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

California suspends Cruise's autonomous vehicle deployment

reuters.com

Post reply on HN
Print view View original

861–870 of 1001 posts

Re: California suspends Cruise's autonomous vehicle deployment

#861

Post by phatskat »

spaced-out wrote: post #220
mariusmg wrote: post #181

Earlier quoted context omitted.

>This looks like Cruise's fault Imagine having to write the code that "detects" if a pedestrain is caught underneath the car

That's not hard for me to imagine. Now that I think about it, it should probably be standard for autonomous cars -- if there's an accident or something unexpected it should pull over, unless it can't reach the side of the road without hitting something or someone is trapped under the car.

> it should pull over, unless it can't reach the side of the road without hitting something or someone is trapped under the car.

Or…insert how many other edge cases? There are plenty of scenarios where it shouldn’t pull over, aren’t there? Training the myriad unique situations and proper responses just feels untenable, at least with current technology.

Re: California suspends Cruise's autonomous vehicle deployment

#862

Post by blub »

londons_explore wrote: post #589
choppaface wrote: post #354

Earlier quoted context omitted.

I’ve been nearly hit by a Waymo as a pedestrian when the thing could see me well before it passed. I hate that they use giant SUVs, really inappropriate car for small city streets even if people love SUVs.

If this ever happens to you or anyone else here, drop them a message with the date/time/place that it happened, and they will watch the footage and probably adjust stuff to not be scary in the future. Without human feedback, it's really hard to program a machine to understand "scary", even if the machine has calculated that it won't hit you. https://waymo.com/contact/ is the place to go.

You’re subtly gaslighting the parent poster by implying the car couldn’t have hit them and that it was just being “scary”.

Re: California suspends Cruise's autonomous vehicle deployment

#863

Post by serf »

stouset wrote: post #543
olex wrote: post #351

Earlier quoted context omitted.

That metric is tracked indirectly, by the lower number of accidents that AVs are involved in per distance travelled compared to human-driven vehicles.

Although things are changing, the overwhelming majority of AV miles are generally-safer miles on protected highways. And yet their statistics are typically compared against vehicle miles on all road types. Further, most AVs explicitly disengage when they encounter situations beyond their understanding. So again, we’re selecting AV statistics based on generally favorable conditions, but we don’t track human-operated m…

>Further, most AVs explicitly disengage when they encounter situations beyond their understanding

the bigger problem here is that the machine may not realize it isn't fully understanding the situation; I think that's the more common situation : a computer situational model doesn't match reality, but the machine has the confidence in perception to proceed, producing dangerous effects.

Re: California suspends Cruise's autonomous vehicle deployment

#864

Post by thorncorona »

oceanplexian wrote: post #845
gerdesj wrote: post #654

Earlier quoted context omitted.

Good grief, two skateboarders lives saved by a Waymo in two consecutive comments. A couple of weeks ago I came across a biker partially lying in the road, trapped by his bike. I parked my van at an angle, so if it was hit from behind it should roll past him. I jumped out and performed an assessment (I'm a qualified, OK: certificated first aider). I diagnosed "pissed" and ascertained he was unharmed. We got his bike i…

> I'm not sure a machine would have noticed an odd lump next to a lamppost, with a civic rubbish bin next to it, in the rain. As opposed to what? You don’t have RADAR, or LIDAR, or echolocation, or any other way to “detect” a person in the road. You have human vision. This is the idea behind Tesla FSD. If human vision is good enough, computer vision is good enough. We have cameras that can approximate human vision. A…

tesla vision doesn’t have an agi behind it though lol.

and why gimp ourselves. if we had an extra sense to navigate with we would 100% be using it.

Re: California suspends Cruise's autonomous vehicle deployment

#865

Post by askvictor »

KKKKkkkk1 wrote: post #860
FireBeyond wrote: post #459

Earlier quoted context omitted.

> And further, I have to presume Cruise and the others have a bay of human pilots that are called-on to deal with difficult situations. And then there's a momentary thought of this, and then I think how bad/hard it would be. Sitting there in a "call center", "Ding!" and you're suddenly thrown in to a car mid-collision, needing to take instant surveying of the situation (like "there's someone partly trapped under the…

By the time you're paged to handle the situation, the pedestrian is already trapped under the vehicle and you cannot see her because the car does not have an under-the-vehicle camera. So the only way you can handle this case is to rewind and review what happened before the collision and respond only then. Considering that the speed with which you react can be a matter of life and death, I don't see a satisfactory sol…

Why not have under-the-vehicle cameras and sensors?

Re: California suspends Cruise's autonomous vehicle deployment

#866

Post by seagullriffic »

pie420 wrote: post #380
seagullriffic wrote: post #226

Earlier quoted context omitted.

This is such a poor use of numbers to prove a point. Any unsafe car - one - could potentially end multiple lives. Therefore, one unsafe car is unacceptable. Look up "Vision Zero". It's possible, and should be expected from our town planners, vehicle manufacturers, and drivers.

Vision Zero is literally the least effective program out there. Almost every metric they track has gotten worse in the past 5 years

Why blame Vision Zero for the metrics getting worse? Unless you're aware of places where all its recommendations are implemented in full, and enforced?

Re: California suspends Cruise's autonomous vehicle deployment

#867

Post by askvictor »

alooPotato wrote: post #379
paxys wrote: post #310

I had an epiphany about self driving recently late at night on the streets of San Francisco. It was a somewhat deserted part of town, and the roads were empty. There was a lone Cruise car chugging along and constantly stopping at red lights. The signals were so badly optimized that the car would be the only one waiting at a completely empty intersection for minutes at a time, only to be stopped again at the next one,…

To have the city planning work correctly you kind of need participation from the cars. I.e. if the traffic light infra structure knew the destination of every car it could do things more globally optimal. So in that sense, driverless cars will actually help because of kind of nuanced reason. My guess is that there will only be a small number of driverless car companies (tesla, waymo, cruise, apple, etc) and it'll be…

> To have the city planning work correctly you kind of need participation from the cars

Perhaps for the optimum solution, but you can get a _lot_ better (than things are at the moment) without that. There are plenty of cities that use sensors and cameras to adjust traffic light timing throughout the day, and have done for some time (In the 90s I studied the system used in Sydney, which had already been in existence for some time then). But these things cost money.

Also, you don't need driverless cars for destination data - anyone using Google/Apple Maps/Waze, or even any recent car's inbuilt nav system can provide this.

And I reckon that even with the optimal solution in this regard, you'll still end up with traffic jams, as individual cars take a lot of space. Start thinking in terms of mass transit, cycling, and city planning to allow walking to the shops.

Re: California suspends Cruise's autonomous vehicle deployment

#868

Post by rgmerk »

ClumsyPilot wrote: post #746
ethbr1 wrote: post #539

Earlier quoted context omitted.

One huge advantage sensor-equiped vehicles have is knowing velocity and acceleration of traffic around them. Human drivers are often conservative because they don't know the speed/acceleration of a potentially colliding vehicle. We look at something and estimate (How fast? Speeding up or slowing down?), but we don't know . If you could put an actual number on it, I think you could drive a lot more "aggressively" and…

but they don't know capabilities orf vehicles, say a vespa vs some sports bike. While humans do and will behave differently around these vehicles.

That seems like pretty weak sauce.

If your sensors can distinguish a Vespa from a sports bike reliably, compared to all the other things that an autonomous vehicle has to cope with programming it to treat those two as different categories of vehicle shouldn’t be particularly hard.

Re: California suspends Cruise's autonomous vehicle deployment

#869

Post by _2d30 »

dopamean wrote: post #535
pie420 wrote: post #361

Earlier quoted context omitted.

The comment you are replying to starts with "My day-to-day experience..."

Yes and then go on to say something they could not possibly know for a fact. In my day to day experience Cruise cars are, mile for mile, far worse than human drivers . How could I possibly know that? I've had a couple bad encounters with Cruise cars but I've had countless encounters with human drivers in between all those. How could either of us possibly know which one is better "mile for mile." It's a ridiculous thi…

Scene: dopamean and their partner get home from the grocery store with a trunk full of groceries. dopamean's partner knows dopamean has had a tough week at work and wants to do something nice for them.

dopamean's partner: "Hey dopamean, in my experience, the grocery bags full of canned goods are heavier than the ones full of chips. Let me take the heavier ones and you can take the lighter ones!"

dopamean: infuriated "How could you possibly know which bags are heavier? It's a ridiculous thing to say. By couching it with 'in my experience' you attempt to make it sound like you're just talking about your personal experience but then you go on to say something that sounds objective and _could_ be measured but wasn't! Did you weigh each bag to determine their objective heft? No!"

dopamean's partner: distraught "I'm so sorry, dopamean! I will never again share informed personal experience with you about objective matters without first conducting a rigorous measurement program beforehand to confirm my priors. Thank you for showing me just how much better I can be! I can tell you're so much smarter than me and I can learn so much from you."

dopamean: angrier than anyone has ever been "Oh 'I'm so much smarter than you' am I? You fail yet again! Did you measure my IQ, did you measure yours?? Have you learned nothing!? I could easily be 3 or even 4 standard deviations below your IQ!"

Fin.

Re: California suspends Cruise's autonomous vehicle deployment

#870

Post by hoseja »

blub wrote: post #862
londons_explore wrote: post #589

Earlier quoted context omitted.

If this ever happens to you or anyone else here, drop them a message with the date/time/place that it happened, and they will watch the footage and probably adjust stuff to not be scary in the future. Without human feedback, it's really hard to program a machine to understand "scary", even if the machine has calculated that it won't hit you. https://waymo.com/contact/ is the place to go.

You’re subtly gaslighting the parent poster by implying the car couldn’t have hit them and that it was just being “scary”.

Well, has it hit them? Fully automated intersection would be very "scary" for a slow meatbag, yet without accidents.
Post reply on HN