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

Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

theinformation.com

Post reply on HN
Print view View original

151–160 of 196 posts

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#151

Post by jacques_chester »

snarf21 wrote: post #142
Animats wrote: post #54

That's useful info. I wonder where they had trouble with erratic steering. One Cruise video shows that where driving is alongside parked cars on a narrow street and the parking is irregular. The self driving vehicle is trying to stay in its half of the street unless absolutely necessary. Waymo still has to use "safety drivers". So far, nobody seems to have full self driving without "safety drivers". Which makes it us…

I firmly believe that autonomous taxis are 30 years away. The big benefit will be for long haul trucking. That will be here in 10 years or less. They will have special rest areas where the autonomous trucks will park. From there they will only drive on interstates for long distances. When there, they will park at similar special rest areas. Local drivers will then take over and do the more difficult driving. It could…

It's taken more than a decade to get to autonomous trains and autonomous mine trucks (Rio Tinto have sunk a lot of money into it), so I wouldn't hold my breath.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#152

Post by jacques_chester »

mdorazio wrote: post #2

Interesting analysis using comments/rider scores. 10% improvement over 6 months is actually pretty good, though. Even if that rate slows as trickier edge cases get handled, It still implies early 2020s for true driverless readiness in select locations. That's pretty much on track with overall predictions for the autonomous market.

If you get nagged to answer questions every time you give a 4/5 you eventually stop giving 4/5 and 5/5 everything because you just want to get on with your day.

The whole "if it's not amaaaaazing it's terrible" thing is idiotic.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#153

Post by pedrocr »

agent008t wrote: post #121
vntok wrote: post #90

Earlier quoted context omitted.

If you don't immediately see the incoming traffic in question, yes you will. Otherwise your self preservation rules will prevail and you won't budge. Note that self driving vehicles aren't different from humans in that respect, except they see much farther.

With self driving cars you have no idea what they would do when presented with an edge case they may have only seen very rarely before. With humans, you can in most cases assume the driver would do something reasonable, especially if there is enough time to think through the situation.

You must be driving in much better places than I do. Human drivers do incredibly unreasonable things even without edge cases.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#154

Post by treespace8 »

Animats wrote: post #54

That's useful info. I wonder where they had trouble with erratic steering. One Cruise video shows that where driving is alongside parked cars on a narrow street and the parking is irregular. The self driving vehicle is trying to stay in its half of the street unless absolutely necessary. Waymo still has to use "safety drivers". So far, nobody seems to have full self driving without "safety drivers". Which makes it us…

I know it's an out there theory but I believe the problem is much more fundamental. It's switching from an analog operator, to a digital one.

Pervious analog to digital transitions have been easier because we could afford to lose information. (IE Audio, from records to CDs.) It was just a matter of getting the digital sample small enough. Information was still lost, but not enough to matter.

But with driving, it matters. We can't digitize the world to a point where a computer can drive better than an alert trained human.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#155

Post by rimliu »

paxys wrote: post #57
moomin wrote: post #26

This might just be me, but it strikes me that the biggest problem self-driving cars has is that no-one actually needs them. Don’t get me wrong, you try to sell me a car that has the (fully capable) feature I’d definitely want it. But need it? Well, you’re not going to solve the problem of too many cars and the slow traffic that results with cars. It’d be hard to get special treatment for cars with a premium feature.…

I personally think there are very few things we need today more than self driving cars. Driving is one of the most dangerous things we willingly do in our daily lives. There is an insane amount of valuable space in cities devoted to roads and parking, which is all used inefficiently. Valuable time is wasted in commutes and traffic. Now imagine if every driver on the road followed all rules. Traffic flowed smoothly an…

Now imagine strong wind brought down a tree branch on the road. A strong rain crated a big puddle. Etc. There is a lot more to driving than just following the rules. And I do no see how self driving car reduce the need for roads. Or parking. And the time spend waiting for them to arrive can be significant.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#157

Post by wpietri »

nradov wrote: post #71
PhasmaFelis wrote: post #68

Earlier quoted context omitted.

I dunno, it's hard to imagine any safe way to drive a car in traffic via cell. I don't see how you could get all-round vision with acceptable resolution, frame rate, and latency. VR might solve the viewing angle, at least, but would greatly magnify the effect of frame rate/latency drops. You don't want your driver getting VR-sick five minutes in. And that's leaving aside reliability. A 99.9% solid connection is not n…

Right. What happens when a construction crew accidentally cuts the backhaul fiber for the local cellular tower? Or if the autonomous vehicle failure occurs in a tunnel with no cell service?

You'll note that Waymo is very much operating in a limited area. So I think the answer is: they don't offer service in an area that lacks good cell coverage.

Of course, it's still possible that the vehicle will somehow be out of communication when it encounters something it doesn't understand. A cell jammer, say. In which case, it'll do what it will do if it, say, detects engine trouble: it'll pull over and wait.

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#158

Post by wpietri »

vidarh wrote: post #76
PhasmaFelis wrote: post #68

Earlier quoted context omitted.

I dunno, it's hard to imagine any safe way to drive a car in traffic via cell. I don't see how you could get all-round vision with acceptable resolution, frame rate, and latency. VR might solve the viewing angle, at least, but would greatly magnify the effect of frame rate/latency drops. You don't want your driver getting VR-sick five minutes in. And that's leaving aside reliability. A 99.9% solid connection is not n…

I think you misunderstand. I agree that a safety driver being expected to be able to pay attention and being ready to take over at any moment isn't viable. But consider a point where the cars are good enough that the remaining risks are ones where they can show that they can tune the hazard detection so that it doesn't miss any potential hazard situations, but may occasionally be overly cautious, and that it can reli…

Exactly. For example, imagine a situation where a tree is down, blocking one direction of travel. Humans would very cautiously share the remaining road space. But a robot taxi would just stop and wait for the tree to move. At that point it summons a human who tells it what to do in broad terms (e.g., "the new lane is here" or "do a u-turn and follow this other route").

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#159

Post by tvladeck »

calcifer wrote: post #112
jessriedel wrote: post #98

Earlier quoted context omitted.

That phrase is just thrown in there to stoke the reader and create a story out of nothing. It indicates a lack of journalistic integrity.

> It indicates a lack of journalistic integrity. Or, the author is suggesting that public resources should be used for public, not private benefit?

Like when an individual drives to a store to get groceries?

Re: Waymo’s Backseat Drivers: Confidential Data Reveals Self-Driving Taxi Hurdles

#160

Post by zodiac »

pnutjam wrote: post #137
jrockway wrote: post #120

Earlier quoted context omitted.

How is someone driving to work in their private vehicle public benefit? The roads are for driving on, nothing more, nothing less.

Not true, the roads are for the use and benefit of citizens.

How about tax-paying non-citizen residents, tourists etc?
Post reply on HN