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

How Self-Driving Cars Work

nytimes.com

Post reply on HN
Print view View original

11–20 of 43 posts

Re: How Self-Driving Cars Work

#11

Post by argonaut »

taneq wrote: post #9
argonaut wrote: post #8

Earlier quoted context omitted.

> Humans only have one sensor: a rotatable stereo camera. So at least in theory the number of sensors seems not the most important element ;-) I hear this comment a lot when defending Tesla's choices, and it's a red herring. The fact that humans only rely on two cameras means nothing. Repeating old comments of mine: You also don't "need" megawatts of power to play top-level Go: humans do it with 100 watts of energy.…

I've been wondering why no self driving systems seem to use DTAM or similar methods. Realtime dense 3D reconstruction and camera localisation on commodity hardware seems perfect for the job.

There is a big open research problem in the state of the art in visual SLAM (visual SLAM = SLAM from cameras), it doesn't work when the environment is moving (!!!).

Visual slam is still linear-algebra/geometric/keyframe based traditional computer vision (including variants that incorporate GPS/accelerometer info). I think the state of the art is stereo LSD-SLAM, but I could be wrong.

Re: How Self-Driving Cars Work

#12

Post by argonaut »

ranman wrote: post #10

I'd pass on reading this if you clicked through to the comments first. There's very little detail about how self driving cars work. This is a very basic survey of brands. Remember the Murray Gell-Man amnesia effect. Does anyone have real examples / links / videos of how self driving cars work?

Firstly, there are different approaches. Google and Uber seem to have a similar LIDAR + map approach. Tesla and Mobileeye have a camera focused approach.

The CEO of Mobileeye (who is an ex-machine learning professor) gave a very good, mildly technical talk on their approach at CVPR: https://www.youtube.com/watch?v=n8T7A3wqH3Q

Re: How Self-Driving Cars Work

#13

Post by jayjay71 »

argonaut wrote: post #11
taneq wrote: post #9

Earlier quoted context omitted.

I've been wondering why no self driving systems seem to use DTAM or similar methods. Realtime dense 3D reconstruction and camera localisation on commodity hardware seems perfect for the job.

There is a big open research problem in the state of the art in visual SLAM (visual SLAM = SLAM from cameras), it doesn't work when the environment is moving (!!!). Visual slam is still linear-algebra/geometric/keyframe based traditional computer vision (including variants that incorporate GPS/accelerometer info). I think the state of the art is stereo LSD-SLAM, but I could be wrong.

A great way to explain this to people would be to ask them if they've ever seen a panoramic photo glitch, and tell them that's what the car would be seeing most of the time (well, assuming anything is moving, like a car or a person or a piece of trash).

Re: How Self-Driving Cars Work

#14

Post by beachstartup »

PinguTS wrote: post #2

This article misses a lot of things technology wise. OK, I understand that. This article also misses a lot air companies like Daimler who showed off self driving car captibilities publicly in the beginning 2000 and on the web 3 years ago. It misses the prototypes shown off by Audi and BMW. It misses also the prototypes shown by Japanese car manufacturers. From technology companies it misses Bosch who will show off at…

the nyt is always off the mark on topics i know something about, and nothing leads me to believe they are any better about topics i know nothing about.

Re: How Self-Driving Cars Work

#15

Post by demosthenes111 »

argonaut wrote: post #8
Gys wrote: post #7

Earlier quoted context omitted.

I just had a look at the website of the Outlander. Its not mentioned anywhere that it has self driving capabilities. The sensors are used to warn the driver and intervene if a crash is imminent. So can I conclude there is a difference in the (state of) implementation between the hardware (sensors) and the software (self-driving intelligence) ? Humans only have one sensor: a rotatable stereo camera. So at least in the…

> Humans only have one sensor: a rotatable stereo camera. So at least in theory the number of sensors seems not the most important element ;-) I hear this comment a lot when defending Tesla's choices, and it's a red herring. The fact that humans only rely on two cameras means nothing. Repeating old comments of mine: You also don't "need" megawatts of power to play top-level Go: humans do it with 100 watts of energy.…

Your point is generally valid, but it's worth noting that power =/= energy. It is conceivable that at 100 watts of power, a human could use on the order megawatt hours of energy while practicing to achieve top-level performance. 10000 hours of practice is not unreasonable to achieve mastery which would be 1MWh.

It's also likely that AlphaGo is reasonably efficient, given that it used custom ASICs.

Re: How Self-Driving Cars Work

#16

Post by jayjay71 »

beachstartup wrote: post #14
PinguTS wrote: post #2

This article misses a lot of things technology wise. OK, I understand that. This article also misses a lot air companies like Daimler who showed off self driving car captibilities publicly in the beginning 2000 and on the web 3 years ago. It misses the prototypes shown off by Audi and BMW. It misses also the prototypes shown by Japanese car manufacturers. From technology companies it misses Bosch who will show off at…

the nyt is always off the mark on topics i know something about, and nothing leads me to believe they are any better about topics i know nothing about.

That's known as the Gell-Mann Amnesia effect.

https://seekerblog.com/2006/01/31/the-murray-gell-mann-amnes...

Re: How Self-Driving Cars Work

#17

Post by globuous »

jayjay71 wrote: post #16
beachstartup wrote: post #14

Earlier quoted context omitted.

the nyt is always off the mark on topics i know something about, and nothing leads me to believe they are any better about topics i know nothing about.

That's known as the Gell-Mann Amnesia effect. https://seekerblog.com/2006/01/31/the-murray-gell-mann-amnes...

I agree with this so much. However, playing the devil's advocate, I guess it depends on the journalist's background.

For instance, a poli-sci major writing about a scientific/tech topic will likely get a lot of things wrong. However, the same journalist might likely have a lot of interesting things to write about international politics, because that's what his background is about.

that being said, I don't know how much journalist writing about politics have studied it in the past.

Re: How Self-Driving Cars Work

#18

Post by beachstartup »

globuous wrote: post #17
jayjay71 wrote: post #16

Earlier quoted context omitted.

That's known as the Gell-Mann Amnesia effect. https://seekerblog.com/2006/01/31/the-murray-gell-mann-amnes...

I agree with this so much. However, playing the devil's advocate, I guess it depends on the journalist's background. For instance, a poli-sci major writing about a scientific/tech topic will likely get a lot of things wrong. However, the same journalist might likely have a lot of interesting things to write about international politics, because that's what his background is about. that being said, I don't know how mu…

my gut assumption is that most journalists have journalism or communications degrees, which seems to be corroborated by the data.

https://books.google.com/books?id=KUyOAgAAQBAJ&pg=PA42&lpg=P...

not that it really matters, i have an econ degree but wouldn't call myself an economist by any stretch.

the real issue, at least in the US, most news is really just either direct or indirect PR. curiously, i think 'X writer' is the term you are looking for. i.e., someone with a background in technology or fashion that reports on things is more likely to be called themselves a 'tech writer' or 'fashion writer'. it's almost like real experts don't even want to be called journalists. i certainly wouldn't.

i've found that you're much more likely to find accurate reporting in industry-specific media rather than general media, because then at least the sources of funding and agenda are pretty clear.

Re: How Self-Driving Cars Work

#19

Post by milanove »

PinguTS wrote: post #2

This article misses a lot of things technology wise. OK, I understand that. This article also misses a lot air companies like Daimler who showed off self driving car captibilities publicly in the beginning 2000 and on the web 3 years ago. It misses the prototypes shown off by Audi and BMW. It misses also the prototypes shown by Japanese car manufacturers. From technology companies it misses Bosch who will show off at…

Covering every detail of the technology wasn't really the point of the article. It's a New York Times article. It's meant to give a brief explanation, for non-engineers, as to how this technology works. The target audience don't need to know all the different companies' achievements nor the specifics of the technology used.

Re: How Self-Driving Cars Work

#20

Post by argonaut »

demosthenes111 wrote: post #15
argonaut wrote: post #8

Earlier quoted context omitted.

> Humans only have one sensor: a rotatable stereo camera. So at least in theory the number of sensors seems not the most important element ;-) I hear this comment a lot when defending Tesla's choices, and it's a red herring. The fact that humans only rely on two cameras means nothing. Repeating old comments of mine: You also don't "need" megawatts of power to play top-level Go: humans do it with 100 watts of energy.…

Your point is generally valid, but it's worth noting that power =/= energy. It is conceivable that at 100 watts of power, a human could use on the order megawatt hours of energy while practicing to achieve top-level performance. 10000 hours of practice is not unreasonable to achieve mastery which would be 1MWh. It's also likely that AlphaGo is reasonably efficient, given that it used custom ASICs.

According to Google they used 280 GPUs and 1,920 CPUs. I'm sure they used custom chips in addition.
Post reply on HN