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

Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

spectrum.ieee.org

Post reply on HN
Print view View original

31–40 of 70 posts

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#31

Post by rm_-rf_slash »

peterwwillis wrote: post #25
rm_-rf_slash wrote: post #18

Earlier quoted context omitted.

A cow kicked a lantern and burned down Chicago. A powerful and incensed AI could destroy the foundations of global society before we would even know what's going on.

What does that have to do with a soul, whether one exists, or whether we care? A powerful and incensed President could order a nuclear strike that could end civilization as we know it. Why the concern over a theoretical intelligence that could theoretically have emotion and theoretically have so much power it could theoretically do the same?

It's hard work to become president. It is much easier to build software that can be hacked to cause far greater devastation than things can be built. Presumably an AI can hack better than humans.

It doesn't matter what we define as a soul, it is the relationship humanity will have with artificial intelligences that matters. If we don't ask these questions, our children will wish we had...if they're still around.

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#32

Post by marvin »

duaneb wrote: post #14
ryanjshaw wrote: post #2

I always thought this was the only way to build a true AI -- build a 'virtual baby' that has to go through much the same experiences as a human baby. I'm sure this idea has been explored somewhere already - anybody have any pointers?

> true AI What does this even mean?

You can define general artificial intelligence in many ways. This is probably not comprehensive, but "an artificially constructed agent that is capable of solving a wide variety of tasks in a wide variety of different environments, doing this to successfully achieve some stated goal" should cover it.

Add a clause for mostly being at least as capable of doing this as an average human, if you want to be sure. At the moment this is closer to a philosophical idea than an actual scientific possibility, but science usually makes its biggest advances at the edge of philosophy. This is also where we can get an idea of the high-level problems that need to be solved. Think the idea of manned space exploration before the advent of rocketry, for instance.

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#35

Post by chriswarbo »

jing wrote: post #7

Are physics engines not yet accurate enough to enable "virtual" pre-training / full training of the networks, lighting conditions, etc? If they are, exclusively using physical robots seems somewhat inefficient.

Closest thing I can think of is Hod Lipson's self-modelling robots: http://www.creativemachineslab.com/self-modeling.html

Their system evolves a virtual body which is evaluated by comparing its predicted behaviour (e.g. if motor A is rotated by X degrees, sensor B should get response Y) to real physical movements (moving motor A and reading sensor B). Once an accurate virtual body has been made, it's used to evaluate a bunch of (again, evolved) movement styles in simulation. Once an efficient style has been found, it's used to control the physical motors on the robot.

Also related, their lab has a "universal gripper" made out of a balloon filled with coffee granules: http://creativemachines.cornell.edu/positive_pressure_grippe...

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#36

Post by jonnycowboy »

iandanforth wrote: post #22
tgflynn wrote: post #15

Earlier quoted context omitted.

That's a very interesting question. My guess is that the physics of grabbing things, especially non-rigid things, is very messy and difficult to simulate. It would be great if someone here were able to give a detailed answer to this question though.

Ok here goes. 1. The best / most recent attempt at this was for the DARPA robotics challenge and the Gazebo simulator. This was still very buggy and prone to hilarious / depressing physics. 2. Almost all game physics engines start from rigid body and slap on particles, deformables, etc. An exciting counter example to this is nVidia Flex which starts with unified particle simulation (much closer to molecular dynamics…

I agree with all the points you made but in addition I would add another - with external cameras for positioning and movement feedback, you don't need to have accurate geartrains or encoders nor have a rigid robot. Since the localization is all in software (and software is scalable/free from Google's standpoint) there are potentials for lots of weight and cost savings on the hardware side. Kind of like my robot: https://github.com/jonnycowboy/YARRM

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#38

Post by rm_-rf_slash »

JoeAltmaier wrote: post #30
peterwwillis wrote: post #28

Earlier quoted context omitted.

There are plenty of organisms on the planet that co-exist with more powerful ones and they don't attempt to wipe out the other. There would need to be such fierce competition over natural [or unnatural] resources that only one of the two organisms could exist, and then competition would give rise to a potential outcome of one extinguishing the other. Your question is simply an irrational fear, probably on the order o…

Plenty of biological organisms. That have niches in the biosphere. But this new life is/has neither. It could decide to cannibalize the earth to fuel a spacefaring civilization for instance. Not an irrational fear.

Or perhaps more simply, eradicate humanity to ensure the survival of the planet. Crude but effective. And final.

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#39

Post by rm_-rf_slash »

peterwwillis wrote: post #28
rm_-rf_slash wrote: post #23

Earlier quoted context omitted.

I have long believed that we aren't going to get an AI that matches biological intelligence until it has to fend for itself. Nearly every biological function is linked to the fundamental need to survive through scarcity in hostile environments in order to reproduce and pass along genetic material. Without that need, there would not have been such rigorous evolutionary arcs that ultimately brought humans to this earth…

There are plenty of organisms on the planet that co-exist with more powerful ones and they don't attempt to wipe out the other. There would need to be such fierce competition over natural [or unnatural] resources that only one of the two organisms could exist, and then competition would give rise to a potential outcome of one extinguishing the other. Your question is simply an irrational fear, probably on the order o…

The Animatrix basically did what you suggested and said the first robots lived in a plot of middle eastern desert set aside for them. After a hundred years their overwhelming superiority made them the dominant economy and global superpower, and as people's living standards began to decline, they fought back.

Re: Google Wants to Solve Robotic Grasping by Letting Robots Learn for Themselves

#40

Post by zellyn »

jing wrote: post #7

Are physics engines not yet accurate enough to enable "virtual" pre-training / full training of the networks, lighting conditions, etc? If they are, exclusively using physical robots seems somewhat inefficient.

Yes, for some things. http://arxiv.org/pdf/1603.01312.pdf
Post reply on HN