Let’s Talk About Self-Driving Cars • Hacker News Board

Re: Let’s Talk About Self-Driving Cars

#221

Post by Retric » Tue, Jan 10, 2017, 8:50 PM UTC

jellicle wrote: post #218

stale2002 wrote: post #163

Earlier quoted context omitted.

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 t…

People also fall asleep at the wheel, with cruse control there now driving randomly.

I watched someone driving on a nice sunny day on a low traffic interstate suddenly make a sharp right turn crossing our lane to fly off the highway and start rolling. I have no idea why this happened, but everyone in the car survived so it's not even part of the traffic fatality statistics.

Re: Let’s Talk About Self-Driving Cars

#222

Post by oconnor663 » Tue, Jan 10, 2017, 8:51 PM UTC

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…

I think there are some basic physical advantages that might make the computers leap ahead of the humans, at least in terms of safety. Things like cameras pointing in all directions, really fast reaction times, and good steering/braking technique. Those don't necessarily help you navigate complicated intersections, so there might still be plenty of practical problems in the phase transition, but maybe fewer safety problems?

It could even be that the safety improvements are so dramatic that they become the pressure for us to engineer around the other issues. (Like marking lanes electronically and giving traffic cops new equipment and whatever else.)

Re: Let’s Talk About Self-Driving Cars

#223

Post by sebastos » Tue, Jan 10, 2017, 8:53 PM UTC

JamesBarney wrote: post #182

sebastos wrote: post #120

Earlier quoted context omitted.

Okay, I've designed a new pill. 1 out of 4 people have adverse reactions to its contents and die instantly, but people who don't live long virile lives until, on average, the age of 100! Your expected gain would be nearly 5 additional years of life! Should I sign you up?

These years aren't comparable because I'm trading years in the immediate future for years in the distant future. Not many people would trade next year for a year and 2 months when they're 80.

Okay. Suppose that you spend 30 minutes on your commute each day for the rest of your working life, until you're 65. That means you'll waste almost a full year's worth of waking hours driving.

I've invented a teleporter that will reduce your commute to 1 second every day. The only glitch is that your molecular makeup may be incompatible with my device, and there's no way to tell for sure. If it is, you'll disintegrate instantly the first time you try to use it.

Don't worry, only 1% of the population is incompatible. From a probability standpoint, you should expect to gain more than 1% of your life in extra time. Care to give her a whirl?

Re: Let’s Talk About Self-Driving Cars

#224

Post by RangerScience » Tue, Jan 10, 2017, 9:10 PM UTC

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…

Simpler than that; Nissan's been working on it, and it's finally been announced:

http://www.autoblog.com/2017/01/10/nissan-self-driving-cars-...

> For example, Sierhuis described a situation where a temporary construction site, something like a crew repairing a traffic light, would confuse the car. Not only would the traffic signal be missing for the AI to process, but we would also have a worker waving cars through the intersection. It's a prime, real-world example of a challenge that is basically impossible to program into software. With SAM, when a self-driving Nissan approaches a situation like this, it stops and sends a signal to a human operator. This operator, called a Mobility Manager, checks the camera feeds from the car, high-definition maps, and whatever else he can, and then plots a new route for the car to take. This information is then sent to all the other Nissan AI machines in the area so that they don't have a problem when they approach the same intersection.

Re: Let’s Talk About Self-Driving Cars

#225

Post by sjwright » Tue, Jan 10, 2017, 9:11 PM UTC

monk_e_boy wrote: post #207

russdill wrote: post #160

Earlier quoted context omitted.

NVIDIA actually talks about this in their last series of talks. The car when planning the drive makes a determination of whether or not it expects driver assist and how much. Of course a drunk person could just check off the sure, I can drive for those sections and then pass out anyway.

Without a steering wheel where all user actions are made on a touch screen or by voice, would it matter that you were drunk? If the car came to a situation that it needed human input then that human could be drunkenly slurring advice. But I am failing to see a situation that the car wouldn't be able to figure out, but the human inside could figure out... I've been in situations where I didn't know what to do and had…

You wouldn't even need drones, the aggregate of all the cars' sensors would be enough.

Re: Let’s Talk About Self-Driving Cars

#226

Post by davnn » Tue, Jan 10, 2017, 9:14 PM UTC

ahains wrote: post #209

alkonaut wrote: post #186

Earlier quoted context omitted.

Driving a known "autonomous safe" route, or map region, and simply not driving if the conditions aren't ok (it's snowing, there is construction in the area so maps or lanes are poor etc) works. But that's basically taking the "mostly autonomous"-level driving, and just adapting either the environment and/or the restrictions/schedule/routes to that. Uber could probably also just have defensive systems that simply park…

Rather than a fallback driver having to physically enter the car, maybe they could take the drone pilot approach and control it remotely. There would be the latency to overcome, but the built in crash avoidance might be good enough for a relatively short/slow distance to exit the exceptional situation.

That's actually a really interesting idea - hand off driving to a remote person when the conditions are bad.

But would a car's connectivity and latency allow for that to be safe?

Edit: If not there would still be some form control needed for the passenger.

Re: Let’s Talk About Self-Driving Cars

#227

Post by coldtea » Tue, Jan 10, 2017, 9:19 PM UTC

jellicle wrote: post #215

coldtea wrote: post #150

Earlier quoted context omitted.

> 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 ser…

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

Self driving cars already know how to park and get out of the road.

The rest of the argument goes into bizarro land. Can't tell if trolling...

First, a stop vehicle in the middle on the road is a surefire way to a multi-car collision at worse, and traffic fines at best. Both of which would be avoided by any self driving algorithm not written (or approved if it's something like a neural network) by Harpo Marx.

Second, "It's obviously maximal for MY vehicle to stay on the road at all times" is not an argument, since self driving algorithms are not written and optimized for the car owners sole convenience but also for overall traffic, traffic regulations, and several other considerations besides...

Re: Let’s Talk About Self-Driving Cars

#228

Post by coldtea » Tue, Jan 10, 2017, 9:23 PM UTC

beachstartup wrote: post #161

coldtea wrote: post #150

Earlier quoted context omitted.

> 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…

yeah, just tell the autonomous 4000 pound missile that stopping is a low priority. i fear much of the enthusiasm behind self-driving cars is from people who understand neither driving, nor computer software, very well.

>yeah, just tell the autonomous 4000 pound missile that stopping is a low priority.

Lower priority than stopping then and there in the middle of the road/interstate (as suggested by parent) as opposed to a service/rest-area/shoulder/side of the road/etc...

Re: Let’s Talk About Self-Driving Cars

#229

Post by nradov » Tue, Jan 10, 2017, 9:24 PM UTC

sytse wrote: post #212

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…

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.

Our wireless communications infrastructure lacks the reliability and latency guarantees that would be necessary for remote operation.

Re: Let’s Talk About Self-Driving Cars

#230

Post by coldtea » Tue, Jan 10, 2017, 9:25 PM UTC

galdosdi wrote: post #202

wolfram74 wrote: post #166

Earlier quoted context omitted.

That feels like you're intentionally misinterpreting the suggestion. The implied solution is that a car would preferentially stop off to the side of the road, rather than the middle.

If there _is_ a valid and safe "side of the road" There are places where it takes some skill just to comply with an officer's request for you to pull over. Not everywhere is a bunch of standardized interstates.

That's what we are saying.

Have the car GO and find a suitable area. Driving for a few more km perhaps slower and with the alarm lights flashing to find a spot to stop, will surely be safer than stopping right then and there just because you can't find a convenient place to pull out.