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

61–70 of 70 posts

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

#61

Post by bgalbraith »

iandanforth wrote: post #56
bgalbraith wrote: post #55

Earlier quoted context omitted.

Ideally, yes, we want to pre-train in a virtual environment using as close to the real model robot as possible. I worked on such a problem as part of my PhD research on mobile robots using the Webots simulator ( https://www.cyberbotics.com/overview ) as my virtual environment. In my case, I was working on biologically-inspired models for picking up distant objects. It's impractical to tune hyperparameters in hardware…

How hot did that first dynamixel get?

Only overheated once, though I rarely had them operating continuously for more than a few minutes at a time.

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

#62

Post by pixl97 »

duaneb wrote: post #44
marvin wrote: post #32

Earlier quoted context omitted.

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 mo…

I dunno, there are plenty of humans that wouldn't make it to AI classification by that measurement, so I'm a skeptical to say the least. I don't think any of us are going to see past the uncanny valley of human-computer interaction—computers will have their tasks, but they'll be just that—task solvers. Why make it more magical than that? It's a waste of money to try, too—much of what makes humans unique isn't really…

>like giving up on problems because you're bored

That is actually one of the more useful things a computer can do. It is also one of the hardest to program (see the halting problem). It is very useful for a computer for a computer to be able to do that when it has to pick out millions of likely candidates from quadrillions of possible answers.

>but they'll be just that—task solvers. Why make it more magical than that?

So you're in the 'people are magic' camp. You'll be very disappointed when you learn that people are just billions of years of bio-chemistry left to run rampant and that electro-mechanics and reproduce the same thing.

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

#63

Post by argonaut »

pixl97 wrote: post #60
argonaut wrote: post #58

Earlier quoted context omitted.

The Animatrix is also a work of fiction.

So are robots that are smarter than people.... so far. There are no trilobites around either.

When you say "so far," you should at least recognize that you are making a speculative guess that is completely unfalsifiable.

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

#64

Post by p1mrx »

rm_-rf_slash wrote: post #38
JoeAltmaier wrote: post #30

Earlier quoted context omitted.

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.

Nothing is final. Even without humans, the Earth will be engulfed by the sun in a few billion years.

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

#65

Post by JoeAltmaier »

peterwwillis wrote: post #47
JoeAltmaier wrote: post #30

Earlier quoted context omitted.

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.

Non-organic organisms would still require the biosphere to self-propagate on earth. Currently they need organic and inorganic matter to operate. Assuming they stayed purely mechanical constructs, they would need the byproducts of the earth to maintain themselves, and there are limits to those byproducts and the rate at which they can be produced, not to mention the rest of the biosphere that supports their production…

You said it yourself: either get away from the homicidal monkeys, or hey! just get rid of the monkeys. Anyway its a given that mechanical constructs can adapt dramatically faster than biological - they just reprogram themselves.

Because we don't know the probability these things would be 'matricidal' does in no way justfity a 50-50 statistic. I'd say, we must be very, very careful not to. Its not at all clear what the long-term goals of a device designed to be our slave would be. Of course nobody would intentionally design it to be a threat to our civilization. The entire notion is, that our society is actually not considering long-term results of anything else; this would be just like all the rest of our inventions: agriculture, fracking, indiscriminate travel and population mixing (providing unlimited disease vectors), politics, money and on and on.

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

#66

Post by jonnycowboy »

rboyd wrote: post #48
jonnycowboy wrote: post #36

Earlier quoted context omitted.

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: http…

I was hoping to use a robotic arm for a project I'm working on, and wondering if you guys could answer a question about motors. In my very limited research it looked like one of the factors that make the industrial (kuka, etc) robots so expensive was that they use backlash-free motors. What does that even mean? I also saw a couple startups aimed at sub-$5k robots (like carbon.ai). Are they solving this problem in som…

I think you mean backlash-free gearboxes (ie: cable driven gearboxes, harmonic drives or spring-loaded gearboxes that always apply a minimal but constant tension).

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

#67

Post by duaneb »

pixl97 wrote: post #62
duaneb wrote: post #44

Earlier quoted context omitted.

I dunno, there are plenty of humans that wouldn't make it to AI classification by that measurement, so I'm a skeptical to say the least. I don't think any of us are going to see past the uncanny valley of human-computer interaction—computers will have their tasks, but they'll be just that—task solvers. Why make it more magical than that? It's a waste of money to try, too—much of what makes humans unique isn't really…

>like giving up on problems because you're bored That is actually one of the more useful things a computer can do. It is also one of the hardest to program (see the halting problem). It is very useful for a computer for a computer to be able to do that when it has to pick out millions of likely candidates from quadrillions of possible answers. >but they'll be just that—task solvers. Why make it more magical than that…

> So you're in the 'people are magic' camp.

...how are you extrapolating that from anything I said? All I mean is that "AI" is inherently meaningless. When you ground it in reality there are more useful terms that are meaningful.

Also, I meant to point out that large parts of the brain's chemistry are not useful to emulate, leading me to question using humans as a base for "intelligence" comparison

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

#68

Post by makip »

peterwwillis wrote: post #11
alan_cx wrote: post #8

Earlier quoted context omitted.

If that were to happen, I would suggest that an artificial "soul" could or would be created. Once you have that on your hands, things being to get interesting. Ethics, religion law, and so on will have one hell of a job on their hands. Especially when you consider that there would be immediate and obvious military applications.

Do animals have souls, and do we care?

A fascinating account of how a wide range of species exhibit sophisticated intelligent behaviour we normally only ascribe to humans.

http://www.nybooks.com/articles/2015/10/08/amazing-inner-liv...

We can't know whether animals have a soul any more conclusively than we can know that about ourselves. But it's arguable that one is not less probable than the other.

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

#69

Post by duaneb »

jlarocco wrote: post #53
marvin wrote: post #32

Earlier quoted context omitted.

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 mo…

I think a big part of "true AI" is the ability to learn knew things. AlphaGo, for example, can only play Go. It's never going to learn to play Poker, Scrabble, or Doom, without being completely reprogrammed.

But even humans can't always learn new things—at least not well.

It seems to come down to being able to interpret language in a way that is broadly within the range of a human's ability to agree with another human on the meaning of a phrase.

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

#70

Post by aminok »

tnecniv wrote: post #49
aminok wrote: post #43

Earlier quoted context omitted.

We care if an animal is intelligent, because then it is sentient like us, and has rights.

Why does it have rights? Why do we have rights? Which rights do we have?

That's how perceive things. It's judged by us as the best way to secure our own interests. It can be seen as a pact between intelligent creatures to shown each other mutual respect.
Post reply on HN