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

Volvo’s first self-driving cars now being tested live on public roads in Sweden

kurzweilai.net

Post reply on HN
Print view View original

91–100 of 183 posts

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#91

Post by acchow »

protomyth wrote: post #9
MrClean wrote: post #5

“The test cars are now able to handle lane following, speed adaption, and merging traffic all by themselves,” This is an important step, although I must say they appear to be far behind Google. My money is on Google getting to an acceptable deployment phase far earlier.

Given the driving conditions in Sweden and the years of experience Volvo has as a car company, I would bet they will be able to deploy and all weather version before Google.

Can you explain what expertise as a car company has to do with AI?

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#92

Post by tormeh »

dalke wrote: post #56
fijal wrote: post #38

Earlier quoted context omitted.

4-way stop turn-taking is a problem that does not exist in europe btw

4-way stops exist in Sweden. Quoting from Wikipedia at http://sv.wikipedia.org/wiki/Stopplikt : > Vissa korsningar har en stoppskylt vid varje väg, ett så kallat flervägsstopp. Det innebär att alla som kommer till korsningen måste stanna, oavsett vilken väg man kommer på. Tanken är att man vid flervägsstopp ska ta ögonkontakt med medtrafikanter för att på så sätt komma överens om vem som ska köra först. Or my transla…

Well, good luck to Google and Volvo in making the eye contact thing work...

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#93

Post by jotm »

tormeh wrote: post #86
jotm wrote: post #63

Earlier quoted context omitted.

The driver won't have to be vigilant or even awake for the whole time, only in emergencies. I'm assuming the car would stop or slow down automatically in case of any problem and notify the driver. Good point on the pilots, though I always felt that it's unnecessary for them to stay awake (especially on cargo planes). And it looks like many do fall asleep inflight: http://uk.reuters.com/article/2013/10/08/oukoe-uk-bri…

>"even a few minutes" Oh boy, do they have straight roads where you come from...

:-) yeah, should've said a few moments/seconds

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#94

Post by trhway »

jacquesm wrote: post #87
nabla9 wrote: post #66

Earlier quoted context omitted.

LIDAR Google uses takes more than a million measurements per second and has ~11 cm resolution.

Right, my camera takes more than a million measurements in 1/100th of a second and has a spatial resolution comparable to that or better depending on the distance. 'A million measurements' sounds really impressive but it does not have much to do with anything. What's a measurement? A single distance measurement in front of the car? Ok, at what opening angle, how many returns, how many pulses / second and so on. As it…

>Right, my camera takes more than a million measurements in 1/100th of a second and has a spatial resolution comparable to that or better depending on the distance.

now you put second camera near-by and run stereo analysis algorithm to build 3D scene. 10+ years ago (DARPA Grand Challenge - where roots of Google self-driving car architecture comes from) with 1M cameras and the available hardware you'd get lucky to get 1 scene/sec and very crude one at that as 1M is much lower resolution than our eyes, and resolution is the key to stereovision. With LIDAR you just get 3D point for each measurement, no processing (beside regular filtering and coordinate transformation)

I wonder (haven't touched it myself for years nor checked the literature) what stereoprocessing one gets today on 10M-20M cameras on Intel CPUs of today plus GPU. It should be pretty close to what our eyes do, and what is most important - using several 20M cameras you can probably do _better_ than our eyes.

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#95

Post by thematt »

augustl wrote: post #35

I own a 2013 XC60 and as a programmer, I'm amazed at how well their current automation works in practice. The car reads road signs to show me the current speed limit in the dash (actual OCR, not a GPS database). It works amazingly well, except when it's very dark in the winter. Adaptive cruise control flawlessly follows cars based on radar, even in somewhat dramatic full stops, e.g. when there's suddenly heavy traffi…

Why would it bother OCR'ing road signs? That seems much more error prone and needlessly complex. That data is readily available from a data sources based on your GPS location, I know TomToms and other navigation devices have it.

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#96

Post by nawitus »

thematt wrote: post #95
augustl wrote: post #35

I own a 2013 XC60 and as a programmer, I'm amazed at how well their current automation works in practice. The car reads road signs to show me the current speed limit in the dash (actual OCR, not a GPS database). It works amazingly well, except when it's very dark in the winter. Adaptive cruise control flawlessly follows cars based on radar, even in somewhat dramatic full stops, e.g. when there's suddenly heavy traffi…

Why would it bother OCR'ing road signs? That seems much more error prone and needlessly complex. That data is readily available from a data sources based on your GPS location, I know TomToms and other navigation devices have it.

At least in Finland, probably in Sweden too speed limits change often (every 6 months) due to winter. In my experience the GPS databases are extremely often not in sync, and you can't predict which speed limits change and when. In addition, there are electronic speed limits that change depending on the weather in real-time. OCR seems like a better option for these conditions.

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#97

Post by interurban »

thematt wrote: post #95
augustl wrote: post #35

I own a 2013 XC60 and as a programmer, I'm amazed at how well their current automation works in practice. The car reads road signs to show me the current speed limit in the dash (actual OCR, not a GPS database). It works amazingly well, except when it's very dark in the winter. Adaptive cruise control flawlessly follows cars based on radar, even in somewhat dramatic full stops, e.g. when there's suddenly heavy traffi…

Why would it bother OCR'ing road signs? That seems much more error prone and needlessly complex. That data is readily available from a data sources based on your GPS location, I know TomToms and other navigation devices have it.

I think OCR may have reliability issues, but most road signage has consistent properties (size, height, font, etc.) that could be easily optimized for.

It also covers the (admittedly limited) situations where no GPS is available (tunnels, skyscrapers). If there are temporary changes in speed limits due to construction or other events, OCR could immediately identify those with no need to download new information.

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#98

Post by pedrocr »

chongli wrote: post #53
pedrocr wrote: post #26

Earlier quoted context omitted.

>Maybe Google has no intention of making autonomous cars for normal use but exclusively for Street View. Sounds like too much expense for just that. If the problem of street view was it's cost you could just pay people to add a StreetView system to the roof of their cars and get the data much cheaper than having your own car. They may very well want to start by using Street View to validate the technology but the end…

If the problem of street view was it's cost you could just pay people to add a StreetView system to the roof of their cars and get the data much cheaper than having your own car. I think you're underestimating the number of people you'd have to pay to get full coverage of cities. Most people do not drive around on every street in a systematic way; they have a small number of destinations and they usually take the sam…

You'd have to optimize for that. You can add incentives for people to mix up their routes, and you can use a much smaller number of dedicated cars to cover whatever is left. My point was that if the problem you're trying to solve is "StreetView is too expensive to operate" you're not going to go and create self driving cars, you'd do something simpler.

That doesn't mean that once you do have self-driving cars you wouldn't use them for that. Or even that StreetView wouldn't be the first thing you'd use them for, since that's a good way to get more training data for your algorithms. But to suggest they'd go to all the expense of creating self-driving cars to then use them just as a cost saving measure for StreetView sounds strange.

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#99

Post by protomyth »

acchow wrote: post #91
protomyth wrote: post #9

Earlier quoted context omitted.

Given the driving conditions in Sweden and the years of experience Volvo has as a car company, I would bet they will be able to deploy and all weather version before Google.

Can you explain what expertise as a car company has to do with AI?

After you explain what expertise a search engine / advertising company has with cars?

Re: Volvo’s first self-driving cars now being tested live on public roads in Sweden

#100

Post by Zigurd »

objclxt wrote: post #49
jotm wrote: post #30

I can't wait for self driving tech to be put into use - transportation will get cheaper and faster (no more 8-10 hours driving limit bs), not to mention that one or two persons could drive a dozen trucks filled with cargo (though a lot of truckers will hate that)...

> transportation will get cheaper and faster (no more 8-10 hours driving limit bs) Why do you say that? Somebody is still going to need to be awake at the controls, at least for the first few decades of self driving tech. There's a reason pilots on planes don't go to sleep when the auto-pilot kicks on.

I don't think that will be a hard requirement. A self-driving system will have to be capable of bringing a truck, or a convoy of trucks, to a safe stop in case of an incapacitated "driver" ("operator?"). Bringing an airplane promptly to a safe stop is usually not possible.
Post reply on HN