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

US probes Waymo robotaxis over school bus safety

yahoo.com

Post reply on HN
Print view View original

201–210 of 237 posts

Re: US probes Waymo robotaxis over school bus safety

#201

Post by krisoft »

tgv wrote: post #153
krisoft wrote: post #4

To be honest. I think this is one of the strengths of autonomous cars. With humans when they do this at max we can punish that individual. To increase population wide compliance we can do a safety awareness campaign, ramp up enforcement, ramp up the fines. But all of these cost a lot of money to do, take a while to have an effect, need to be repeated/kept up, and only help statistically. With a robot driver we can de…

> With a robot driver we can develop a fix and roll it out on all of them. Problem solved. I find that extremely optimistic. It's almost as if you've never developed software. I am curious about Waymo's testing. Even "adding a regression test" can't be simple. There is no well defined set of conditions and outputs. > Try to do that with human drivers. At least where I live, the number of cars and car-based trips keep…

> It's almost as if you've never developed software.

I do develop software. In fact I do develop self driving car software.

Yes it is not easy. Just talking about this particular case. Are the cars not remaining stationary because the legally prescribed behaviour is not coded down? Or are they going around school busses because the "is_school_bus" classifier or the "is_stop_arm_deployed" classifier having false negative issues? If we fix/implement those classifiers will we see issues caused by false positives? Will we cause issues where the vehicles suddenly stop when they think they see a stop arm but there isn't one actually? Will we cause issues if a bus deploys a stop arm as we are overtaking them? What about if they deploy the stop arm while we are 10 meter behind them? 20? 30? 40? 100?

And that's just one feature. How does this feature interact with other features? Will we block emergency vehicles sometimes? What should we do if a police person is signalling us to proceed, but the school bus's stop arm is stopping us? If we add this one more classifier will the GPU run out of vram? Will we cause thread thrashing? Surely not, unless we implement it wrong. In which case definitely. Did we implement it right? Do we have enough labeled data about stop arms of school buses? Is our sensor resolution good enough to see them far enough? Even in darkness? What about fog? Or blinding light? Do every state/country uses the same rules about school busses?

> I am curious about Waymo's testing

They do publish a lot. This one is nice overview but not too technical: https://downloads.ctfassets.net/sv23gofxcuiz/4gZ7ZUxd4SRj1D1...

Or if you want more juicy details read their papers: https://waymo.com/safety/research/

Re: US probes Waymo robotaxis over school bus safety

#202

Post by hyghjiyhu »

lawlessone wrote: post #61
bluGill wrote: post #19

Earlier quoted context omitted.

The first fines should be meaningless to the company. If the issue isn't fixed the fines should get higher and higher. If the company fixes one issue but there is a second discovered quickly we should assume they don't care about safety and the second issue should have a higher fine than the first even though it is unrelated. Companies (and people) have an obligation to do the right thing.

>The first fines should be meaningless to the company. Why?

The goal should be to make them appropriately cautious. Not careless but also not paralyzed by fear. Escalating fines have the property that they are self-tuning. They basically say "go ahead and try it! But if there are issues you have to fix them promptly"

Re: US probes Waymo robotaxis over school bus safety

#203

Post by BeFlatXIII »

terminalshort wrote: post #196
lotsofpulp wrote: post #72

Earlier quoted context omitted.

A) everyone is already constantly surveilled via mobile networks and license plate readers, so surveillance is a moot point. We might as well get something out of it. B) the system can be setup to purge and/or record only at relevant times or during infractions

That's kind of like justifying invading a country by saying "we have this big military so we might as well get something out of it."

"If you have a big gun, shoot it." (a.k.a. how the Great War started)

Re: US probes Waymo robotaxis over school bus safety

#204

Post by BeFlatXIII »

hamdingers wrote: post #65
kjkjadksj wrote: post #37

Earlier quoted context omitted.

“Wasn’t me in the car”

"Don't care, car is registered to you, pay up" This is only an issue because traffic code violations are treated like criminal acts instead of... code violations. We don't have this issue with parking tickets, there's no reason we should have it with automated red light and school bus cameras.

> "Don't care, car is registered to you, pay up"

Answers like this are what drives the populace to support domestic terrorism.

Re: US probes Waymo robotaxis over school bus safety

#205

Post by inglor_cz »

sdenton4 wrote: post #191
inglor_cz wrote: post #160

Earlier quoted context omitted.

This is a tradeoff, in which the original case might have been the less dangerous one. Autonomous fleets have a major potential flaw too, in form of a malicious hacker gaining control over multiple vehicles at once and wreaking havoc. Imagine if every model XY suddenly got a malicious OTA update and started actively chasing pedestrians.

Hm, so you would put a hypothetical scenario on the same footing as thousands of actual deaths caused by drunk drivers each year? 30% of us road fatalities involve a drunk driver each year... I seriously doubt that the "mass takeover and murder" scenario would ever actually happen, and further doubt that it would cause anywhere near 10k deaths if it did occur.

"I seriously doubt that the "mass takeover and murder" scenario would ever actually happen"

OK, so you are optimistic. My own specialization is encryption/security, so I am not. State actors can do such things, too, and we've already had a small wave of classical physical-world sabotages in Europe that everyone suspects Russia of.

"further doubt that it would cause anywhere near 10k deaths"

This is something I can agree upon, but you have to take into account that human societies don't work on a purely arithmetic/statistical basis. Mass casualty events have their own political and cultural gravitas, doubly so if they were intentional.

Sinking of the Titanic shocked the whole world and it is still a frequent subject for artists 100 years later, even though 1500 deaths aren't objectively that many. I don't doubt that way more than 1500 people drowned in individual accidents worldwide in April 1912 alone, but the general public didn't care about those deaths.

And a terrorist attack with merely 3000 dead put the US on a war footing for more than a decade and made it spend a trillion dollars on military campaigns, even though drunk American drivers manage the same carnage in five months or so.

Re: US probes Waymo robotaxis over school bus safety

#206

Post by DangitBobby »

spike021 wrote: post #151
DangitBobby wrote: post #135

Earlier quoted context omitted.

Lots of people make this mistake around school buses. It's probably time for a different system if we are worried about children's safety.

Sounds more like a testing problem to me. Honestly I can't even remember if this particular rule was on the license exam when I took it. I know it because I put more care into remembering driving laws but many people don't.

Possibly an occasional refresher would help. I think it's just a weird thing to have. A roving stop sign that appears and disappears conditionally is going to have some people not see it (people accidentally run stationary stop signs on occasion), especially if you don't encounter school buses often. It's been maybe a decade since I needed to stop for one myself, I honestly cannot remember the last time.

Re: US probes Waymo robotaxis over school bus safety

#207

Post by DangitBobby »

wiether wrote: post #162
DangitBobby wrote: post #135

Earlier quoted context omitted.

Lots of people make this mistake around school buses. It's probably time for a different system if we are worried about children's safety.

We have some nice initiatives here. Either completely removing cars from streets near schools, or blocking cars when children are coming or leaving school. https://fr.wikipedia.org/wiki/Rues_aux_%C3%A9coles_%C3%A0_Pa...

The issue in the US is not about safety near schools. School buses often have to go pretty far to drop evyone off, so most of their stops are not near the school. For route optimization they'll drop kids off on the opposite side of the road from where they need to be, not at a bus stop and not anywhere near a crosswalk. Also kids in the US tend to not be very mindful of how dangerous the road can be, so they are liable to run into the street unpredictably. To make sure kids don't get hit by a car that didn't see them, when stopping a school bus deploys a stop sign from its side that all drivers going either direction on the road must abide by (usually, there are exceptions, which makes matters worse). Drivers occasionally accidentally run these stop signs and very rarely intentionally run them.

Re: US probes Waymo robotaxis over school bus safety

#208

Post by DangitBobby »

SoftTalker wrote: post #54

"approached the school bus from an angle where the flashing lights and stop sign were not visible" I call bullshit on that. Yes the stop sign is only on the left side but the flashing lights are on all four corners of the bus. You'd need to be approaching the side of the bus from a direct right angle to not see the flashing lights.

Nah, if you want people to stop reliably the stop sign needs to be visible from all directions you care about. Just add it to the list of reasons why the roving random stop sign deployment solution for school buses is a bad one.

Re: US probes Waymo robotaxis over school bus safety

#209

Post by JumpCrisscross »

Spooky23 wrote: post #182
JumpCrisscross wrote: post #143

Earlier quoted context omitted.

> ultimately self driving services will have political power to cap their liability You're fighting an objectively safer future on the basis of a hypothetical? Also, we already have capped liability with driving: uninsured and underinsured drivers.

The real cap is the operator ultimately is accountable. When a software defect kills a bunch of people, the robot operator’s owners will subject to a way lower level of liability. Airlines have international treaties that do this. An objectively safer future is common carriers operating mass transit. Robot taxi will creating a monster that will price out private ownership in the long term. Objectively safer remains t…

> real cap is the operator ultimately is accountable

Which is in practice lower than what a large operator would pay, particularly if they also write the software.

> will require a nationwide government regulatory body

It doesn’t require any such thing. That would be nice. But states are more than capable of regulating their roads.

Re: US probes Waymo robotaxis over school bus safety

#210

Post by bloppe »

ozgrakkurt wrote: post #180
atleastoptimal wrote: post #125

On net, Waymos are safer than human drivers. Really all that matters is deaths per passenger mile, and weighted far less, injury/crash per passenger mile. Waymos exceed human drivers on both metrics, thus it is reasonable to say that Waymos have reduced crashes compared to the equivalent average human driver covering the same distance. Mistakes like this are very rare, and when they do happen, they can be audited, an…

Taxi drivers or bus drivers are also much safer than regular people if you interpret it like that

Which is also true
Post reply on HN