Live data from Hacker News

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

bloomberg.com

141–150 of 340 posts

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

#141
post #58

Earlier quoted context omitted.

In my entire life, I've never encountered the Trolley Problem, and I've never met anyone who has. Most safety problems in driving can be solved by slowing down . The problem with AI is all those weird, little edge cases that humans can reason through -- for example: if there's a deer next to the road, then I'll slow down, even if it's not on the road yet. I've known many people who have hit a deer when it spontaneous…

Perhaps most safety problems. But if you need to outrun an erupting volcano, a tsunami, or the police, slowing down won't really help you.

I think that this is a more realistic/relevant example of "slowing down or stopping is not always the safest action":

https://www.youtube.com/watch?v=eWuK-fi-D_w

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

#142
post #54
post #36

Earlier quoted context omitted.

Perhaps San Francisco rain is solved, but I doubt the downpours we get in the South East are solved. Zero visibility is just one thing, how about hydroplaning when there is over 1" of standing water on the road because it's coming down faster than gravity can drain it away? Or spotting that your lane is fine but the opposite one is flooded so that car coming the opposite direction is going to have to borrow your lane…

Those conditions sound like you wouldn't be driving. So, solved. Pull over and stop

You have to pull over when it happens. Sometimes those southeast flash flood rains go from bad to opaque in an instant. Depending on the road you may not have enough of a shoulder to pull over, and any other driver will only be able to see you at 5-10 feet away maximum and (initially) going 45-60mph. Not ending up in a ditch can be difficult.

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

#143
post #133
post #111

Earlier quoted context omitted.

> safely I've seen people do all sorts of foolish things. When the rain is so hard that I can't see more than 15 feet, I pull over and stop.

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.

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

#144

I don’t see the fact that self driving cars can’t drive in all conditions as a reason not to still want one that can drive on the freeway in good weather. A lot of people spend a large portion of their driving time on freeways so if we could solve that to a standard of safety that is acceptable, that would be a huge win in my book. As soon as it starts raining, have the system disengage and I’ll take over. It seems t…

Safely disengaging is a pretty critical feature that we haven't heard much about. We know that Tesla's don't do it, and that Uber's don't do it, and waymo says in their tests, humans aren't capable of reengaging in a short time frame. In a lot of the most vexing cases, I would guess the time between everything is fine and the computer can't find amy safe options is quite short.

A self driving car that can't drive in all conditions should be positioned instead as a driver assistant that can't assist in all conditions. If the expectation is that the human driver is doing all the work, but sometimes the computer will help keep the lane, or with emergency braking, it's OK for that to not happen in rain or snow -- it was always the human driver's responsibility, the computer will help when it can.

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

#145
post #54
post #36

Earlier quoted context omitted.

Perhaps San Francisco rain is solved, but I doubt the downpours we get in the South East are solved. Zero visibility is just one thing, how about hydroplaning when there is over 1" of standing water on the road because it's coming down faster than gravity can drain it away? Or spotting that your lane is fine but the opposite one is flooded so that car coming the opposite direction is going to have to borrow your lane…

Those conditions sound like you wouldn't be driving. So, solved. Pull over and stop

I’d recommend visiting Finland. In these parts, there’s basically 3 months of optimal visibility. The rest is fog, rain, snow, sleet and road conditions that would shut down most of US. Yet people drive and do so safely. “What people can do” is a bit different from “what an average us driver can be expected to do”

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

#146
post #54

Earlier quoted context omitted.

Those conditions sound like you wouldn't be driving. So, solved. Pull over and stop

I’d recommend visiting Finland. In these parts, there’s basically 3 months of optimal visibility. The rest is fog, rain, snow, sleet and road conditions that would shut down most of US. Yet people drive and do so safely. “What people can do” is a bit different from “what an average us driver can be expected to do”

Doesn’t findland have a higher vehicle fatality rate than other nations?

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

#147

Earlier quoted context omitted.

I'm still curious about street signs. Can any self driving car read parking signs because it's not like there is some API for when/where you can park or drop passengers off.

I wouldn't be surprised if something like that existed now or in the near future. There are APIs for speed limit, it would make sense to have them for other traffic rules as well.

My naive view is that a simple RFID standardization would solve that.

Together with some regulations, of course. Though, this already has to be regulated. Not just anyone can put up a "only park during certain times" sign. (Right?)

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

#148
post #114
post #14

> Waymo, widely seen as leading the self-driving vanguard, says it has made progress teaching its software to better filter out “noise” from precipitation. The last Waymo leak claims that it is more than just 'progress', but that 'rain is solved', incidentally: https://thelastdriverlicenseholder.com/2018/09/14/waymo-plan...

From that article: > Also snow seems to be solvable, as there will probably similar patterns that the sensors get in their signals. Real snow is not just a software problem. Fancy rear facing sensors near bumper? I hope they function through a couple inches of frozen muddy spray. Front windshield? Sometimes needs scraping. Lidar on roof? Does it work through the big heap of snow on it?

I have a hunch that as cars get more sophisticated, they also need to have more sophisticated treatment. The reason I leave my car out to have a foot of snow on it is because it works anyway. If the car wouldn't actually work without the windscreen clear and sensors ice-free, I would either use a garage every night or have a less sophisticated car. And I suspect that once autonomous vehicles get good enough, people will actually want to ride in them - so will keep them indoors more than they do with their normal cars. Effctively then, the rugged cars have become machines we treat like fragile fighter jets.

Still, for a wide range of weather conditions the autonomous car will just say a big NOPE and refuse to drive anywhere. Which is why it must always have manual controls. The autonomous car that could take me to the city through the worse conditions I experience every winter, won't have to take me in it because that car is probably clever enough to do my job as a software developer too.

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

#149
post #114

Earlier quoted context omitted.

From that article: > Also snow seems to be solvable, as there will probably similar patterns that the sensors get in their signals. Real snow is not just a software problem. Fancy rear facing sensors near bumper? I hope they function through a couple inches of frozen muddy spray. Front windshield? Sometimes needs scraping. Lidar on roof? Does it work through the big heap of snow on it?

As it is now, sometimes ice needs to be scraped off the windshield before you can drive. It may be the same with the cars external sensors.

Also mud spray and other road debris covering sensors can be solved with hardware (wipers, sprayers etc.) so it's probably not at the top of Waymo's long list of difficulties.

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

#150
post #131

Earlier quoted context omitted.

> hydroplaning when there is over 1" of standing water on the road because it's coming down faster than gravity can drain it away? I'd say that's pretty calculable, and has a solution, slow down to a speed that the tires can shed water. Perhaps most telling about your qualification is the misplaced risk; the light precipitation with a little oil slick is likely more dangerous, mostly because you don't slow down for i…

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.

Post reply on HN