Slashdot Mirror
Nvidia GPU-Powered Autonomous Car Teaches Itself To See And Steer (networkworld.com)
An anonymous reader quotes a report from Network World discussing Nvidia's project called DAVE2, where their engineering team built a self-driving car with one camera, one Drive-PX embedded computer and only 72 hours of training data: Neural networks and image recognition applications such as self-driving cars have exploded recently for two reasons. First, Graphical Processing Units (GPU) used to render graphics in mobile phones became powerful and inexpensive. GPUs densely packed onto board-level supercomputers are very good at solving massively parallel neural network problems and are inexpensive enough for every AI researcher and software developer to buy. Second, large, labeled image datasets have become available to train massively parallel neural networks implemented on GPUs to see and perceive the world of objects captured by cameras. The Nvidia team trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands. Nvidia's breakthrough is the autonomous vehicle automatically taught itself by watching how a human drove, the internal representations of the processing steps of seeing the road ahead and steering the autonomous vehicle without explicitly training it to detect features such as roads and lanes.
In situations that do not resemble the training data, the network's response is essentially undefined, as well as unknown (it's all unknown... an NN results in behaviors that are not deterministic in the sense that anyone planned them out -- they are what they are, that's all.)
Nice experiment, though. :)
I've fallen off your lawn, and I can't get up.
and the system rebooted itself.
Sounds exactly like this (from December of 2015): http://www.bloomberg.com/features/2015-george-hotz-self-driving-car/
Ever driven with one eye shut? The drunks needn't answer that one. But with two or more cameras and various other sensors, it seems that the "learning" process would go much smoother.
“He’s not deformed, he’s just drunk!”
"What is my purpose?" ... "Oh God!"
"You drive me places."
"Welcome to the club, pal!"
https://www.youtube.com/watch?...
Don't turn evil and kill us all.
Shit guise, really don't need another bunch of expensive and inefficient room heaters in the car.
To be fair, if I was driving on the highway at night and a deer jumped out in front of the car I was driving,
I too, would reboot myself.
Once from the shock of the deer jumping in front of the car,
once from the collision
once from appraising the mess the collision created
once from clearing the mess off the road (assuming my car was still drivable)
once from the mental anguish of gruesomely killing a large charismatic animal.
the preceding comment is my own and in no way reflects the opinion of the Joint Chiefs of Staff
It takes 2 Dave2s and 2 lanes to drive on 4k roads with any kind of decent frame rates.
Marketing. They are showcasing their hardware.
Last I checked NVIDIA's market cap was 20.3B$. You'd think they have the ability to do more than one thing at a time, especially if it returns a profit on investment in the future.
This sort of AI usage is only going to increase, it would be dumb of NVIDIA not to at least divert a miniscule amount of manpower and resources to try and get their feet wet in this field. Anything they can patent or turn into a product will outweigh the paycheck for the engineers on this "worthless" venture.
ideally,
computing hardware running AI should be developed separately ( by many companies ),
so many deferent 'AI's can be created by many companies/groups separately, to run on those hardarews to interact with generic prototype vehicles/interfaces,
then many different vehicle producers can create many actual models to sell, enhancing those generics with added customized features that can be marketed.
doing all of the creating from start to selling, or at least most of that, by a single company, while other similar companies also do most of that separately, is a bad way to go.
many groups creating each separate part, and competing with each other to get those lower down to accept their creation, will benefit all.
Sorry, there is no algorithm that makes algorithms..
"Automatically taught itself by watching how a human drove..."
Oh my... and just what kind of driver was used as the role model?
It's nice to see how technology can be used in real world (ie on the road), not just on a store shelf.
A special chip for adaptive learning... heck yes, show that off!
This might work:
Neural net on a stick.
http://techcrunch.com/2016/04/...
I don't read your sig. Why are you reading mine?
We all know this car's running Windows cos Linux ain't got no good nVidia drivers!
"I like to lick butts!" by MobileTatsu-NJG (#32700246) (Score:5, Informative)
The Nvidia team trained a convolutional neural network (CNN) to map raw pixels from a single front-facing camera directly to steering commands.
That's about as "direct" as... well, as direct as the connection between the photons that enter my eye and the hand movements I make to steer my car, I suppose. Not very direct at all.
systemd is Roko's Basilisk.
Worthless?
This is precisely the sort of task you bring up every time there's a story on AI.
They're just doing what you told them to. Was your demand pointless all along?
Isn't this exactly the type of problem that DARPAs new CPU that's bad at math should be really good for?
"Grab them by the pussy" -- President of the United States of America
I love the comment when there is a merging lane, "I just have to watch out for BMWs."
-- I have a private email server in my basement.
"I watched you very carefully. Red light stop, green light go, yellow light go very fast."
-Starman
Here's an excellent article by Ashlee Vance about a self-driving neural net-based system created by one man, George Hotz: http://www.bloomberg.com/featu...
It contains one passage that sums up my fears:
Hotz hadn't programmed any of these behaviors into the vehicle. He can't really explain all the reasons it does what it does. It's started making decisions on its own.
This will come back to bite us. More than once. Systems can exhibit unexpected behavior even when the inventor has an excellent understanding of the invention; here, a very bright inventor seems to have no hope of fully understanding things.
Unexpected behavior from the control system of an object that has a lot of kinetic energy is usually bad. And a car is not the most dangerous thing you can put a neural net in charge of.
That that is is that that that that is not is not.
Obviously this thing needs more training data. If anyone happens to have a spare flock of lemmings and knows of a cliff near NVidia HQ please let them know ASAP.
"KITT, drive me home!" I can't believe no one has't already cited Michael Knight and KITT of "Knight Rider" the TV series that launched David Hasselhoff
This will never work until they give the machine the ability to raise a middle finger. Only then can it emulate human driving. :)
learned by observing, especially to accelerate hard to get through yellow lights.