backtop


Print 17 comment(s) - last by YashBudini.. on Sep 27 at 10:19 PM

The system is based off human vision systems and will be applied to fully-autonomous vehicles

Researchers at Yale University and New York University have developed a new supercomputer that is capable of navigating a car more quickly and efficiently through the use of a human-based visual system. 

The supercomputer is called NeuFlow, and it was created by Eugenio Culurciello of Yale's School of Engineering & Applied Science along with Yann LeCun from New York University. Culurciello developed the human-inspired system while LeCun supplied the complex vision algorithms, which runs the neural networks for synthetic vision applications. NeuFlow's actions are based on the human visual system, acting as quickly and efficiently as a human when obeying traffic laws, distinguishing different objects from one another such as trees and buildings, and reacting to other drivers on the road. 

Culurciello and LeCun are looking to use this supercomputer as a way for cars to drive themselves. To do this, NeuFlow runs more than 100 billion operations per second only using a few watts of power, which is less than what's required to power a cell phone. NeuFlow exists on a single chip, making it no larger than a wallet, but it is more efficient and powerful than full-scale computers. Also, this system "processes tens of megapixel images in real time." 

"One of our first prototypes of this system is already capable of outperforming graphic processors on vision tasks," said Culurciello.

The development of fully-autonomous vehicle's will be a significant advancement in the world of human convenience and safety, and that's why NeuFlow isn't the only computer-driven system out there right now. 

In 2008, DailyTech went for a spin in the Chevrolet Tahoe DARPA Challenge vehicle, which is a fully-autonomous vehicle that won the DARPA 2007 Urban Challenge and is equipped with GPS, radar, video, laser and LIDAR sensors and inputs to recognize objects on the road. Its key sensor, velodyne, has 64 sensors in a wide array and is able to collect one million bits of data per second at 10 Hz. It's logic consists of over 350,000 lines of code, and is able to obtain a 3-D view of the surrounding terrain just like NeuFlow.

But unlike the Chevrolet Tahoe DARPA Challenge vehicle, NeuFlow is not quite ready for vehicle use yet. Culurciello and LeCun are looking to use NeuFlow in other applications as well, such as a tool for 360-degree synthetic vision for soldiers in combat and to help improve robot navigation in dangerous locations. 

NeuFlow was presented by Culurciello at the High Performance Embedded Computing (HPEC) workshop in Boston, Mass. on September 15. 



Comments     Threshold


This article is over a month old, voting and posting comments is disabled

Logic
By KIAman on 9/16/2010 2:21:48 PM , Rating: 3
This is an amazing achievement in technology but the program can only be as good as their maker; humans. Humans are *gasp* prone to making errors.

Assuming the code is bug free, imagine the decision making logic a device like this needs. What thresholds need to be met to swerve from an object vs crashing into it? Do you swerve left or right? What happens when going over a sharp crest where you cannot see anything over it until you are over? etc.

I predict this company will start getting into AI or a fuzzy logic system.




RE: Logic
By Jaybus on 9/16/2010 2:51:11 PM , Rating: 2
It will have many advantages over a human driver. Obviously, in addition to visible light vision, it can have IR night vision, as well as distance and speed info via LIDAR/RADAR, and all at the same time. Unlike the human, it won't get itself into these situations as often in the first place, since it won't get drunk, become distracted, or make a choice to go over a sharp crest at extreme speeds. There is no question that nearly all accidents are caused by driver error and carelessness.

Anyway, the principle has already been shown in aircraft, which are clearly safer when on autopilot.


RE: Logic
By xthetenth on 9/16/2010 2:56:55 PM , Rating: 3
quote:
What thresholds need to be met to swerve from an object vs crashing into it?

Whether swerving can be done without something overly stupid happening such as hitting a tree. Just look to see if there's somewhere safe to swerve, if so, do it. If not, try to determine whether the objects off road or on road are safer to hit. That's the real tricky bit. Still, anticipation is the real key, and something an always alert computer could do much better than a human.

quote:
Do you swerve left or right?


Look at the object, calculate it's velocity and acceleration, figure out where it'll be when you pass, and go to the side which gives bigger clearance. Check the sides to make sure you aren't boxed in and you're good.

quote:
What happens when going over a sharp crest where you cannot see anything over it until you are over?


Maybe feather the accelerator, but other than that, it's not like humans do much more, and computer reflexes are already an advantage.

The real tricky bit is going to be building an object library so that it can make good guesses about objects' properties, such as weight and whether they're attached to the ground.


RE: Logic
By magneticfield on 9/17/2010 3:38:46 AM , Rating: 2
I think there are a lot of computer programs made by humans out there, running on computers made by humans, and which do things way better than humans.

This kind of software solution is called an "expert system".

Or take the example of the Japanese Automatic Train Control. You know their trains have a precise schedule, with a cumulated delay of a few seconds per year. Do you think humans could do better?


OK
By Dr of crap on 9/16/2010 12:40:46 PM , Rating: 2
So first there will be cars that drive themselves, which will transform into there not being cars.
Why do you need cars if they drive themselves?
The next step would be pods that are available to take where ever you want to go.
I'm ok with that. Then I wouldn't need to deal with the god awful drivers out there everyday. And that lady could put on her makeup on the way to work, and that kid could text while riding and NO ONE would have an accident!




RE: OK
By Smartless on 9/16/2010 2:29:42 PM , Rating: 2
Ah yes, pods, that's a transportation engineer's vision. There's even been research into computer brains taking over on the freeway so that you can literally tailgate another car to increase the road capacity. In any case, iRobot comes to mind especially since Will Smith still "drove" his car. We Americans love our cars for its freedom, its unique expression, and because not everyone lives where mass transit is practical. Will this AI driven vehicles see consumer use? Maybe, but how much you want to bet someone's going to root their AI to program it to race or swerve in and out of traffic lol.


RE: OK
By geddarkstorm on 9/16/2010 3:27:27 PM , Rating: 2
I could see Japan loving something like this. Not only because they enjoy, culturally, being on the cutting edge AI/Robot wise, but also because of the population densities in their major city areas (being an island and all). This could be a serious boon to commuting.

For the US, we have tons of open space and sprawl, so computer controlled freeway systems are necessary or practical for the vast majority of the country. That would make it much harder to roll out, even selectively.


I wonder...
By Modeverything on 9/16/2010 1:50:31 PM , Rating: 2
I love technology, and I'm all for this, but I wonder if this would cause a large increase in state taxes.

If cars are driven by computer, there would be a lot less traffic violations (there would still be some since everyone would not have this), so states would collect a lot less money. I think the government would have to get it from somewhere else. I realize there would be less cops, but I don't think that would make up for the income states would lose from traffic fines.




RE: I wonder...
By The Raven on 9/17/2010 9:41:33 AM , Rating: 3
Also, there will be taxes so the country can afford to give gov't jobs to former chauffeurs. Because we all know now that if you don't have a job, the gov't will give one to you.


Yeah right into a wallYeah right into a wall
By zippyzoo on 9/16/10, Rating: 0
By spread on 9/16/2010 11:47:37 AM , Rating: 4
Yeah, but at least they stop on a dime.

http://www.youtube.com/watch#!v=A_83efj9Xdg&featur...


self-amusement
By RivuxGamma on 9/16/2010 9:47:26 PM , Rating: 2
quote:
Culurciello and LeCun


I suppose I might be the only reader that mentally substituted "Cthulhu and LeChuck" for my own amusement.




RE: self-amusement
By ians55 on 9/17/2010 1:42:24 PM , Rating: 2
This is epic!!!


Toyota
By The Raven on 9/17/2010 9:45:40 AM , Rating: 2
I hope my parent company Toyota gets right on this one. Thanks to the media, I'm sure everyone will trust them to implement this technology first. I mean if recent history has taught us anything is that we can't trust computers in cars.




RE: Toyota
By ians55 on 9/17/2010 1:31:31 PM , Rating: 2
You definitely can trust more to the drunk buddy on the next lane.


which sex?
By danrien on 9/21/2010 10:53:46 AM , Rating: 2
Is it based on a male or female driver? Just wondering....




RE: which sex?
By YashBudini on 9/27/2010 10:19:42 PM , Rating: 2
I don't recall caring what gender the person was while they were texting and driving straight into my vehicle.


"The whole principle [of censorship] is wrong. It's like demanding that grown men live on skim milk because the baby can't have steak." -- Robert Heinlein














botimage
Copyright 2014 DailyTech LLC. - RSS Feed | Advertise | About Us | Ethics | FAQ | Terms, Conditions & Privacy Information | Kristopher Kubicki