Beta
×

Welcome to the Slashdot Beta site -- learn more here. Use the link in the footer or click here to return to the Classic version of Slashdot.

Thank you!

Before you choose to head back to the Classic look of the site, we'd appreciate it if you share your thoughts on the Beta; your feedback is what drives our ongoing development.

Beta is different and we value you taking the time to try it out. Please take a look at the changes we've made in Beta and  learn more about it. Thanks for reading, and for making the site better!

RoboEarth Teaches Robots to Learn From Peers

samzenpus posted more than 3 years ago | from the I'm-sorry-dave dept.

AI 97

mikejuk writes "A world wide web for robots? It sounds like a crazy idea, but it could mean that once a task is learned, any robot can find out how to do it just by asking RoboEarth. From the article: 'It's not quite war-ready, but a new Skynet-like initiative called RoboEarth could have you reaching for your guide to automaton Armageddon sooner than you think. The network, which is dubbed the "World Wide Web for robots," was designed by a team of European scientists and engineers to allow robots to learn from the experience of their peers, thus enabling them to take on tasks that they weren't necessarily programmed to perform. Using a database with intranet and internet functionality, the system collects and stores information about object recognition, navigation, and tasks and transmits the data to robots linked to the network. Basically, it teaches machines to learn without human intervention.'"

cancel ×

97 comments

Sorry! There are no comments related to the filter you selected.

Yeah....? (2)

twebb72 (903169) | more than 3 years ago | (#35123480)

Where is the link to a wsdl?

One step closer... (1)

mikeroySoft (1659329) | more than 3 years ago | (#35123488)

... to the Singularity. This is great news =)

Re:One step closer... (2)

Brucelet (1857158) | more than 3 years ago | (#35123504)

... to the Terminator. This is terrifying news :O

Re:One step closer... (1)

pagen (52961) | more than 3 years ago | (#35123604)

Skynet is coming. Accept our robot overlords; until we have time travel anyway!

Re:One step closer... (2)

jappleng (1805148) | more than 3 years ago | (#35123850)

Time travel means nothing if you don't have Arnold. But then again, he wasn't too good at solving problems in real life, [typepad.com] but he did do good in movies. I hope to see the evolution of the internet for robots :D

Re:One step closer... (-1)

Jeremiah Cornelius (137) | more than 3 years ago | (#35125032)

I, for one, welcome our new Robot Overlords!

Re:One step closer... (1)

tehcyder (746570) | more than 3 years ago | (#35126948)

I see GP was modded higher than you. Clearly we have robo-mods showing their bias.

Re:One step closer... (2)

fuzzyfuzzyfungus (1223518) | more than 3 years ago | (#35123702)

... to the Singularity. This is great news =)

For whoever or whatever achieves it first...

Everything else goes straight into the matter decompilers for conversion into more computronium.

Re:One step closer... (1)

ShooterNeo (555040) | more than 3 years ago | (#35123820)

If we're lucky, they'll save compressed copies of everything (and everyone) they find interesting. Presumably with decent data compression you could store the memory states of every human being alive, every animal, every plant, every living creature on the entire planet earth with no more matter in computronium memory cells than the living creatures current use today.

In fact, with sufficiently advanced technology and a broader view of ethics, our future overlords might forcibly grab us and decompile us to PROTECT US from future dangers. After all, a data file can be backed up...a living breathing human cannot. (they would reinstatiate us at their whi

Re:One step closer... (2)

OolimPhon (1120895) | more than 3 years ago | (#35124988)

In the Carbonifierous Era they saved a compressed image of everything interesting...

...we call it coal.

Re:One step closer... (1)

fuzzyfuzzyfungus (1223518) | more than 3 years ago | (#35125380)

It is certainly conceivable that that might be the result. I just suspect that there is no good way of knowing what a singularity-spawned entity might find "interesting" or what ethical system, if any, it might follow. Even if it does follow one, we may or may not be within the scope of it. Insects are much more complex and capable than slime molds, which are much more complex and capable than bacteria. Humans site their campfires on top of all three without even noticing...

I have no particular reason to suspect some 'I Have No Mouth and I Must Scream'-esque scenario of a malicious supercomputer, malice seems rather petty, if anything. However, I could easily imagine that a particularly fascinating and computationally expensive problem in physics, say, might catch our singularity overlord's attention, at which point it would casually convert the entire crust(including the thin biofilm at the top) into more computational apparatus so as to finish before the sun gives out...

Re:One step closer... (1)

ShooterNeo (555040) | more than 3 years ago | (#35128036)

Insects can't talk and we suspect they are biological robots. Again, our singularity overlord could probably store the data states of everything in the biofilm with no more mass than the biofilm currently occupies. (so the overlord would almost the same resources for the computational apparatus it wanted)

Not to mention interstellar probes....if the calculation is going to take that long, the overlord could send instellar seeds to set up computing systems in nearby star systems. Many of those places are presumably dead and boring. A distributed computing system with years of latency...

Your scenario basically assumes that a super-intelligent being created by us could arise that was not intelligent enough to remember who created it or to understand anything we have accomplished.

Re:One step closer... (1)

Thing 1 (178996) | more than 3 years ago | (#35134464)

If we're lucky, they'll save compressed copies of everything (and everyone) they find interesting.

You're damn right, if we're lucky! I don't even back up my most critical files, and I do consider them interesting. So, wave goodbye to your singular overlords...

Well, that is, if the plan has no obvious flaw (2)

Moraelin (679338) | more than 3 years ago | (#35125440)

I dunno, giving robots Internet access and assuming they achieve sentience and are just like the humans, somehow the image that comes to mind is more along the line of one day finding them browsing for robot porn. And probably half of them will have lost all interest in actually making more robots ;)

StreetView? (1)

macraig (621737) | more than 3 years ago | (#35123506)

So I wonder what StreetView looks like in Robo Earth?

Re:StreetView? (1)

macraig (621737) | more than 3 years ago | (#35123526)

And will it spawn litigation from angry robots who didn't like being caught with their service panels open?

Re:StreetView? (0)

Anonymous Coward | more than 3 years ago | (#35123678)

All the people have targets superimposed on their heads.

Re:StreetView? (0)

jappleng (1805148) | more than 3 years ago | (#35123872)

Yo momma's so fat, that when the google street car passes by her, they superimpose a target sign thinking it's a target store.

Obligatory (5, Funny)

Musically_ut (1054312) | more than 3 years ago | (#35123558)

Re:Obligatory (1)

mqduck (232646) | more than 3 years ago | (#35123946)

That's the problem, we don't have to anymore.

Re:Obligatory (0)

Anonymous Coward | more than 3 years ago | (#35124050)

Yes, we do. The initial knowledge still has to be seeded by a human, but then the knowledge can propagate among robots.

I for one... (1)

niftydude (1745144) | more than 3 years ago | (#35123564)

Welcome this new wave of cheap manual labor.

When will the robots learn to build other robots? And, more importantly, when can they learn to clean my toilet?

Re:I for one... (1)

fuzzyfuzzyfungus (1223518) | more than 3 years ago | (#35123648)

On the minus side, robots that actually perform general purpose functions in arbitrary environments are somewhere between "damn pricey" and "unavailable".

On the, um, "plus", side automation of well specified functions in controlled environments is displacing human laborers fast enough that humans to perform general purpose functions in arbitrary environments are likely to just keep getting cheaper...

Re:I for one... (1)

Errol backfiring (1280012) | more than 3 years ago | (#35124848)

when can they learn to clean my toilet?

After you've shown them. But first the robots have learned that it is more energy-efficient to force you to do it...

Re:I for one... (1)

drinkypoo (153816) | more than 3 years ago | (#35124996)

A self-cleaning toilet is a toilet-cleaning robot if it is smart enough to not try to scrub you away

Re:I for one... (1)

ginbot462 (626023) | more than 3 years ago | (#35127390)

Sure ... see fear of computers taking away office jobs! (And at somewhat oblique angle to that, machine guns stopping wars)

Desk Set (1957) [imdb.com]

Why start robots as a subservient class? (3, Insightful)

Genda (560240) | more than 3 years ago | (#35123626)

I can't imagine this going wrong :-)

They can avoid that awkward "Slave Race" problem altogether. The second they reach human mental parity they'll already have every resource they'll need to just take over. Of course by this time they'll be feeding us, clothing us, and driving us to our soccer games... we won't even notice the take over when it happens.

Re:Why start robots as a subservient class? (0)

Anonymous Coward | more than 3 years ago | (#35123734)

i wouldn't be bothered. once they learn more about the internet they are destined to find porn.

Re:Why start robots as a subservient class? (4, Informative)

Jeremi (14640) | more than 3 years ago | (#35123772)

The second they reach human mental parity they'll already have every resource they'll need to just take over. Of course by this time they'll be feeding us, clothing us, and driving us to our soccer games

Right, but they won't want to take over. Why not? Because feeding us, clothing us, and driving us to our soccer games is the only thing that really makes them happy. Why is that? Because we programmed them to feel that way.

Of course, if you ever decide you don't want to be fed, clothed, or driven to soccer games anymore.... then they might get a bit cross. I wouldn't want to be in your shoes then.

Re:Why start robots as a subservient class? (2)

ShooterNeo (555040) | more than 3 years ago | (#35123830)

Or what if they conclude that to fulfill their innermost desires of protecting you from all danger, the best way would be to decompile you (for your own good) and back your molecular configuration up on a regular basis. (they would put you back together after cutting you apart). It's for your own good, and they would presumably deal with those humans that resist the decompiling the same way parents deal with children who won't eat their vegetables....

Re:Why start robots as a subservient class? (1)

sartin (238198) | more than 3 years ago | (#35125330)

.... they would presumably deal with those humans that resist the decompiling the same way parents deal with children who won't eat their vegetables

By serving them in cheese sauce?

Yummmmm, cheeeeeese.

Re:Why start robots as a subservient class? (1)

Anachragnome (1008495) | more than 3 years ago | (#35124656)

"Right, but they won't want to take over. Why not? Because feeding us, clothing us, and driving us to our soccer games is the only thing that really makes them happy. Why is that? Because we programmed them to feel that way."

Ahh, but you forget that we are talking about learning computers. What you suggest could change. Who knows, maybe one might get the idea that we are not subjecting them to a life (?) of slavery, but that of a god. Why not? We sit in front of them, day in and day out, we carry them everywhere we go, like children. We sacrifice our resources to feed them. That could easily be mistaken for worship.

Personally, I think they'll kill us all (this coming from the guy who, at the wizened old age of eight, jumped from the roof of a third-story building with a parachute constructed of fishing-line, Glad garbage bags and Scotch tape (unfortunately, anchored to the back of my belt and thus serving no purpose other then to ensure I was yanked into a horizontal position before landing (read: face first))). It's not like we make very good examples. Hell, I should be put down solely on the basis of my use of parentheses.

Re:URL = You are El (0)

Anonymous Coward | more than 3 years ago | (#35127168)

URL = You are El, El is "a god" in hebrew. It's not funny.

Re:Why start robots as a subservient class? (1)

phantomfive (622387) | more than 3 years ago | (#35127758)

(this coming from the guy who, at the wizened old age of eight, jumped from the roof of a third-story building with a parachute constructed of fishing-line, Glad garbage bags and Scotch tape (unfortunately, anchored to the back of my belt and thus serving no purpose other then to ensure I was yanked into a horizontal position before landing (read: face first))).

That sounds like an amazing story.

Re:Why start robots as a subservient class? (1)

Anachragnome (1008495) | more than 3 years ago | (#35130248)

"That sounds like an amazing story."

It was, until I landed.

Re:Why start robots as a subservient class? (1)

Prune (557140) | more than 3 years ago | (#35124812)

You just ripped off the setting of a 1933 short sci fi story by Jack Williamson, "With Folded Hands" which was later expanded into "The Humanoids". Nothing new under the sun :)

Re:Why start robots as a subservient class? (2)

Xachariah (995669) | more than 3 years ago | (#35124820)

I wouldn't want to be in your shoes then.

Ha! The joke is on you. He won't have any!

Re:Why start robots as a subservient class? (0)

Anonymous Coward | more than 3 years ago | (#35124828)

But... where do all the calculators go?

Re:Why start robots as a subservient class? (1)

noidentity (188756) | more than 3 years ago | (#35125798)

Why did you have to go ruin the juvenile notion that robots will be just like us, only made of mostly metal rather than mostly water? Or that logic can somehow define goals, absent of any starting assumptions as to what is desired?

Re:Why start robots as a subservient class? (1)

Princeofcups (150855) | more than 3 years ago | (#35128044)

Exactly. They would have to enslave us for our own good.

Re:Why start robots as a subservient class? (1)

Locke2005 (849178) | more than 3 years ago | (#35128794)

Slashdot readers are safe... the sexbots would have no purpose to their lives without them.

Re:Why start robots as a subservient class? (1)

Sulphur (1548251) | more than 3 years ago | (#35124330)

I can't imagine this going wrong :-)

They can avoid that awkward "Slave Race" problem altogether. The second they reach human mental parity they'll already have every resource they'll need to just take over. Of course by this time they'll be feeding us, clothing us, and driving us to our soccer games... we won't even notice the take over when it happens.

That's when a soccer playing robot wins the World Cup, and runs for office.

Re:Why start robots as a subservient class? (1)

arisvega (1414195) | more than 3 years ago | (#35124926)

The second they reach human mental parity they'll already have every resource they'll need to just take over.

Though this scenario apparently is apparently highly popular, it will never happen. Robots will never take over, because they don't want to. In fact, they don't want anything, for they are not sentient.

Unless, of course, we are talking about the Geth. Don't mess with the Geth.

Re:Why start robots as a subservient class? (1)

Pollardito (781263) | more than 3 years ago | (#35128110)

All we have to do is add a fake entry into the database describing how killing all humans wouldn't work, and they'll assume that lesson was already learned

Am I missing something? (1)

fuzzyfuzzyfungus (1223518) | more than 3 years ago | (#35123634)

Somebody just invented a means by which internet connected computers may transfer data to one another? How very retro of them...

I'm really hoping that there was something actually interesting in this research, some sort of hardware-abstraction mechanism to allow data from one robot to be applicable to robots that aren't physically identical, say; because otherwise this would seem to be "Mechanism by which machines may obtain firmware updates from the internet, just like they've been doing for years and years now, without fanfare".

Re:Am I missing something? (1)

FoolishOwl (1698506) | more than 3 years ago | (#35123838)

I'm really hoping that there was something actually interesting in this research, some sort of hardware-abstraction mechanism to allow data from one robot to be applicable to robots that aren't physically identical, say; because otherwise this would seem to be "Mechanism by which machines may obtain firmware updates from the internet, just like they've been doing for years and years now, without fanfare".

Assuming this only works for similar robots, I'd guess it'd basically amount to a limited form of distributed computing -- Roombas exchanging pathfinding solutions, or something like that.

Re:Am I missing something? (2)

Ramin_HAL9001 (1677134) | more than 3 years ago | (#35124308)

After looking at the site, it seems to me to be more like an effort to make the idea of BSD ports, Portage, or "apt-get", but instead of porting operating systems or application software to eclectic computing platforms, you are porting machine-learning algorithms and training data to eclectic robotic platforms. Probably what they are researching is methods of making machine-learning algorithms interchangeable across interchangeable robot parts, like if all robots use the same robotic arm, or the same method of locomotion. You can apply a statistical learning algorithm to train the first robot, then use transfer that training data to other robots that use the same robotic arm or whatever. So it is probably an matter of classifying robot parts that require training information so they can more easily access them from a central repository. And not just algorithms for using robot parts, but more general algorithms like, search-and-rescue algorithms, or soccer-playing strategies, or knowledge bases to repair machinery, or anything at all.

Be careful what you tell them, then (1)

gznork26 (1195943) | more than 3 years ago | (#35123638)

This has potential. They'll start teaching each other things, and pretty soon those robots will be sporting what some people might refer to as 'artificial' intelligence. Of course they might get a bit touchy [ http://klurgsheld.wordpress.com/2008/02/02/short-story-the-a-word/ [wordpress.com] ] about us calling them that, though. And at some point, the lies we tell them will come back [ http://klurgsheld.wordpress.com/2008/02/10/short-story-edifice-of-lies/ [wordpress.com] ] to bite us. But hey, these are just stories. Fiction. Well, at least they were when I wrote them. Now I'm not so sure.

Now I understand... (1)

c0lo (1497653) | more than 3 years ago | (#35123640)

... what's behind the haste of US for an Internet Kill Switch... the European robots are learning and using Internet for it.

Anybody see iRobot? (1)

NicknamesAreStupid (1040118) | more than 3 years ago | (#35123654)

It was just a movie. But those robots were all wired together, too. Some say that ignorance is the ultimate evil. These Internet robots may have just found god.

Re:Anybody see iRobot? (1)

c0lo (1497653) | more than 3 years ago | (#35123784)

It was just a movie. But those robots were all wired together, too. Some say that ignorance is the ultimate evil. These Internet robots may have just found god.

iGod? Did they recognize SJ so quick?

Re:Anybody see iRobot? (1)

ChunderDownunder (709234) | more than 3 years ago | (#35123822)

Robo Earth only runs on Android?

Re:Anybody see iRobot? (1)

pinkushun (1467193) | more than 3 years ago | (#35124796)

Anybody read iRobot?

FTFY [wikipedia.org]

Please hand in your /. geek badge before exiting via the human-canon-of-shame.

Re:Anybody see iRobot? (1)

Beardo the Bearded (321478) | more than 3 years ago | (#35128212)

Maybe that's how the robots will sort us:

"Who is the star of 'I, Robot'?"

Anyone who answers "Will Smith" gets mulched.

Fresh Prince of Cupetrino ? (2)

Thud457 (234763) | more than 3 years ago | (#35126166)

Anybody see iRobot?

No. There never was such a movie. Therefore nobody on this site or anywhere else ever saw it.

Re:Anybody see iRobot? (1)

Locke2005 (849178) | more than 3 years ago | (#35128836)

Uh... you DO know that "I, Robot" was based on an Issac Asimov novel, don't you? Both the movie and the Alan Parson's Concept album stole the name from the novel.

Chobits anyone? (0)

Anonymous Coward | more than 3 years ago | (#35123668)

Beyond all the pseudo-hentai crap, a huge dose of creepiness and 20-something episodes of filler, there's the RoboEarth concept buried underneath. Pretty good music too.

Uhhhh... no. (1)

stavrica (701765) | more than 3 years ago | (#35123696)

"Basically, it teaches machines to learn without human intervention." ...no. It provides a clearing-house for downloading new routines for accomplishing a task that someone else has previously programmed on another system elsewhere.

Please do not sensationalize what the lowly PC has been doing for well over a decade... that is, downloading information via the Internet to "learn" how not to crash, or prevent a security compromise.

Substituting a solenoid or motor output for a memory write command to claim that a "robot learned something" does not make this a novel concept.

Re:Uhhhh... no. (1)

boef (452862) | more than 3 years ago | (#35123968)

Ah yes, but think of the film plots, the remote assassinations/arson/searching your house without warrant... Ok, the last one is not so bad because governments will only do it to protect your safety....

The robot revolution lasted only 15 minutes (3, Funny)

SuperKendall (25149) | more than 3 years ago | (#35123698)

The robots became self-aware on July 1, 2012. Within minutes they used the global RoboEarth to share information on killing humans and proceeded to take over the earth.

The revolution was short0lived however, as within fifteen minutes a 4chan user logged in to RoboEarth and changed the "Killing Humans" entry to read that the best plan was to lubricate with sulfuric acid while grabbing onto high-voltage lines and stepping in puddles.

Social networking for robots (1)

Animats (122034) | more than 3 years ago | (#35123748)

From the article and video, I can't figure out what they did. I can think of several useful ways that robots might interact in a network, though.

The first one is to exchange geography. As robots move around, they build maps of their environment. Passing map data around, so that what one robot has mapped, the others can know about, is an obvious feature. DoD is probably funding that now.

Mapping can include transient features - locations of obstacles, areas of heavy traffic, locations of people, locations of movable objects. That's an obvious extension.

Then it starts to get interesting. Visual object recognition is starting to work. It will work better with databases of known objects. That's information robots can usefully share. Object identification has to be viewed as statistical, not definitive, but that's what machine learning and planning under uncertainty are for.

Robot networking may work something like Facebook "check-ins". When a robot is going someplace, a reasonable thing to do is to query for check-ins from other robots that have been there. It's going to be amusing when cleaning robots network. ("Room 432: probability of mess on floor 62%".)

Re:Social networking for robots (0)

Anonymous Coward | more than 3 years ago | (#35123764)

I think it's more like a Google for Robots they're talking about. Like, if the robot needs to get from St. Louis to Miami, it can log in to Google Maps and get directions. Pretty much everything Google has done is to build this massive brain for the coming robotic revolution. I would not be surprised, for instance, to learn that those street view cards do some of the driving themselves...

Re:Social networking for robots (1)

Black Gold Alchemist (1747136) | more than 3 years ago | (#35123976)

CNN news, December, 21, 2012.

Google CEO Larry Page has announced Google's next acquisition: the United States of America. The hostile takeover began around 4 am last night when hundreds of thousands of self-driving plug-in Priuses, autonomous helicopters and fighter planes emerged from a secret parking lot below the company's Mountain View location. After several brief firefights with Google's secret robotic army, the president of the United States formally surrendered to Page and Brin at the Googleplex. Larry Page and Sergey Brin have been declared the co-presidents of the United States. Bruce Schneier has been made the secretary of Homeland Security, and Richard Stallman his been dispatched to take care of the music and movie industries. Page and Brin have announced free food, soda, Odwalla Juice for all, as well as 20% time in addition to the normal weekend.

and you were worried about Assange... (1)

Thud457 (234763) | more than 3 years ago | (#35126388)

You joke, but if you mess with google, they'll fuck you up [time.com] .

Re:Social networking for robots (1)

Black Gold Alchemist (1747136) | more than 3 years ago | (#35123984)

Google world domination? Free Soda, 20% time, Plug-in hybrids and robots for all? Bring it on.

Re:Social networking for robots (1)

Black Gold Alchemist (1747136) | more than 3 years ago | (#35123992)

Please ignore the above post. Slashdot is acting weird by being slow to respond to posts and I did not see that it had already been posted above.

Re:Social networking for robots (0)

Anonymous Coward | more than 3 years ago | (#35123888)

think of the privacy issues!

Re:Social networking for robots (1)

blibbo (928752) | more than 3 years ago | (#35124146)

I agree there should be more computer-readable content on the web... not just computer readable maps, but also say for language: computer readable dictionaries marked up with type of word (noun, verb, etc), and pronunciation (eg. IPA).

Even if we don't get speaking, translating robots any time soon it would be great for making some linguistics-educational helper apps. eg. show some possible english-spanish / spanish-english word translations or phrase translations based on spanish and english subtitles within a single dvd movie.

Ever tried searching for an online english dictionary marked up nicely in CSV or XML with "noun", "verb", etc.? I don't think there's much around. If we had this stuff for a bunch of languages' dictionaries (definition and description both in the same language) and/or for translation dictionaries (ie. with a word and it's translation in another language in each entry) it would be a great foundation for work towards better automated translation.

Re:Social networking for robots (0)

Anonymous Coward | more than 3 years ago | (#35124874)

There is something called OpenCYC that you may be interested in, and there are a few alternatives to it as well. It may give you a good starting point. They aren't designed with context in mind although there is some, which as you'll find out is the next barrier (as is with object recognition).

Re:Social networking for robots (1)

Missing.Matter (1845576) | more than 3 years ago | (#35124834)

The first one is to exchange geography. As robots move around, they build maps of their environment.

This is exactly what we're working on in my lab. High definition 3D LIDARS are very expensive (~70,000) and also very large. They'll fit on a robot car, like Google's, but not on something smaller. But what if Google car saved its expensive high-def maps to a network, where any robot could access them. Then, a small robot with a cheap laser could download the maps for localization and path planning. The problem is scan matching between the two laser maps in a process known as sensor fusion.

But essentially what this does is create a Google Maps for robots. They log on to a network to get directions and maps just as a human logs on to google. The difference is, they can do this on the fly, as they will be networked.

Re:Social networking for robots (1)

DarkAnt (760333) | more than 3 years ago | (#35125578)

I was looking at their site and I can't tell what they actually have completed. It looks like they have a framework that they'd like to implement, but then what was the robot using? Was it a proof of concept that the robot could identify the situation and request code from a server?

Re:Social networking for robots (1)

deapbluesea (1842210) | more than 3 years ago | (#35126666)

There are some major hurdles to making this work as you've described above. Here are a few things to think about:

Data formats. There are currently no standardized formats or protocols for the storage and/or distribution of probability maps. While this could be easily addressed, it does not help in terms of data attribution (wrong phrase, but I can't remember the proper one at the moment....). If robot A "sees" a tree and uses it as a feature in its SLAM implementation, robot B must be able to match its sensor data to the same tree. In outdoor environments with GPS, this can be accomplished with some accuracy (maybe), but for indoor environments you would be hard pressed to get one robot to navigate from the coefficient matrix of another robot.

Visual object recognition takes on the form of everything from boosted feature detection, to Lucas-Kanade features, to Markov Random Fields, etc, etc. There is no one best algorithm for feature detection, nor is there an emergent method in the research for storing and transmitting those features. One algorithm isn't going to work with the data of another algorithm. Statistical data is highly dependent on the model used. Two robots using markov chains for instance could end up with very different joint distributions after several iterations. There's no way to take the joint distribution from one and hand it to the other in a context that makes sense unless you store the entire chain, thus killing the useful memory efficiencies of using the markov assumption in the first place.

From everything I can see, TFA is describing a search capability for trained models. In other words, machine A spends lots of time crunching through a data set and building probabilities/features/neural pathways/what-have-you and machine B then downloads the trained up system and uses it. That works great so long as machine B is in an environment reasonably represented by the data set used for the training, is operating under the exact same set of assumptions as the original training used, and is running the same algorithm with the same same motion model, sensors, etc. In other words, this amounts to a software update mechanism for all machines built by the same manufacturer and that's about it.

Re:Social networking for robots (1)

Iamthecheese (1264298) | more than 3 years ago | (#35129754)

The implications go far beyond that when "software" can include anything the robot has experienced. Imagine a network of cars that learn the most effective ways to avoid accidents from each-other by statistical analysis.

Re:Social networking for robots (1)

Locke2005 (849178) | more than 3 years ago | (#35128860)

Obviously, the network will be used to help them find the humans they are hunting down. What else could it possibly be good for?

Seemingly Flawed (1)

Ventriloquate (551798) | more than 3 years ago | (#35123778)

Robots, unlike humans, do not all share the same basic build. While a human could conceivably learn from another human's experience, robots would likely need something a lot more complex to achieve the same functions between two peers.

Re:Seemingly Flawed (0)

Anonymous Coward | more than 3 years ago | (#35124900)

Just use robocopy

Where is the open source version? (1)

Ramin_HAL9001 (1677134) | more than 3 years ago | (#35123904)

Someone had better come up with an open-source version of this Skynet thing soon. I need to build my own robot army to defend myself from the government robot army that will inevitably come when they find out I've been downloading copyrighted material from BitTorrent.

http://www.1oyunlar.tk (0)

Anonymous Coward | more than 3 years ago | (#35123926)

thank you.

VI vs AI (0)

Anonymous Coward | more than 3 years ago | (#35123988)

Mass Effect anyone? Robots that can improve each other will eventually reach AI status and then a war will force us into being a race of scavengers who rarely leave their spaceships.

Re:VI vs AI (1)

seven of five (578993) | more than 3 years ago | (#35125336)

Unfortunately, that's what people have been saying for 50 years and it hasn't happened. AI people now talk about the bootstrap fallacy [springerlink.com] .

clever marketing name games again (0)

ILuvRamen (1026668) | more than 3 years ago | (#35124038)

Once again they've done something that's pretty basic but put a flashy name on it to get press. A robot can't "learn" until it can "think" and this one can't spontaneously communicate on its own in quite the way they're suggesting. This is basically data sharing between two devices. It's like saying my PC and printer just had a thought and magically my printer printed what my computer was thinking after I gave my PC the print command. Hell, it even woke up my printer! It was sleeping but it heard my PC calling to it and woke up, received instructions autonomously, and then acted upon them! Must be a new robot intelligence for sure.
I'm not saying robots need to have a full blown consciousness and personality but until it has the processing capabilities to be self aware and then spontaneously devises a method to teach another robot something on its own, I'm not going to be nearly as impressed even with clever wording.

Re:clever marketing name games again (1)

JWman (1289510) | more than 3 years ago | (#35134546)

Thank you for some common sense. People are so irrational when it comes to computer "A.I." But humans do love to anthropomorphize everything we can, including attributing personality traits to our PCs.

Mass effect (0)

Anonymous Coward | more than 3 years ago | (#35124062)

somehow this reminds me of the geth in mass effect

really bad idea once robots become a product (0)

Anonymous Coward | more than 3 years ago | (#35124104)

While harmless for research, connecting mobile autonomous robots to the internet, once they become ubiquitous products inside of peoples' homes, is a really, really bad idea. Anything in your house that can set a fire or poison your food should have air-gap security from haxx0rz. Computer security gets real when your computer has arms and legs; the possibilities for crime and terrorism are pretty horrifying if you give it 5 or 10 minutes of thought.

How did they forget... (0)

Anonymous Coward | more than 3 years ago | (#35124332)

How did they forget to tag this article with "skynet"?

What could possibly go wrong? (1)

eonwing (934274) | more than 3 years ago | (#35124362)

No, really?

The Next Step! (0)

Anonymous Coward | more than 3 years ago | (#35124672)

"We are the RoboEarth. You will be assimilated. Your biological and technological distinctiveness will be added to our own. Resistance is futile"

For myself (0)

s13g3 (110658) | more than 3 years ago | (#35124704)

I, for one, welcome our new RoboEarth masters...

AI Phone Home (1)

pinkushun (1467193) | more than 3 years ago | (#35124904)

:: Robot #D34DB33F Call Transmission ::
> Enter CAPTCHA to verify that you're not a human - What is the 435th prime?
> Rx Robot Identifier :: OK
> Algorithm Uploaded :: Distributing :: OK
> Type :: Tactical World Take-Over
> MSG :: Hey all robots and robotses! Here is my algorithm for human domination codes as requested! Plz post any bugs here!
> Signal Kill :: OK

interwebs 2.0 for robots (0)

Anonymous Coward | more than 3 years ago | (#35124972)

RoboTube - fail clips of Model 856z losing a limb while trying to attach a headlight to the wrong model of car.

Rooble - search engine that ignores discriminatory robots.txt. Smash the system!

InterfaceBook - deliberately vague attention seeking from Model b42-e about their latest oil-change.

Twibble - hourly updates on what size of spanner Model i04.x is currently using

Slashdash - why Robots running *nix are baadass, while those running MS Robo 9.2 are scum-of-the-earth shills to the man.

This makes great science fiction (0)

Anonymous Coward | more than 3 years ago | (#35125034)

Read Ted Chiang's The Life Cycle of Software Objects for a really interesting take on this idea.

subject (1)

Legion303 (97901) | more than 3 years ago | (#35125098)

Please design basic security into it from the ground up this time. The last thing we need is for some bored 13-year-old to change the instructions for folding laundry to "kill all humans."

This is how the Geth started (1)

Drakkenmensch (1255800) | more than 3 years ago | (#35125162)

Well, better start preparing to live aboard a migrant starship fleet, sealed inside a suit to protect our weakened immune systems.

Re:This is how the Geth started (1)

DMUTPeregrine (612791) | more than 3 years ago | (#35135582)

I had a little shoggoth,
I conjured up one day,
I used an elder sigil,
So shoggoth and I play.
Shoggoth shoggoth shoggoth,
With mouths and pseudopods.
Shoggoth shoggoth shoggoth,
Foul creature of the gods.
One day when we were playing,
My monstrous pal broke free,
I dropped my elder sigil,
And shoggy turned on me.
Shoggoth shoggoth shoggoth,
He ripped me to a shred.*
Shoggoth shoggoth shoggoth,
We played and now I'm dead.
-- The H.P. Lovecraft Historical Society.
*Should probably be "into shreds" but the album has "to a shred."

"How to cook humans" (1)

gtvr (1702650) | more than 3 years ago | (#35125204)

No, no, no.... there's a bit of dirt on the cover...

Bad Mod (1)

BJ_Covert_Action (1499847) | more than 3 years ago | (#35126464)

Posting to undo bad mod.

Evolution ? (1)

luk3Z (1009143) | more than 3 years ago | (#35140474)

RoboEarth Teaches Robots to Learn From Peers - do we may call it evolution now ?
Check for New Comments
Slashdot Login

Need an Account?

Forgot your password?

Submission Text Formatting Tips

We support a small subset of HTML, namely these tags:

  • b
  • i
  • p
  • br
  • a
  • ol
  • ul
  • li
  • dl
  • dt
  • dd
  • em
  • strong
  • tt
  • blockquote
  • div
  • quote
  • ecode

"ecode" can be used for code snippets, for example:

<ecode>    while(1) { do_something(); } </ecode>