Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Let’s Talk About Self-Driving Cars

medium.com

Post reply on HN
Print view View original

211–220 of 341 posts

Re: Let’s Talk About Self-Driving Cars

#211

Post by Gargoyle »

saosebastiao wrote: post #174
nostrademons wrote: post #152

Earlier quoted context omitted.

Dunno if you live in Silicon Valley, but here in the Mountain View / Sunnyvale area, they absolutely do drive the same miles that humans drive, in the same conditions. There is about the same chance that you'll see a WayMo self-driving car on your trip as that you'll see a VW Bug, perhaps slightly higher. There's a significantly higher chance than seeing a Tesla or McLaren, even though both of those marques are quite…

By virtue of the typical working hours of engineers alone, they are unlikely to drive in the same conditions, roads, and traffic as normal drivers. Their operating hours skew heavily towards driving in city traffic during non rush hours. They skew heavily away from driving at night, during rush hour, during lunch times, and during extreme weather events. I would also feel comfortable assuming that even if they put an…

>I would also feel comfortable assuming that even if they put an effort into driving at similar times as other people, they would still skew away from scenarios that engineers find boring. Good luck getting them to drive in 2mph stop and go on 880 or 101 during rush hour.

If you don't know their actual testing regimes, you should probably avoid assuming they ignore obvious test cases.

Re: Let’s Talk About Self-Driving Cars

#212

Post by sytse »

MR4D wrote: post #99
CPLX wrote: post #19

I find it odd the way people talk about moving through the levels sequentially without really acknowledging there's a massive phase change that happens somewhere between level two and four, where a self-driving car could easily be way more dangerous than the average human driver. That comes as soon as you have a situation where the automation has to be able to handle all foreseeable scenarios without failing because…

Imagine some drunk guy hops into his car in bad weather. He taps the auto-cruise button and then passes out. Snow, rain, construction, - something - hinders the ride somewhere along the way home. Car cannot process the issue correctly, and slows to a stop, alerting the driver. Driver, being sound asleep, cannot hear the annoying alert tone. Alert continues, and possibly after some time, alerts authorities of it's dis…

It would be interesting to allow tele operations in this kind of scenario so the drunk, sleeping, underage, and disabled can benefit from self driving cars.

Re: Let’s Talk About Self-Driving Cars

#213

Post by sbov »

Eridrus wrote: post #55
tyingq wrote: post #28

Earlier quoted context omitted.

One I thought of when I encountered it the other day... Driving through a red light when it's obvious something's gone wrong with the traffic signal, and it's stuck on red. Harder than it seems at first, because other drivers at the intersection seem to make up the rules interactively, with you, via facial expressions and hand waving. There's also a fair amount of variables, like looking sideways to see if the cross…

A broken traffic light seems no different than a 4 way stop once you've realised it's broken, and I'm pretty sure Waymo can handle those already.

In California most lights have sensors, and the sensors themselves can break/not be properly calibrated. When you happen across this that means is certain lights will always be green, and others will always be red.

It's mostly a problem with motorcycles, and I've had to go through my fair share of red lights late at night when no one was around, but I've also (rarely) had a problem with a car.

Re: Let’s Talk About Self-Driving Cars

#214

Post by Animats »

CPLX wrote: post #19

I find it odd the way people talk about moving through the levels sequentially without really acknowledging there's a massive phase change that happens somewhere between level two and four, where a self-driving car could easily be way more dangerous than the average human driver. That comes as soon as you have a situation where the automation has to be able to handle all foreseeable scenarios without failing because…

The big change is between levels 2 and 3. That changes who's responsible. At level 2, the driver is responsible for accidents; at level 3, the manufacturer is. California and Michigan have already enacted that into law, that's what NHTSA recommends, Volvo's CEO publicly endorses that, and the big US automakers accept it. Tesla finally accepts it. Uber is still whining, but that's Uber.

Volvo's is starting a 100 vehicle test in one city in Sweden. Automation is only available on some major roads. The driver is not required to pay attention in automatic mode. There's a progress bar - minutes until the end of automatic driving. There are previously located points at the end of automatic driving regions where the vehicle can pull over and stop, should the driver not take over when requested. So that's what entry level full autonomy looks like. That's a good level 3. Those go on the road any day now; the vehicles have been built and tested, and the first of the 100 drivers, who are car purchasers, not Volvo employees, have already been chosen.[1]

And yes, they work in snow. The test is in Gothenburg, Sweden; they have to work in snow.

[1] http://www.volvocars.com/intl/about/our-innovation-brands/in...

Re: Let’s Talk About Self-Driving Cars

#215

Post by jellicle »

coldtea wrote: post #150
MR4D wrote: post #99

Earlier quoted context omitted.

Imagine some drunk guy hops into his car in bad weather. He taps the auto-cruise button and then passes out. Snow, rain, construction, - something - hinders the ride somewhere along the way home. Car cannot process the issue correctly, and slows to a stop, alerting the driver. Driver, being sound asleep, cannot hear the annoying alert tone. Alert continues, and possibly after some time, alerts authorities of it's dis…

> I'll bet that in the near future (next decade or so), there will be rising incidents of traffic being blocked due to a stopped automated car who's driver is not responsive, but the computer couldn't handle some construction or weather, and went into fail-safe mode, simply slowing down and stopping (but not pulling over due to lack of space). Obviously "do not stop in the middle on the road" will be high on the prio…

Why would that be? Self-driving cars should want to stay on the road in all cases.

The edge of the road is soft, not well marked, contains rocks and nails and housepets. The road proper is hard, well-marked, and vehicles should want to stay there always.

Of course this will occasionally result in inconvenience for other drivers as vehicle 1 has been stationary for 25 minutes now as it applies a mandatory software service pack. But, oh well. That is THEIR problem. It's obviously maximal for MY vehicle to stay on the road at all times.

Re: Let’s Talk About Self-Driving Cars

#216

Post by nostrademons »

saosebastiao wrote: post #174
nostrademons wrote: post #152

Earlier quoted context omitted.

Dunno if you live in Silicon Valley, but here in the Mountain View / Sunnyvale area, they absolutely do drive the same miles that humans drive, in the same conditions. There is about the same chance that you'll see a WayMo self-driving car on your trip as that you'll see a VW Bug, perhaps slightly higher. There's a significantly higher chance than seeing a Tesla or McLaren, even though both of those marques are quite…

By virtue of the typical working hours of engineers alone, they are unlikely to drive in the same conditions, roads, and traffic as normal drivers. Their operating hours skew heavily towards driving in city traffic during non rush hours. They skew heavily away from driving at night, during rush hour, during lunch times, and during extreme weather events. I would also feel comfortable assuming that even if they put an…

I've personally seen them on the road at twilight (which is rush hour, by nature), during lunch time, and in pouring rain. They don't do highways yet, because most of the test vehicles are limited to 25mph for safety reasons (which is infuriating when you're stuck behind them in a 35mph zone). They do get plenty of practice at stop & go though.

Re: Let’s Talk About Self-Driving Cars

#217

Post by rhino369 »

bluGill wrote: post #37
CPLX wrote: post #19

I find it odd the way people talk about moving through the levels sequentially without really acknowledging there's a massive phase change that happens somewhere between level two and four, where a self-driving car could easily be way more dangerous than the average human driver. That comes as soon as you have a situation where the automation has to be able to handle all foreseeable scenarios without failing because…

Just remember that self driving cars do not have to be perfect, they just need to be better than humans. The use is at just over 1 death per million miles. If self driving cars can reach .5 they are better already. If the cars can detect the times they are bad and pull over (screw your appointment) that might be enough.

If I'm the government, I'm going to make sure they have to be better than humans with self driving co-pilot.

You also can't compare deaths per million miles if the self driving cars don't operate in dangerous conditions. You'd have to compare apple miles to apple miles and orange miles to orange miles. A lot of people die in car wrecks in bad conditions.

A car that only kills .5 people per million miles, but doesn't work in the rain, snow, dark, whatever, likely isn't safer than a person.

Re: Let’s Talk About Self-Driving Cars

#218

Post by jellicle »

stale2002 wrote: post #163
random_upvoter wrote: post #66

Earlier quoted context omitted.

When a piece of software crashes out of its model space, it becomes infinitely stupid. A drunk driver, while impaired, retains a level of understanding of the situation but a program has nothing to fall back on. I suspect that accidents with automated driving, while rare, will tend to be more severe. Think train wrecks.

Not really. If something goes wrong, 99.9% of the time, the solution is to slam on the brakes, and maybe swerve a little to avoid an immediate obstacle. If a self driving car only does this, it will be a way better driver than a human. Talking about weird edge cases misses the point. Edge case = slam on the brakes.

If something goes wrong, as we've seen with Tesla, the car tends to barrel full-speed into very solid obstacles.

Because, duh, something went wrong.

Human errors tend to be misjudging something and then getting into a situation that, due to physics, they can't quite get out of. So you can't quite stop the car in time and you hit the car in front of you at 15mph.

Car errors are going to be things like "I thought the tractor trailer was a billboard or a bird so I hit it at 60mph with no braking". Or "I lost all sensor data and got stuck in a loop so I drove off the bridge". It's a fundamentally different sort of error.

Re: Let’s Talk About Self-Driving Cars

#220

Post by jcranmer »

stale2002 wrote: post #163
random_upvoter wrote: post #66

Earlier quoted context omitted.

When a piece of software crashes out of its model space, it becomes infinitely stupid. A drunk driver, while impaired, retains a level of understanding of the situation but a program has nothing to fall back on. I suspect that accidents with automated driving, while rare, will tend to be more severe. Think train wrecks.

Not really. If something goes wrong, 99.9% of the time, the solution is to slam on the brakes, and maybe swerve a little to avoid an immediate obstacle. If a self driving car only does this, it will be a way better driver than a human. Talking about weird edge cases misses the point. Edge case = slam on the brakes.

Most of my driving (as in 90% by mileage) is on highways, and most of that is 70-mph rural highways. The first edge case I'd think of, totally not a weird edge case at all, is sudden 0-visibility fog banks at 70mph. If you think it is a good idea to slam on the brakes in such conditions, someone is likely to lose a life.
Post reply on HN