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

11–20 of 340 posts

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

#11

Post by jefft255 »

munk-a wrote: post #8
SheinhardtWigCo wrote: post #6

Earlier quoted context omitted.

That is clearly not the case.

That clearly is the case, it was my experience growing up that even seasoned New England drivers couldn't take the weather seriously and ended up in a ditch on the side of the road.

That's not really a good point. When New England/Canada drivers drive through a snowstorm, the vast majority of them get to where they were going just fine.

In comparison, basically no self driving car could safely drive 100 ft during a snowstorm.

Getting self driving cars to be as good as humans during harsh weather (which is not that good I'll give you that) will take 10 years in my opinion (I say this as a grad student in mobile robotics).

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

#12

Post by trhway »

>For the local breed of unflappable seagulls—which can stop autonomous cars by simply standing on the street, unbothered by NuTonomy’s quiet electric cars—engineers programmed the machines to creep forward slightly to startle the birds.

seeing the fun my dog is having chasing the birds, i'd suggest that a Boston Dynamics dog would jump out of the car, scare the birds away, jump back (and continue to drive while watching electric sheep funny videos :)

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

#13

Post by rm_-rf_slash »

hooloovoo_zoo wrote: post #5

All the extra sensors that can be added to cars in addition to the suite of cameras make self-driving cars seem inevitable, yet no manufacturers appear to be close to bringing one to market.

The problem isn’t sensing, it’s decision-making.

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

#14

Post by gwern »

> 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...

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

#15

Post by ocdtrekkie »

musgrove wrote: post #4

Neither can most humans driving cars.

The self-driving car hype has failed to recognize that humans are, in fact, exceptionally good at driving cars. There are many car accidents, and many fatalies from car accidents, but a relatively small number considering the number of cars, the number of drivers, and the amount of miles driven, every single day across widely varying conditions worldwide. A large percentage of humans drive every single day, as routinely as getting up from bed, and for most of them, this does not have a bad result.

The idea that we can quantify all of the subtle little ways the human brain instinctively has gotten so good at driving cars is supreme arrogance.

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

#16

Post by dbcurtis »

poulsbohemian wrote: post #9
justtopost wrote: post #7

Earlier quoted context omitted.

The problem here, is that you are half-right. Its localized conditions. No country, much less worldwide, system can account for local anomolies. Where I learned to drive, most humans could 'see' black ice by predicting where water will pool, the recent weather, and subtle clues that abound, but are not easily expressable. Any out-of-town'er would surely be spun out or driving 10mph, white-knuckled, aghast at the "man…

I've often wondered how much of this is hubris or fear vs. physics. What I mean is - are people in say, icy and snowy climates actually better drivers, able to adjust to the conditions, or are they fooling themselves? Likewise, the person going exceptionally slow and cautiously - are they misjudging the actual risk of inclement weather, relative to an actual scientific judgement? It certainly feels like humans become…

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 overall for knowing how to handle ice? Probably not, but I might be the best person to do the driving under those conditions if everyone else in the car is from warmer climes.

I remember standing in line at Minneapolis rental car counter one night when it was snowing an inch an hour with 4 inches on the ground already. Agent to the guys in front of me: “There are chains in the trunk if you need them.” Customer with heavy southern accent: “Chains? What the heck are chains?” I wonder to this day if those guys made it to their hotel.

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

#17

Post by justtopost »

poulsbohemian wrote: post #9
justtopost wrote: post #7

Earlier quoted context omitted.

The problem here, is that you are half-right. Its localized conditions. No country, much less worldwide, system can account for local anomolies. Where I learned to drive, most humans could 'see' black ice by predicting where water will pool, the recent weather, and subtle clues that abound, but are not easily expressable. Any out-of-town'er would surely be spun out or driving 10mph, white-knuckled, aghast at the "man…

I've often wondered how much of this is hubris or fear vs. physics. What I mean is - are people in say, icy and snowy climates actually better drivers, able to adjust to the conditions, or are they fooling themselves? Likewise, the person going exceptionally slow and cautiously - are they misjudging the actual risk of inclement weather, relative to an actual scientific judgement? It certainly feels like humans become…

I am confident it is both. As someone who races rallycross for fun, I am sure I am an exeption, but I am oft amazed by ordinary drivers every day when skiing.

One cannot discont the psychological factor of feeling 'in control' when the control decides if you or others might die.

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

#18

Post by kxrm »

rm_-rf_slash wrote: post #13
hooloovoo_zoo wrote: post #5

All the extra sensors that can be added to cars in addition to the suite of cameras make self-driving cars seem inevitable, yet no manufacturers appear to be close to bringing one to market.

The problem isn’t sensing, it’s decision-making.

The trolley problem is a tough one.

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

#19

Post by seibelj »

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.

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

#20

Post by vaughnegut »

As a Canadian, it's the snow that's made me skeptical of self-driving cars. Seeing how much they depend on road markings to navigate in traffic properly is completely impossible in winter. Until that's solved, there's a lot of places that just can't use them for a lot of the year.
Post reply on HN