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

111–120 of 340 posts

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

#111

Post by xapata »

Niten wrote: post #108
mdhen wrote: post #54

Earlier quoted context omitted.

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

It sounds like you've never lived in the southeast US? These conditions can occur on a daily basis in the summer, especially in Florida. "Pull over and stop" isn't realistic advice here. Humans can and do drive safely in these conditions, however, and it's a valid concern to point out that Waymo's West Coast-centric models might not yet be trained to handle these cases. (To be clear, I don't doubt that machines will…

> 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.

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

#112

Post by GCA10 »

mdhen wrote: post #54
athenot wrote: 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 grew up with that kind of summer rain in Illinois, too. After about five minutes of it, yes, a lot of (sane) drivers pull over. But it comes on very suddenly, and for the first two or three minutes, traffic flows continue.

If you're in the center lane and traffic is heavy on both sides of you, while your windshield (or camera) is overwhelmed with water, you need to keep moving with traffic for a bit -- or you get rear-ended.

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

#113

Post by planteen »

CamperBob2 wrote: post #106
grahamburger wrote: post #31

Earlier quoted context omitted.

This sounds like exactly the kind of job for a computer. I live in an area that gets a lot of snow. The only 'safe' things for a human to do in snowy, icy, wet conditions are: slow down (a lot), leave a lot more following distance, stay home. I talk to a lot of people who seem to think that they are able to drive at full speed in the snow and complain about all of the 'out of town' drivers who slow down the roads bec…

"Slow down" is not, contrary to popular belief, always the best advice. Slowing down too much in the snow is a good way to get stuck.

Yep the key to climbing a hill in snow is to keep your speed up so momentum carries you over slick spots. I've seen a slick hill look like a Tetris game with stuck cars in many different orientations.

It's the same with a muddy and wet 4WD road.

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

#114

Post by amluto »

gwern wrote: 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?

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

#115

Post by graycat »

clay_the_ripper wrote: post #81

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…

The edge cases are a show stopper: You are talking about something like "driver assist" or upgraded cruise control. Thing is, still need a human right there.

Much of the dream of self-driving is for no human driver there, for taxi cabs, school buses, 18 wheel trucks, local deliveries from pizza or Chinese carryout, USPS, UPS, or FedEx, etc. For that, for current technology, for current traffic, on current roads, there's no hope at all because the edge cases are way too common in practice (can't put up with mean time to destroying an 18 wheel truck of six months -- 5 million miles is more like it) and require full, wide awake, sober, mature human intelligence with full ability at reading, talking, understanding, natural language understanding, hand signals, flag signals, tough to read road signs, etc. Edge cases.

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

#116

Post by seibelj »

jryle70 wrote: post #56
seibelj wrote: post #19

I’ve taken downvotes from HN optimists for years about self driving cars. The slightest bit of criticism would have comments calling me an idiot 20 different ways. Then a single dead pedestrian changes all the news articles and the opinions change. We are a very, very long way away from self driving taxi cabs. What a total PR scam that was - but it did help valuations.

Not sure if you have read the article, but it's actually about a company called WaveSense who claims to have developed ground-penetrating radar that can greatly improve all weather autonomous driving. So yes, it's a daunting task but lot of people are working on it and progress is being made. I'd be interested to hear your counterargument.

I’m not an expert in self driving car engineering. I have some experience with ML but not in a significant professional way. What I have is a decade of professional experience building all kinds of software and a skeptical eye.

You have a problem that is unconstrained, with infinite variables, where even a simple mistake can have catastrophic outcomes. Society itself may object to self driving cars for a ton of reasons, from safety to simply driving like a grandma and slowing everything and everyone down. The cost to develop this technology, plus the added cost of hardware to each car, will be enormous and is not obviously a cost savings over a $15 per hour human. If the self driving car is doing anything other than getting from A to B, you still need a human (or a human-like robot) to handle the unloading / delivery / whatever at the end.

Now, I’ve worked at companies with extremely talented and intelligent engineers, and something as constrained and seemingly simple as making a login form can take a long time to perfect - and no lives are at risk! Just imagine the challenges and requirements for building self driving cars. New hardware, software, real-time processing and analysis of tons of data, all to drive split-second decisions that can kill people if done incorrectly.

Huge challenge - huge risks - huge money - uncertain payoff. This is not something that will appear suddenly. If there aren’t convoys of self driving trucks operating in desert highways overnight, where it’s dry and straight and flat and no one else is there, then we aren’t going to see city taxis for a very long time.

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

#117

Post by planteen »

gmadsen wrote: post #51
dbcurtis wrote: post #16

Earlier quoted context omitted.

I don’t think they are qualitatively “better drivers”. But they are more experienced at certain things. When I lived in Minnesota, I got lots of practice driving in snow and ice and rain. Now in NorCal, not so much :) Its a skill. You get better with practice. The person going slow probably just hasn’t had enough practice yet with the conditions. Going slow is probably a good choice for them. Am I a better driver ove…

I've always been curious what "skills" need to be practiced to drive in the snow. It isn't overly technical. Just don't accelerate or brake too fast and dont turn while you are doing either. If you feel the car start to wobble or fishtail a little, it means you are going too fast. Thats literally all I change, and I have done fine all my life

Fish tail doesn't necessarily mean you are going too fast. If you are cruising, it means let off the gas. Have you ever driven a rear wheel drive car on a packed road? You will fish tail when accelerating from a light or stop sign. You need to build some speed and ride the fish tail out.

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

#118

Post by semi-extrinsic »

mortehu wrote: post #64
scj wrote: post #24

Driving in dry / warm conditions is simple mechanics. Driving in snow and ice is an art. In snow and ice, variables that are typically constant or static become dynamic. Formally dynamic variables now become multi-variable equations. For example: travelling down a hill normally requires dynamically factoring for the extra speed due to the incline. Under blizzard conditions you have to factor ice/snow volume, as well…

Yet electronic stability control[1] works far better than human control on snow, wet roads, or ice. If you don't believe it, try an obstacle course on an ice track with and without it sometime (a required part of driver's ed in Norway). Example: https://youtu.be/hd5JMQr4qe0?t=56s https://en.wikipedia.org/wiki/Electronic_stability_control

ESP works magic because it can do things that a human physically isn't allowed to do, namely "stop this one wheel from spinning faster than the others".

Incidentally, if you've ever tried driving on snow/ice/mud in a 4x4 car with fully locking differentials, you have a completely mechanical solution that beats ESP.

And FWIW, Swedish insurance agency research pointed out last year that cars with permanent 4x4 and ESP were up to 40% more likely to get into severe accidents in bad conditions, because the driver does not get the "hey, this road is slippery, better slow down" experience, so they go too fast for the prevailing conditions.

http://feed.ne.cision.com/wpyfs/00/00/00/00/00/3E/5A/A2/wkr0...

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

#119

Post by bronco21016 »

Waymo’s Michigan testing facility is very close to my home. I’m really curious to see how they do on snowy pothole ridden roads in Michigan. I’ve seen very few of them on the road this summer but if there’s supposed to be heavy testing and validation going on perhaps we’ll see an army of them on the roads here soon.

I’m curious how self driving focused groups are solving lane detection and managing surrounding traffic on snow covered roads. It’s not uncommon for a multi lane highway to be completely covered with snow and multiple tracks for different ‘lanes’ that overlap. It’s also not uncommon to see cars just making their own lanes. This occurs even after the snow has stopped flying.

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

#120

Post by mediaman »

jefft255 wrote: post #83
Itsdijital wrote: post #77

Earlier quoted context omitted.

Trees don't refract and reflect light.

Of course they do. Airborne lidar usually works in the near infrared spectrum which is not absorbed by wood. It is however more absorbed by leaves which have a higher water content. My main point is: airborne lidar (which is what OP is referring to when talking about removing forests and keeping the ground) has multiple returns for one laser beam. Laser beams can have a radius of 1-2 meters or more when they hit the…

What would prevent using the same technique of only retaining the maximum Z direction return to tell the difference between a refracted rain drop and car bumper?

Perhaps it is that the rain drop refracts the beam to all sorts of other objects which can make it difficult to tell which actually has the longest Z-distance return?

Post reply on HN