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

191–200 of 340 posts

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

#191

Post by ghaff »

wool_gather wrote: post #60
mdhen wrote: post #54

Earlier quoted context omitted.

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

This; arguing that a computer can't drive safely in conditions where a human can't either isn't an argument against computer drivers. Just because humans sometimes get away with it doesn't make it a good idea.

It's not always possible to pull over. If it's snowing so heavily that driving has become dangerous there probably is no shoulder to pull over to, much less a shoulder you can safely pull over to. Source: I've been in these conditions. You do the best you can.

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

#192

Post by imtringued »

dasil003 wrote: post #89
romed wrote: post #82

Earlier quoted context omitted.

That Waymo has not solved left turning is not really a conclusion supported by that article. A supportable conclusion is that the impatient meatbags are angry that the Waymo van won't dangerously veer out into oncoming traffic.

LOL, yes, the meatbags. Waymo exists to serve Waymo's purpose, it is a higher entity beholden only to its funding source not to petty meatbag concerns.

Waymo's purpose is to not kill the meatbags. Unlike Uber, Waymo has been very successful at this. Also the claim was that the car cannot turn left on its own which is completely wrong. There is merely a very high safety margin so that the car will only drive when it is sure that no collision will occur.

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

#193

Post by ghaff »

nradov wrote: post #134
hef19898 wrote: post #123

Earlier quoted context omitted.

I'm by no means an expert for self driving cars or auto-pilots, so take it is just my personal impression. It seems that developers for self driving cars are dealing with a very different, and in some ways more difficult, environment than aircraft auto-pilots. While cars only have to deal with two dimensions instead of three and cars are still less complex machines compared to planes there are a lot more challenges.…

Dealing with failures is far more complex for aircraft. When a car gets a flat tire or suffers an engine failure the driver can just pull over and stop. But an autonomous aircraft carrying passengers or flying over populated areas would have to cope with broken sensors, uncontained engine failures, loss of cabin pressure, stuck control surfaces, etc.

>the driver can just pull over and stop

Yes, sometimes you can pull over and sometimes you just have to put the blinkers on, stop in the traffic lane, and hope for the best--even though it can be very dangerous. One challenge is that, with full autonomy, the vehicle needs to be able to very quickly deal with a once-in-10-years scenario in the least bad way--both for its occupants and for any other traffic on the road.

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

#194

Post by Piskvorrr »

jakeogh wrote: post #74
njarboe wrote: post #30

Earlier quoted context omitted.

Or most people. If it is actually blizzard conditions, one should have a very serious reason to be on the road. If not, stay at home instead of driving. Snow days are called for schools. Maybe work in general also?

Bad trend when limitations of pre-programmed cars become apparent; treat the humans as the bugs.

Even worse: it works. Jaywalking 2.0, here we come!

https://www.vox.com/2015/1/15/7551873/jaywalking-history

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

#195

Post by maxerickson »

Moru wrote: post #175
scj wrote: post #45

Earlier quoted context omitted.

> I'd rather share the road with a computer. Not version 1. Factoring in all these variables is going to be a lot of work for a non-universal feature. I have no doubt they'll be included some day, but I doubt it'll be day 1. EDIT: To be clear, I believe that dealing with ice and snow is an order of magnitude more difficult than driving under normal conditions. This is an 80-20 feature that many people won't need. I c…

I'm worried about the south europeans jumping into their self-driving car thinking they can come visit us in northern Sweden early spring (their season, still full winter here). How do you meassure how slippery the road is? How much wind from the side? Will the wind blow me off the road because it has been polished by the wind just after those trees end, next to the lake? Will the car know to stop before even going b…

Modern cars can drive at their traction limit already, it's a solved problem.

https://en.wikipedia.org/wiki/Traction_control_system

It's been a safety boon to have a computer limiting power to the wheels when they slip, humans are really bad at estimating how slippery the road is.

Estimating for the road ahead is a different problem, but there is data to feed into that estimate.

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

#196

Post by Piskvorrr »

grecy wrote: post #98
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 first cars ever couldn't drive in 100F+ heat, and wouldn't start below 0F. And even worse, there were virtually zero gas stations! Especially in rural areas! Does that mean they were useless? Absolutely not! Lately the mindset seems to be unless a product is all things to all people at all times then it's useless. In reality a product just has to fit a category really well and it will sell like hotcakes. Then it…

Sure. This is just pushback to the recent hype "it has full autonomy capabilities [small print: except not at all]". If the first cars had been marketed as "better in every aspect and in any conditions", you would have seen similar reactions.

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

#197

Post by imtringued »

grecy wrote: post #98
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 first cars ever couldn't drive in 100F+ heat, and wouldn't start below 0F. And even worse, there were virtually zero gas stations! Especially in rural areas! Does that mean they were useless? Absolutely not! Lately the mindset seems to be unless a product is all things to all people at all times then it's useless. In reality a product just has to fit a category really well and it will sell like hotcakes. Then it…

This reminds me of intel's optane. Yes they overhyped it and it doesn't perform 1000x faster than SSDs. But you have to consider that SSDs required decades of improvements to become viable and cheap. Even when Optane was a first generation product it was already better than SSDs in terms of latency and IOPS but despite that people thought it was a massive failure.

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

#198

Post by Moru »

maxerickson wrote: post #195
Moru wrote: post #175

Earlier quoted context omitted.

I'm worried about the south europeans jumping into their self-driving car thinking they can come visit us in northern Sweden early spring (their season, still full winter here). How do you meassure how slippery the road is? How much wind from the side? Will the wind blow me off the road because it has been polished by the wind just after those trees end, next to the lake? Will the car know to stop before even going b…

Modern cars can drive at their traction limit already, it's a solved problem. https://en.wikipedia.org/wiki/Traction_control_system It's been a safety boon to have a computer limiting power to the wheels when they slip, humans are really bad at estimating how slippery the road is. Estimating for the road ahead is a different problem, but there is data to feed into that estimate.

If you read the manual for the traction control it is full of big warnings on every page,'Does not cancel out physical laws'. It is not a solved problem, it can only do as best it can uphill until car does not have enough traction to continue upwards. At which point the car will slowly glide down or into the ditch.

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

#199

Post by Piskvorrr »

wongarsu wrote: post #185
vaughnegut wrote: post #20

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.

Waymo seems much less focused on road markings than Tesla and Uber, and instead more focused on the geometry problem of not hitting stuff. They are also in a great position to analyze summertime satellite images to get a better understanding of road markings. I'm optimistic that this is a very solvable problem for Waymo.

Solvable, indeed - in the Dartmouth-1956-workshop meaning of "solvable": there's as of yet an unknown amount of research to be done, and it looks reasonably complex to be hacked at by a dozen people over the summer. Therefore, a few man-centuries of research and development will surely bear fruit.

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

#200

Post by gugagore »

jpindar wrote: post #186
gugagore wrote: post #73

Earlier quoted context omitted.

But if snow occludes lane markings, which is what the parent was discussing, then no amount of sensing helps you see them, right? (You can have a map with lane markings and localize on that map, though)

Except that many times when the lines are invisible, new lanes form that are in a different location. So your map will not match up with what the rest of the traffic is doing.

I agree. I was just anticipating the common response to that challenge, or any other "static" perception challenge, which is "but there is a map"
Post reply on HN