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

181–190 of 340 posts

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

#181

Post by jakobegger »

umichguy wrote: post #174
bronco21016 wrote: post #119

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 traffi…

"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." Yep. As a Michigander, I totally agree. Y…

Humans are good at improvising. Not using all the lanes when the lane markings are covered by snow, and the road is slippery, sounds like a reasonable strategy. And nobody ever told us that's what we should do.

With autonomous vehicles, you need to plan every situation in advance. Our current AI technologies can't improvise. It seems to me that current AI is basically just a decision tree with some neural networks sprinkled on top.

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

#182

Post by LandR »

emodendroket wrote: post #63
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?

Yeah I don't think most bosses in Boston are going to let you stay home every time it snows.

The last 2 jobs I've had we've always been told pretty explicitly if the roads are bad with snow DO NOT try to get to work.

Hell, I've been told I've not even to walk to work when it's snowing. ALthough saying that the last time it snowed here badly, I tried to walk to shop and fell over twice. Maybe my employer just knows me too well...

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

#183

Post by usrusr »

toast0 wrote: post #144
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…

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…

Even full autonomy, but restricted to very limited intervals could make sense as a compromise. E.g. up to five minutes of hands-off (and eyes off) per hour or something like that. It looks weird at first, because hey, if the car can drive itself for five minutes, why can't it drive itself for five hours? But only at first glance. I believe that it makes a lot of difference which is the regular case and which is the exceptional. Humans would be terrible at idling most of the time to occasionally take over, but computers can be just as attentive waiting to take over as while actually driving.

Also, that time-limited "hold the wheel" mode would typically be engaged exactly for those times when the human driver is not at their best (tempted by communication devices, tempted by the food basket or just wrestling with navigation), so achieving better than human would be relatively easy.

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

#184

Post by pathseeker »

xapata wrote: post #111
Niten wrote: post #108

Earlier quoted context omitted.

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.

Nobody said anything about 15 feet but you. If you're pulling over in a normal heavy downpour with 500 ft of visibility, you're less safe than the people who continue to drive. Being pulled over to the side of any high-speed road is an unsafe condition that should be avoided.

Self-driving cars would be putting lives at risk if they just pulled over and shutdown on every summer thunderstorm.

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

#185

Post by wongarsu »

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.

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

#186

Post by jpindar »

gugagore wrote: post #73
cal5k wrote: post #41

Earlier quoted context omitted.

It seems plausible to me that LIDAR + radar could eventually outperform humans in white-out conditions. Here's an interesting bit of research on filtering out snow noise from a LIDAR point cloud: http://wavelab.uwaterloo.ca/?weblizar_portfolio=real-time-fi...

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.

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

#187

Post by Piskvorrr »

jakeogh wrote: post #170
mortehu wrote: post #64

Earlier quoted context omitted.

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

Unscientific test. Give the human individual brake control (I can think of simple analog systems to do it). I learned to drive on ice covered dirt roads, many times I would have liked to have the ability to asymmetrically brake. A simple 2nd order gimble would be awesome. Having a single symmetric pedal dumbs it down way too much to make a pre-programmed car vs human comparison. Same thing goes for torque distributio…

A mind-machine interface would be probably appropriate there - I can't imagine a physical interface for this which could be operated by anyone except for an octopus (but I don't see many octopi driving anyway).

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

#188

Post by marvin »

njarboe wrote: post #30
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…

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?

This is a very locational consideration. In areas that regularly have snow and ice, everyone will have winter tires on their cars, studded if icing conditions are expected, or even snow chains, and a big crew of snowplow operators will keep the roads relatively clear of snow at all times. Starting with salting the roads in preparation for cold weather, and then sending out the crews the moment there is a few millimeters of snow on the road.

I have never experienced a "snow day", although there have been days with problematic traffic conditions due to snow. (Usually due to an experienced or unprepared driver going off the road on the first day of snow).

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

#189

Post by marvin »

semi-extrinsic wrote: post #166
kasey_junk wrote: post #99

Earlier quoted context omitted.

In most places that have snow removal equipment “snow days” are actually called more frequently for cold. Leaving kids out in the cold is the issue. Driving in sbasic snow is a solved problem for humans in much of the world.

> Leaving kids out in the cold is the issue. I live in Norway and beg to differ. We see temperatures down to -40 C in winter, and the kids love it. We don't have "snow days", it's literally not a thing here. All you need is proper clothing, some seal fat for rubbing on your face, and cold weather experience among the adults (checking the kids faces for warning signs of frostbite, etc.). 95% of Norwegian babies and to…

I was baptised in -40 C weather. The temperature inside the church was just above freezing. My parents did take steps to ensure I was safely warm when outside, but there was no question of staying home.

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

#190

Post by ghaff »

jakobegger wrote: post #181
umichguy wrote: post #174

Earlier quoted context omitted.

"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." Yep. As a Michigander, I totally agree. Y…

Humans are good at improvising. Not using all the lanes when the lane markings are covered by snow, and the road is slippery, sounds like a reasonable strategy. And nobody ever told us that's what we should do. With autonomous vehicles, you need to plan every situation in advance. Our current AI technologies can't improvise. It seems to me that current AI is basically just a decision tree with some neural networks sp…

More like decision tree/rules engine with pattern recognizing neural networks underneath. You detect features and then take largely pre-programmed actions based on those features.
Post reply on HN