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

The latest chapter for the self-driving car: mastering city street driving

googleblog.blogspot.com

Post reply on HN
Print view View original

131–140 of 455 posts

Re: The latest chapter for the self-driving car: mastering city street driving

#131

Post by danpat »

skrause wrote: post #48
rwmj wrote: post #5

This is hardly city driving. Try driving in a European city. (I love this project and can't wait to buy or rent a self-driving car)

I think self-driving cars will be introduced very gradually. First only highways where it's really easy for a computer, then maybe American cities. The harder the street layout, the longer we'll have to wait for this technology. So maybe American cities will get the technology a few years before European.

I don't understand why the detractors don't understand this. Many people (including some commenters here) seem to think that the technology is useless unless it can handle all possible situations.

Auto-drive on long highway sections would be an amazing improvement by itself and prevent all kinds of fatigue related accidents. The cars could just announce ("Driver, take control") as they exit the highway system.

Hell, trucking companies could just have drivers waiting at highway exits to do the last-mile driving, the long-haul sections of trucking wouldn't require a person on-board.

I don't think it would be unfeasible to install beacons designed to aid driverless vehicles either, especially on highways where things don't change very quickly. Simple posts with machine-readable signalling (visual/radio/whatever). Most signage is designed for human recognition, but I bet it wouldn't be impossible/terribly expensive to install signage designed for automated driving.

Re: The latest chapter for the self-driving car: mastering city street driving

#132

Post by danpat »

I assume that someone has done an analysis of how the sensors will interact when there are many self-driving cars on the road?

Because many of the primary sensors are active (radar, lidar), will they work when they're surrounded by 50 other cars also blasting out the same signals?

Re: The latest chapter for the self-driving car: mastering city street driving

#133

Post by chillingeffect »

nabla9 wrote: post #18
deanclatworthy wrote: post #4

This is amazing, but if anything it's made me more wary of some of the challenges the project faces. - What if the cyclist fell off his bike in front of the car? How quickly can the computer process the real-time imagery and react compared to a human with their peripheral vision. - What if the cyclist swung from the pavement on to the road. A human driver will probably have spotted the hazard (we all train for that k…

Somebody correct me if I'm wrong, but Google cars still can't drive in the rain or in the snow. Not even on a wet street. They have driven all those thousand miles in Mountain View, Calif. in good weather. Generally lidar's don't work well with rain or reflective surfaces.

I am also curious about multiple vehicles using LDAR at the same time. Is it possible for two or more vehicles to operate using LIDAR independently, or must they synchronize with one another and how far apart do they have to be?

Re: The latest chapter for the self-driving car: mastering city street driving

#134

Post by thefreeman »

josefresco wrote: post #106
Zigurd wrote: post #23

Earlier quoted context omitted.

Even before we get self-driving cars, autonomous braking should be mandated so that cars and trucks are literally incapable of coming too close to a cyclist.

I'll back that as soon as a system to force bicyclists to abide by traffic laws is required.

I have a feeling that the general populace of hacker news will disagree with us, but I am with you 100%.

I live in a small-ish town on the outskirts of Philadelphia that happens to be in the middle of some sort of really popular biking route. Unfortunately, we have a ton of really small streets with cars parked on both sides.

I understand and appreciate that cyclists have no other place to ride then in the street, and they as much a right to the road as drivers. But it can be quite frustrating to be stuck behind a cyclist who is making no effort to pedal quickly on a road where it is impossible to pass them.

The really frustrating thing though is that they completely ignore traffic rules. If you have to ride in the street and I have to treat you as part of traffic, fine. But why do you get to creep up the side of the street at red lights, then positioning yourself in front of more cars to slow down. And why do you get to run red lights? It seems it needs to be one way or the other. Either you are a pedestrian, and you should be trying to avoid traffic, or you are a participant on the road and you should obey the traffic laws.

Re: The latest chapter for the self-driving car: mastering city street driving

#135

Post by jacquesm »

antr wrote: post #3

I love how the car understands the cyclist's hand signals. The self-driving car is going to have a gigantic impact on the world, I can't wait to see it commercialised.

Now all you have to do is to get cyclists to actually use hand signals. Sure they're technically required but in any of the countries that I have been to where bikes are a frequent mode of transportation hand signals appear to be mostly optional.

Re: The latest chapter for the self-driving car: mastering city street driving

#136

Post by shekhar101 »

dalke wrote: post #115
skrause wrote: post #94

Earlier quoted context omitted.

You can do that now already, e.g. pretend to quickly step on a road while a car is approaching and watch the human drives hit their brakes. Yet I don't see that happening because the majority of people aren't jerks.

Doing so physically, that is, driving erratically or aggressively, or giving false signals, is both visible to other drivers and illegal. It can also be recorded on camera. Electronic signals are not visible, and fewer people have the ability to record and analyze the signal traffic. While the majority of people aren't jerks, consider existing cases of people/jerks who use traffic signal preemption devices for person…

Errr... wouldn't it be easier to record such 'jerks' electronically? I mean isn't it difficult to catch a number plate in dark while it would be lot easier to record someone doing it if there is a communication along with an ID for each vehicle?

Re: The latest chapter for the self-driving car: mastering city street driving

#137

Post by jacquesm »

Zigurd wrote: post #77
josephlord wrote: post #73

Earlier quoted context omitted.

I'm a cyclist as well as a driver and I give a lot of space to cyclists when overtaking them but I don't see that working too well. When cyclists/pedestrians get used to the system they will start to abuse it and rely on the systems to force the vehicles to avoid them/stop. Also what defines too close? If you stray 1mm inside that zone do the brakes come on hard regardless of other traffic? What happens when the cycl…

Autonomous braking exists for those kinds of events: When a person steps out in front of a car, for example. Yet I don't see people deliberately jumping out in front of cars just to mess with them.

Google 'russia dashcam' videos and have your worldview adjusted. Incredibly, in Russia people apparently throw themselves in front of cars to try to get injury compensation. It doesn't happen often but often enough that people have made compilation videos. That and a whole pile of crazy drivers are the reason that dashcams are so popular in Russia in the first place, they give the driver some evidence to show what happened prior to the accident.

Re: The latest chapter for the self-driving car: mastering city street driving

#138

Post by jacquesm »

tim333 wrote: post #105
masklinn wrote: post #39

Earlier quoted context omitted.

> very little regard to any regulations. That's an important point, I never expected lanes count and lane direction to be interpreted as suggestions until I saw people going through a roundabout on both sides at the same time.

Yeah I was just biking in Vietnam and Cambodia and it's quite a different system with stuff all over the place. There is a kind of logic to it - you project their trajectory and yours and if there's no impact you keep going, otherwise you modify speed and direction in a minimal way to avoid impact regardless of going the wrong way on the wrong side of the road etc. It takes quite a bit of getting used to as a western…

The basics of flock behavior.

Re: The latest chapter for the self-driving car: mastering city street driving

#139

Post by antr »

jacquesm wrote: post #135
antr wrote: post #3

I love how the car understands the cyclist's hand signals. The self-driving car is going to have a gigantic impact on the world, I can't wait to see it commercialised.

Now all you have to do is to get cyclists to actually use hand signals. Sure they're technically required but in any of the countries that I have been to where bikes are a frequent mode of transportation hand signals appear to be mostly optional.

> Now all you have to do is to get cyclists to actually use hand signals.

I was waiting for the snarky comment. All I'm highlighting is the system's ability to recognise such intention (many times ignored by drivers). Regardless, such indications seem not to be "necessary", the GSC detects the cars direction/intention primarily via its mounted laser, rather than "looking" for left/right light indicators.

Re: The latest chapter for the self-driving car: mastering city street driving

#140

Post by voicereasonish »

melling wrote: post #17
deanclatworthy wrote: post #4

This is amazing, but if anything it's made me more wary of some of the challenges the project faces. - What if the cyclist fell off his bike in front of the car? How quickly can the computer process the real-time imagery and react compared to a human with their peripheral vision. - What if the cyclist swung from the pavement on to the road. A human driver will probably have spotted the hazard (we all train for that k…

There are over 30,0000 deaths in the US alone every year, which is actually near historical lows. I believe there are several million accidents and hundreds of thousands of injuries. Now the computer might not be perfect but if it's 10x better, wouldn't that be acceptable?

30,000 deaths a year in a country like the US is nothing. More people die from falling down the stairs. Should we ban stairs next?
Post reply on HN