post by rjsw »

graycat wrote: post #319
nkurz wrote: post #305

Earlier quoted context omitted.

To the contrary, "winter tires" actually have comparable benefits for stopping. Here's are the first three findings (of ten) from a recent University of Michigan report: Finding #1: The main benefit of winter tires is improved tire adhesion, braking and cornering performance–not acceleration performance. Finding #2: Winter tires provide improved traction on roads that are below 7 °C (45 °F) even when snow and ice are…

I agree, but "winter tires" are quite different from "snow tires". Moreover, I was implicitly assuming that the stopping would be on snow, and not packed snow but, say, just snow as it fell although maybe a minute ago to several days ago. For stopping on wet or slushy streets or just, say, 1-2 inches of snow, then, sure, "winter tires" not only help stopping but likely are better than snow tires. But when my driveway…

I have driven in 8" of fresh snow with winter tyres, more than once, they work well. I do remember my grandparents having tyres with deep treads but that kind of thing isn't common in Europe.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#326

Post by telchar »

Piskvorrr wrote: post #318
bluGill wrote: post #252

Earlier quoted context omitted.

We already know that the assumption is correct for a lot of cases. Self driving cars have logged millions of miles on the road. The only question is can we make them work in situations that are hard.

Meanwhile human-driven cars have driven billions. The only question is can we make them (humans) work in situations that are hard? In other words, "it works until it doesn't" is tautologically true, but useless precisely for that reason.

The answer to your question is basically "no". Humans aren't getting better at driving in the aggregate - new ones are born, learn to drive, get better, then get worse, then die off. On average humans are as good as they're going to get (with small variations due to culture and different training programs).

On the other hand the self-driving cars are just getting started. It's entirely reasonable to suppose that they may surpass the average human in the next X years. And they won't get old and confused and eventually replaced with new cars that have to learn from scratch -- they should get more or less monotonically better. I think the optimism is warranted even if the timeline and technology is uncertain.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#327

Post by telchar »

saalweachter wrote: post #296
shiftpgdn wrote: post #250

Earlier quoted context omitted.

I have been in a lot of monsoon level downpours where it is effectively impossible to drive as visibility goes to 0. There are different types of rain.

At some point "no one[0] should be driving" becomes a valid answer. [0] I mean, there are going to be cases, but the number of people currently driving in horrific weather conditions because it would be inconvenient not to is too damn high.

It seems a lot of posters aren't willing to consider self-driving cars feasible until the cars are as foolhardy as the bottom-decile driver while still maintaining a perfect safety record. But most of accident prevention is in the planning more than the execution. It seems only reasonable to expect SDCs to avoid situations that some human drivers would brave if the risk is too high.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#328

Post by Retra »

wool_gather wrote: post #308
Retra wrote: post #133

Earlier quoted context omitted.

How does a car know it can't see well?

How does a human know it can't see well?

Well, that's a great question. It's also basically equivalent to the one that I asked. My point would be that I don't have an answer to that question, and given your response, I bet you don't either. Which leaves either of us at a loss when we try to create a safe and reliable autonomous vehicle.

It's certainly not an unanswerable question. It's just quite hard to verify that they answer you have is a sufficiently correct one.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#329

Post by Retra »

adrianN wrote: post #143
Retra wrote: post #133

Earlier quoted context omitted.

How does a car know it can't see well?

It uses its sensors. If the LIDAR shows only white noise it knows that it can't see well.

White noise certainly isn't the only indicator that one can't see well.

Re: Self-Driving Cars Can Handle Neither Rain nor Sleet nor Snow

#330

Post by Retra »

throwaway76543 wrote: post #150
Retra wrote: post #131

Earlier quoted context omitted.

Yes, it is trivial to calculate how to respond to known hazards. What is hard to calculate is what the hazards actually are in any given situation. Humans don't merely look at the road and compute how much standing water is there, they have prior experiences and a sense of what other drivers are doing on the road and why they are doing those things.

Self driving cars also have prior experiences and a sense of what other drivers are doing and why. That's sort of the point of machine learning. In fact, they will have a lot more prior experience than any human driver in the world.

They have a lot more experience driving, but humans do not only use their driving experiences as priors.
Post reply on HN