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

341–350 of 455 posts

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

#341

Post by dnr »

bertil wrote: post #316
barrkel wrote: post #46

Earlier quoted context omitted.

don’t notice what passing just being, shift in gear, swerve and… bang Can you rephrase this? I can't understand it.

At the very end of the video, you can see a common situation: a car waits at an intersection to turn right. Nothing seems to block its way. Actually, in the US, cars seem to turn right even when the light is red, for instance. Anyway: what they show is that, just behind the car, just at its right, there is a cyclist. But it is in the dead spot. That cyclist is most likely going steady because the path is clear: cars…

In the US, that situation is called a "right hook", and it's indeed very dangerous for cyclists. Once you know about it, though, it's pretty easy to ride defensively and avoid it: just refuse to pass on the right of a car that might turn right. Get behind them instead and wait for them to turn (or go straight). In California, at least, a cyclist is legally entitled to take the lane at any intersection where a right turn is allowed.

(In practice, I admit that I don't do this 100% of the time. I never pass to the right of a car with a right turn signal on, but if a car is waiting at a red light without a turn signal, I'll sometimes pass on their right, always stopping well in front of the front of the car, so that I'm confident the driver sees me.)

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

#342

Post by jfoster »

pyre wrote: post #335
andrewfong wrote: post #252

Earlier quoted context omitted.

I suspect the higher standard question will be resolved in a couple of ways: * NTSB review: Airplanes face higher scrutiny than automobiles (despite the lower overall casualty rate). Part of the reason people have grown comfortable with air travel nonetheless is because the NTSB analyzes what went wrong after each crash and recommends (mandates) certain changes. Moreover, as far as government agencies go, the NTSB do…

UPS employees are unionized, and driving routes (vs. working in the warehouses) is a sought-after position that is one of the benefits of seniority (as I understand it). I expect that they might have issues rolling out a computerized delivery fleet.

So they'll just get replaced. Amazon and Google do seem keen to get into that space.

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

#343

Post by jameshart »

ignostic wrote: post #209

Everyone seems really concerned with the edge cases right now. What about insurance and liability? What about when X happens and it's raining? These are (usually pretty minor) technical challenges, and I haven't heard one yet that we won't be able to overcome with today's technology. Under given circumstances the car will be safer than a human or it isn't. The moment it crosses that threshold (for most conditions) th…

"a full network of communicating cars and fail-safes" is a long way away, though. And to get there you have to go through a long period of some self-driving cars, sharing the road with old-fashioned human piloted ones. As a human driver, I spend a lot of my time anticipating the behavior of my fellow road-users. That car coming up from the side street - did they see me? They're on their phone, maybe they didn't see me... they're going to pull out... better brake...; now I'm coming up to an exit; the car in the lane to my left just changed speed, probably going to try to cut across in front of me, better give them some room...; cyclist coming up on the right, am I going to get past him before I need to slow for my right turn, or should I slow up behind him?

Understanding and anticipating all those human behaviors seems to me to be well beyond the capabilities of current AI.

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

#344

Post by pyoung »

dclowd9901 wrote: post #334
ignostic wrote: post #314

Earlier quoted context omitted.

I hear people fretting about liability as a "problem to overcome," but it's actually much simpler than the technical challenges. People have to drive the same distance regardless. Whether it's human or computer error leading to the accident is irrelevant to your premium. To a car insurance company it's all about rates and risks. Assuming driverless cars are shown to be safer than humans - and they'll have to be in or…

The problem is your insurance company. If you get in an accident, they're not going to want to pay for it, and they're going to go after Google for the damages. Now we're right back where we started.

Why couldn't Google just offer their own insurance plan? They could bundle the cost with a monthly or yearly service/maintenance fee. If the margins are so high on insurance products, I'm sure they would be more than happy to keep the profits themselves.

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

#345

Post by jfoster »

chillingeffect wrote: post #256
TheEzEzz wrote: post #231

Earlier quoted context omitted.

There must be at least 50 million residential garages in the US alone. If we automate all cars and switch to a Cars-as-a-Service model that is 50 million large rooms suddenly available. That's a lot of reclaimed real estate. Edit: If the average garage is 250 sq ft (pretty small), average cost of real estate is $100/sq ft (pretty low), then this is a $1.25 trillion windfall. Not bad for a small side-effect of autonom…

Way to only see everything with rose-colored glasses. Has it even occurred to you there might be any possible cons to your scenario? First of all, the lot the cars come from is going to require real estate, so subtract that from your windfall. Where will they be at night or other low-use times? Second, subtract the additional resources in gas/electricity it takes to get to my house from god-knows-where it came from.…

Entrepreneurs see the future by being optimistic idealists.

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

#346

Post by genericone »

danpat wrote: post #132

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?

When 50 other cars are nearby actively communicating with each other about the road conditions that they each see, only a representative subset of those cars need to correctly identify road conditions and report them to the entire group as a road-conditions map. Cars in the group validate the observations and risk-factors reported by other cars. Then each car independently makes its driving decisions based on this shared-data based on its relative position in the group.

In this way, being surrounded by hundreds of other cars is a plus, and leads to more data by which to determine safe self-driving behavior.

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

#347

Post by gbog »

pinaceae wrote: post #130
gbog wrote: post #120

In this discussion I very rarely see mentioned how heavy are cars. Since when do we need multi tons machine to move a being that is usually below 100kg from a to b? Here in northern China, many people have very small egg-cars, which are nothing more than an electric bike with a thin shell for the cold, and this is much less likely to kill someone by accident. I think we have been under a very strong brain washing so…

because it is a multi-purpose vehicle. i drive a car to work, single passenger. i drive the car to buy stuff, with my wife, 2 passengers, plus hauling stuff in the trunk. i drive the car to various places on the weekend, wife plus kid plus shit in the trunk. i bought it to cover multiple transportation scenarios I encounter on a weekly basis. it also has a certain size to protect me in an accident. bumping into somet…

Ok I actually have the same usage pattern as you and I have a minivan, which I think optimizes quite well the size.

Also, you say you didn't kill anyone. Great but how much room did cities you crossed have to plan for you? How many other non driving people had to reduce their living space for this? Not counting fossil fuel, materials used, etc.

Safety is probably the mask used by this light to hide their agenda, and it is clever. Buy maybe it is completely made up. Maybe everyone would be much safer in very different cars, maybe our human tastes have been terraformed to fulfill the avidity of some powerful lobby.

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

#348

Post by midas007 »

The interesting problems are:

- tracking thousands of objects' trajectories to avoid as many threat-weighted collisions as possible. (think NYC times square)

- not going too fast when visibility is blocked

FYI: When I was at Trimble Nav, there were self-driving farm equipment demonstrated c. 2000.

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

#349

Post by midas007 »

ignostic wrote: post #209

Everyone seems really concerned with the edge cases right now. What about insurance and liability? What about when X happens and it's raining? These are (usually pretty minor) technical challenges, and I haven't heard one yet that we won't be able to overcome with today's technology. Under given circumstances the car will be safer than a human or it isn't. The moment it crosses that threshold (for most conditions) th…

Parking structures might become high-security, automated bldgs that people don't enter. Further, local parking spaces may be unnecessary as your car (or the car you rent) will pick you up.

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

#350

Post by TheEzEzz »

aetherson wrote: post #328
TheEzEzz wrote: post #307

Earlier quoted context omitted.

Paying for the self-driving cars will likely be a cost savings by itself, since we won't need as many auto-cars as regular cars. Most cars are only used maybe 5-8% of the time, and sit unused otherwise. An auto-car service could probably get at least 50% usage out of a car, potentially much more. That means a 10x reduction in the number of cards needed.

For this to be true, we have to assume that, during rush hour, at least 90% of all cars are parked and unused. 90%? That's a hell of a lot, dude. It's certainly true that most cars spend most of their time being parked and unused. But they tend to do so during times of day when there is very low demand. The vast majority of cars are unused at 4am (and, indeed, at 2pm), certainly. But even if every car that was on the…

Great point, was not considering that. I'd love to see some stats on maximum car utilization as a percentage during each minute of rush hour.

You could imagine that in addition to single-serve autocab services, you could have auto "micro" buses, sitting 4 people. Your "bus" is guaranteed to stop at no more than 7 other stops. With tens of thousands of people using the service it should be possible to pick optimal batches of people for each bus, to minimize how far the bus has to deviate from an ideal path for any given rider. It would be a giant logistical problem, but I think theoretically you can get a service working that was almost as seamless as an autocab service. Would be interesting to work on.

Post reply on HN