Hacker News Reader

Comment by dkonofalski | Hacker News Reader

I don't really know why this is surprising. Computers are already better than humans at most tasks that involve a limited set of behaviors and they have infinitely better response time than humans (and continue to get better). How could anyone think that a report like this was going to end up any differently?

View on HN

You might want to read about Therac-25

It's okay to withhold judgement and to be skeptical until seeing actual data. Especially for rapidly developing technologies like self-driving cars.

I didn't say it wasn't ok to be skeptical, just that I wasn't surprised by the results. Teslas have been on the road for over a year with AutoPilot and there haven't been any accidents caused by the system. Why anyone is surprised that AutoPilot is safer than a human driver is what I'm not understanding. Based on the votes, though, apparently computers are evil and shouldn't be trusted and we should all be amazed when they don't just kill us.

You said you didn't understand why it was surprising, which is a different thing than not being surprised.

Computers are good at lots of things like playing chess, and still completely incapable at lots of things that involve common sense. Expecting autonomous cars to be better than human drivers eventually is one thing, but it is certainly not obvious that we are there yet.

The history of self driving cars shows that it is not an easy task. We've been working on this for over 15 years. I was on a self driving car team during 2008-2010. We won multiple intercollegiate competitions. At that time I was certain it would be 20+ years before we had something that could drive on the roads. The progress has been spectacular.

No, programming the self-driving car is not an easy task. A car that's already been programmed, though, is definitely going to be safer than a human driver and driving for the computer is an easy task.

> definitely going to be safer than a human driver

That's just ridiculous. It is going to be safer in some cases and less safe in others, and obviously it depends on the system and the driving conditions. To say that a computer is necessarily a better driver is just science fiction until we have solid data showing that to be the case.

> We've been working on this for over 15 years.

Over 25 years, actually - CMU's ALVINN (1989) was one of the first full-sized vehicle implementations:

http://repository.cmu.edu/cgi/viewcontent.cgi?article=2874&c...

It was preceded by an E-MAXX based RC car system called DAVE (DARPA Autonomous Vehicle).

CMU also worked on an investigated other systems, going back to 1984 or so:

http://www.cs.cmu.edu/afs/cs/project/alv/www/

They had an interesting system called the Terragator, from at least 1983; I can't find a paper about this system, though I know they exist - there is a video, though:

https://www.youtube.com/watch?v=beGRM9ZmWlI

One might consider the Stanford Cart as an earlier example (I believed it used computer vision techniques - and was really slow at computing the "next move"):

https://web.stanford.edu/~learnest/cart.htm

(side note: As part of SAIL, the Cart was instrumental in paving the way for Thrun's Stanley - which won the DARPA Grand Challenge, and ultimately led to Google's efforts in self-driving cars)

ALVINN was unique in that it used a (simple compared to today's CNNs and deep learning) neural network (and a WARP systolic array):

https://en.wikipedia.org/wiki/WARP_(systolic_array)

...coupled to a camera to digitize and model/learn the road features for driving, while "watching" the human driver (early form of "behavioral cloning" - but it wasn't termed as such in the various papers you can find about ALVINN).

Interestingly, during the ML Class in 2011 (which I participated in), one of the students - after we were shown several times how ALVINN worked - decided to replicate the system using "modern hardware":

http://blog.davidsingleton.org/nnrccar/

We've really come a long way...

Reply on news.ycombinator.com