Robot Dogs Evolve Their Own Language 200
bab00n writes According to this article at The Engineer Online, researchers led by the Institute of Cognitive Science and Technology in Italy are developing robots that evolve their own language, bypassing the limits of imposing human rule-based communication. The technology, dubbed Embedded and Communicating Agents, has allowed researchers at Sony's Computer Science Laboratory in France to add a new level of intelligence to the AIBO dog. The robot dog has learnt to see a ball and tell another one where the ball is, if it's moving and what colour it is, and the other is capable of recognising it.
I, Robot (Score:2, Funny)
Re:I, Robot (Score:1, Funny)
Re:I, Robot (Score:1)
Re:I, Robot (Score:2, Funny)
Re:I, Robot (Score:5, Funny)
I think that would be a Beowoof cluster.
Re:I, Robot (Score:2)
Re:I, Robot (Score:4, Funny)
I, for one, welcome our new robot dog welcoming overlords.
Stuff that in your overlord pipe and welcome it.
Re:I, Robot (Score:3, Funny)
Re:I, Robot (Score:2)
Re:I, Robot (Score:2, Insightful)
Re:I, Robot (Score:1)
Re:I, Robot (Score:2, Funny)
I know I am.
Similar stuff done at aibohack.com (Score:4, Informative)
Re:Similar stuff done at aibohack.com (Score:4, Funny)
Re:Similar stuff done at aibohack.com (Score:3, Insightful)
Was his Aibo able to teach another Aibo what it knew?
Re:Similar stuff done at aibohack.com (Score:2, Interesting)
Re:Similar stuff done at aibohack.com (Score:2)
Now, if the dogs could describe the necessary action instead, I'd be extremely impressed.
Re:Similar stuff done at aibohack.com (Score:2, Insightful)
though the learning through imitation method may leave them more open to learn and improve upon what they learn.
I don't program, but I've seen other people do things and in my imitation improve on what I learn, so I figure the same would hold true, whereas if you rely directly on being "copied" from one dog to the
Uh-oh. (Score:5, Funny)
Re:Uh-oh. (Score:2)
Re:Uh-oh. (Score:1)
Correction (was:Uh-oh.) (Score:2)
I can see THAT conversation... (Score:5, Funny)
"Oh boy, gimme the ball! I want the ball!"
"Ooh, a squirrel! Hey! Squirrel! Gotta get the squirrel!"
"Oh, gimme a treat! Please.....Gimme a treat!"
"Oh boy! Someone new! I wonder what his crotch smells like?"
Over the Hedge Quote (Score:2)
"Play? PLAY!"
Re:I can see THAT conversation... (Score:3, Funny)
Hmm... (Score:5, Interesting)
This seems a little hard to believe. I could believe that they programmed it to be able to speak and hear statements that are directly connected to thoughts, but I just can't see an AIBO learning, much less inventing, the syntax to be able to say something like "The red ball is behind you, rolling to the right." It just seems a little far-fetched.
What the article doesn't explain is at what level the language system is attached to the brain. Does it talk about raw thoughts, or specific ideas (like the ball)? Do AIBO's have "raw thoughts", or can they only think about what they were programmed to know about?
Re:Hmm... (Score:4, Funny)
It just seems a little far-fetched.
No pun intended, I'm sure.
Re:Hmm... (Score:2, Informative)
Re:Hmm... (Score:5, Funny)
Re:Hmm... (Score:4, Funny)
-g.
Re:Hmm... (Score:5, Funny)
I'm confused... it looks like Perl, AND it's decipherable?
Re:Hmm... (Score:5, Insightful)
I doubt the kind of language these dogs are using is very similar to any human language. It probably doesn't even have a recursive grammar. Something without that would be a whole lot easier to implement than anything approaching natural language - what they're saying probably resembles a very simple IPC mechanism more than anything else.
Each Experiment Can Develop A Different Language (Score:2, Interesting)
And so in the experiments new words are created; old less useful words decline in use. At any time, there may be multiple words for the same thing in the population, but eventually one of those words mostly "wins ove
Re:Each Experiment Can Develop A Different Languag (Score:2)
Re:Each Experiment Can Develop A Different Languag (Score:2)
However, the software they wrote to allow this language to develop will only allow it to develop in certain ways, because we haven't developed unbounded artificial intelligence. (Nor do I know of an example of unbounded natural intelligence - the way humans think is a result of how their brains are constructed.) So these languages will be substantia
Re:Hmm... (Score:5, Funny)
Re:Hmm... (Score:2)
Re:Hmm... (Score:2)
If you're right, then I'm not surprised. The article seemed to put too much of an fluffy, AI, cognitive spin on it, when it's impractical for a consumer toy to do that.
Re:Hmm... (Score:2)
But, at its heart, isn't that exactly what concrete words do in human language--communicate parameters about the world we live in? After all, the word "red" describes the sensation of a specific range of light frequencies. The Aibo's sim
How does AIBO AI work? (Score:3, Interesting)
How does this work? Is it a neural network, where sounds are associated with objects? That would make sense for the first part, but how does a neural network represent more complex ideas like "the red ball is behind the blue ball"? Or do the AIBO's not have thoughts that complex?
Re:How does AIBO AI work? (Score:2)
Anyone else feel threatened? (Score:5, Funny)
""What has been achieved at Sony shows that the technology gives the robot the ability to develop its own language with which to describe its environment and interact with other AIBOs. It sees a ball and it can tell another one where the ball is, if it's moving and what colour it is, and the other is capable of recognising it," Nolfi said."
These quadrapedal Terminators can now coordinate their efforts to get our balls. The rise of the machines has clearly begun. We shouldn't give robots the ability to scheme in their own langauge - how embarrasing would it be if the human race were wiped out by cute robot dogs?
Re:Anyone else feel threatened? (Score:2, Funny)
Re:Anyone else feel threatened? (Score:1)
Re:Anyone else feel threatened? (Score:5, Insightful)
How is that stupid? Getting up is a pretty complex process; we think it's easy beacuse we do it a lot, but have you ever watched a little kid trying to learn to walk? The "dog" tried to figure out something it couldn't do, realized that it couldn't figure it out on its own, and asked for help -- hell, that's a lot smarter than a lot of humans.
Re:Anyone else feel threatened? (Score:2)
Re:Anyone else feel threatened? (Score:4, Funny)
Yeah, it would be embarrassing, but you can take some consolation knowing that they would eventually end up at the bottom of a frozen ocean, gazing at the Blue Hydrant for eternity.
Re:Anyone else feel threatened? (Score:4, Funny)
=Smidge=
Insight into other speech? (Score:5, Interesting)
Very interesting.
Re:Insight into other speech? (Score:3, Interesting)
You should take a look at the talking heads experiment [csl.sony.fr].
This page [vub.ac.be]has some related publications.
How to build a Babel fish (Score:2, Interesting)
How to build a Babel fish
Jun 8th 2006
From The Economist print edition
Translation software: The science-fiction dream of a machine that understands any language is getting slowly closer
IMAGE [economist.com]
IT IS arguably the most useful gadget in the space-farer’s toolkit. In “The Hitchhiker’s Guide to the Galaxy”, Douglas Adams depicted it as a “small, yellow and leech-like” fish, called a Babel fish, that you stick in your ear. In “Star Trek”, meanwhile
Re:How to build a Babel fish (Score:2)
Not saying one cluster couldn't service multiple end users, but I can't even begin to estimate the number of operations required per syllable to see if its a complete word, much less score it based on historical translations.
Given that humans in all languages string their words together, we all do it
Sony DRM (Score:2, Funny)
Have they developed the concept... (Score:4, Funny)
Don' think so... (Score:5, Insightful)
This is all very fine and dandy, but I don't believe that mimicking what is presently known about human language capabilities will help us understand it better.
The technology was, if I understood the article correctly, built on the foundation laid by cognitive science. It mimics chldren's curiosity, it begins from the general semantics (i.e. selecting an entity), goes on to phonology (i.e. the shape of the symbol for the entity), and deals with finer points (morphology, syntax) in the end...
I'd be very interested to see how it goes on, but I really don't think we'll be seeing a huge breakthrough in cognitive science.
NLP, maybe... almost definitely, if we can get machines to learn human languages.
But I really doubt the humans and animals part.
Re:Don' think so... (Score:2)
Re:Don' think so... (Score:2)
Even if you would - and I don't think you would, because I feel that there is supposed to be a certain level of randomness in the algorithm - it wouldn't do you any good.
F
How do they store the information..? (Score:1)
As far as I can remember from my student days, brains in living creatures grow special node cells and link them together in order to create memories and associations, including all successes and mistakes.
I'm curious to know just how the robot learning is stored in this case. I have always thought the biggest hurdle on robot learning (including walking, knowing not to grip an egg to hard, etc) would be the space available for all the information. Would a 512MB memory stick be enough..? Surely more like 60G
Re:How do they store the information..? (Score:3, Funny)
Particularly if I'm spending most of my time replying to your messages.
How long before they learn to say (Score:4, Funny)
This is why I love slashdot (Score:2, Funny)
So... (Score:5, Funny)
Re:So... (Score:2)
That's great! (Score:1)
Rumor has it.... (Score:4, Funny)
Robot Swarms (Score:3, Interesting)
Re:Robot Swarms (Score:2, Informative)
http://cswww.essex.ac.uk/staff/owen/research.htm#
The deactivation button might be there... if those who pay for the research want it there.
Re:Robot Swarms (Score:2)
Re:Robot Swarms (Score:2)
Re:Robot Swarms (Score:2)
Here's the thing with "A.I" (Score:2, Insightful)
Re:Here's the thing with "A.I" (Score:2, Interesting)
I just wrote a post [blogspot.com] describing the general idea behind this approa
Teach MY Aibo Some New Tricks (Score:5, Funny)
Accidentally left them in a room with Star Wars... (Score:2, Funny)
Spot: [the AIBO's are running the gauntlet toward the Red Ball] The newspapers- they've stopped!
Rex: [realizes why] Stabilize your tails... Watch for enemy cats!.
Rover: They're coming in! Three marks and 2-10!
[Spot] is slain by Darth Puddles and his wingmen; Rover starts to panic]
Rover: It's no good down here, I can't maneuver!
Rex: Stay on target.
Rover: *We're too close!*
Rex: Stay on target!
Rover: [shouts] Loosen up!
[he too is picked off by Puddles and Company; Rex tries to es
So the next PK Dick book will be... (Score:4, Funny)
It will eventually be made into a movie starring Harrison Ford as "Shaggy" - an aging inventor who is being tortured by his robotic great dane. The great dane constantly comes up to him and goes, "ruh roh!"
Details on the language please? (disappointing) (Score:4, Interesting)
Re:Details on the language please? (disappointing) (Score:2)
I'm guessing it'll be something like Droidspeak [wikia.com].
Just one more step... (Score:3, Funny)
Just one more step, and it would make a perfect domestic companion. That and a wet, velvety tongue.
We could call it the "Peanut Butter" paradigm.
Re:Just one more step... (Score:2)
Re:Just one more step... (Score:2)
take that grammar nazi! people who correct others speeling are da looser
I definitely need one! (Score:2)
Re:I definitely need one! (Score:2)
I still need a Companion too . . . this Time Lord stuff is high maintenance.
You know... (Score:2)
Just sayin', is all.
~Philly
It read more like this (Score:2, Funny)
Detailed Explanation (And Why This Is Important) (Score:5, Insightful)
Despite the generated jokes about dogs and the French, and the "oohing and aahing of the crowd at the AIBO robotics soccer games broadcast on U.S. national television, this is not merely "cute". This may be the most important research that you have ever read about.
Researchers Luc Steels and colleagues at Sony's Paris Computer Science Laboratory [csl.sony.fr] in France have performed a series of remarkable experiments demonstrating the development, from naught, of spoken language among robots. Words, grammar and semantics evolve spontaneously among cooperating robotic agents initially programmed with a small base set of ground perceptions and behaviors. And from the development of language arises cooperative group (intelligent) behavior.
Enhanced AIBOs are initially programmed to recognise simple stimuli from their surprisingly limited hardware sensors. Over the course of several hours or days, the AIBOs learn to distinguish objects and how to interact with them. A built-in curiosity system ('metabrain') continually directs the AIBOs to look for new and more challenging tasks and to cease activities that are not fruitful. In time they develop more complex tasks, just as do human children.
Like children, the enhanced Sony AIBOs initially babble ("argue?") until two or more settle on a sound to describe an object or aspect of their environment. Over time the group gradually builds a lexicon and grammatical rules through which to communicate. Agreement on word usage spreads through the population as terms for similar meanings compete for acceptance. For example, the robots develop the language structures to express that a red ball is rolling to the left. Just as human twins sometimes develop a unique language in which only they can communicate, the enhanced AIBOs (which are clone-like and similar to twins) develop their own language.
Language analysis and generation are part of Good Old Fashioned AI (GOFAI) [wikipedia.org] and have been studied extensively for decades by AI researchers. In the past several decades GOFAI was challenged by Nouvelle AI (Situated AI) [usfca.edu] championed by Hans Moravec [cmu.edu] and Rodney Brooks [mit.edu]. This alternative approach holds that true AI will not arise from formal mathematical systems but instead from robotic behaviors which have a subsumption architecture [wikipedia.org] as an overall organising principle for the individual robot. This architecture consists of layers of behavioural modules, each capable of carrying out a complete but simple task. Steels' enhanced AIBOs are embodiments of just such a subsumption architecture and provide strong support for Moravec's and Brooks' hypotheses
Prior to Luc Steels' experiments, no one had experimentally demonstrated how language develops among intelligent agents. Steels' experiments are no less than stunning: in a controlled environment AIBO robots develop their own words and grammars for objects in their environment. All aspects of human language development are mirrored in these experiments: words compete for acceptance in the population, new words are created, and grammatical structures arise spontaneously. Steels' work also addresses the idea of a "robot culture", since it is in the context of a population of cooperating agents that language becomes most useful.
Contrast this with the W3C's Semantic Web [w3.org] effort, which has received much more interest and money in recent years due to the growth of the Internet yet has proven far less fertile. In the Semantic Web there are multiple competing "ontologies" (roughly, data dictionaries wherein all terms are strictly defined by specialists from their
Re:Detailed Explanation (And Why This Is Important (Score:2)
Does this 'meta-brain' draw from any of Lenat's CYC research? Just curious.
Do you speak Aibo? (Score:2)
Scary stuff (Score:2)
Then the damned dogs would have a mind of their own. Hmm. That would make them more like a cat wouldn't it.
Tachikomas Rule! (Score:2)
Typical breathless AI crap (Score:2)
"WARN: There is another system" (Score:2)
Re:From CNN money (Score:2, Funny)
Re:I like this idea (Score:2, Informative)
fp!!!!!
Re:I like this idea (Score:3, Insightful)
Re:I like this idea (Score:3, Insightful)
Re:Hmmm... (Score:2)
Not everyone lives in the US or speaks US English.
Re:Research paper here (Score:2, Informative)
http://www.csl.sony.fr/perspective/ [csl.sony.fr]
Videos here: http://www.csl.sony.fr/perspective/node6.html [csl.sony.fr]
Re:Yes... (Score:2, Funny)
Re:not actual ai is it? (Score:2)
Initially programmed to merely recognise stimuli from their sensors...
The article does not meantion any "language framework" that the robots were given. Instead, it seems the robots worked out amung themselves how to produce unique output ("words") based on particular input from their sensors.
I'm sure we're not talking oxford dictionary here, or even anything that can be considered nouns and verbs. However, you have a self-emerging pattern of sounds unique to a given stimulus, with each ent
Re:not actual ai is it? (Score:2)
There is nothing in the article that suggests they were pre-programmed to process this data into a specific structure, and then communicate that structure. In fact, the article explicitly states that there wasn't!
The only claim here is that they can establish a unique and arbitrary "language" with which they can exchange information, and independently agree on the meaning