Your login is case sensitive
I have forgotten my password
Register nowActivate my subscriptionInstitutional loginAthens logincloseMy New ScientistHomeNewsIn-Depth ArticlesBlogsOpinionTVGalleriesTopic GuidesLast WordSubscribeDatingLook for Science JobsSPACETECHENVIRONMENTHEALTHLIFEPHYSICS&MATHSCIENCE IN SOCIETYCookies & PrivacyHome|Tech|News
Robot learns to recognise itself in the mirror22 August 2012 byHal HodsonMagazine issue 2878. Subscribe and saveFor similar stories, visit theRobotsTopic Guide NICO spends a lot of time looking in the mirror. But it's not mere vanity - Nico is a humanoid robot that can recognise its reflection - a step on the path towards true self-awareness. In fact, Nico can identify almost exactly where its arm is in space based on the mirror image. Justin Hart and Brian Scassellati at Yale University have taught Nico to recognise the arm's location and orientation down to accuracy of 2 centimetres in any dimension. It is a feat of spatial reasoning that no robot has ever accomplished before. Nico is the centrepiece of a unique experiment to see whether a robot can tackle a classic test of self-awareness called the mirror test. What does it take to pass the test? An animal (usually) has to recognise that a mark on the body it sees in the mirror is in fact on its own body. Only dolphins, orcas, elephants, magpies, humans and a few other apes have passed the test so far. Precise recognition of where its body is in space will be key if Nico is to get to grips with the mirror test, which by its nature is performed in 3D. Before it does, though, the robot will need to learn more about itself. The team plan to teach Nico how to recognise where its torso and head are, what shape they are, and their colour and texture so it can see and react to the mark on its body. Nico already understands how to connect movement of its limb to motion in its reflection, another important skill it achieved in an experiment in 2007. "What excites me is that the robot has learned a model of itself, and is using it to interpret information from the mirror," says Hart. He and Scassellati presented the work last month at the Conference on Artificial Intelligence in Toronto, Canada. Mary-Anne Williams of the University of Technology Sydney, Australia, points out that robotic self-awareness is crucial if robots are ever going to work safely alongside humans. "Many robots today not only do not recognise themselves in a mirror, but do not recognise their own body parts directly," she says. "For example, a robot may be able to look downwards and see its feet but not recognise them as its own." Self-awareness is a basic social skill and without it robots will struggle to interact with people effectively, Williams adds. Subscribe to New Scientist and you'll get:New Scientist magazine delivered every weekUnlimited access to all New Scientist online content -a benefit only available to subscribersGreat savings from the normal priceSubscribe now!If you would like to reuse any content from New Scientist, either in print or online, please contact the syndication department first for permission. New Scientist does not own rights to photos, but there are a variety of licensing options available for use of articles and graphics we own the copyright to.Have your say
Only subscribers may leave comments on this article. Please log in.
email:password:Remember meOnly personal subscribers may leave comments on this article
Subscribe now to comment.
Well. . .Fri Aug 17 22:15:10 BST 2012 by Eric KvaalenWake me up if it starts singing "Daisy, Daisy, give me your answer, do".
login and replyreport this commentThis comment breached our terms of use and has been removed.
view threadWell. . .Wed Aug 22 19:08:04 BST 2012 by Polemoshttp://2012wiki.com/index.php?title=The_end_of_the_world
That's a good one, Eric!
The electromagnetic intellect of a robot operates with bound information, aslo known as discrete knowledge.
The electric intellect of a human operates with free information, also known as analog understanding:
"Bound information is always connected with a definite material structure, free information is abstract/symbolic. Free information is to a high degree independent from the carrier. Free information is connected with meaning and with goals (Zweck). In course of evolution several "phase transitions" from bound to free information are observed." —Ebeling, Werner ? Entropy, Information and Predictability of Evolutionary Systems ? in Hofkirchner, Wolfgang (ed.) ? The Quest for a Unified Theory of Information ? Routledge, 1999, p. 262
"Any fool (i.e., any robot) can know. The point is to understand. ... Imagination is more important than knowledge." —Albert Einstein
Read more: http://2012wiki.com/index.php?title=The_end_of_the_world
http://twitter.com/rhamdu
Self-recognition is almost a pre-condition of life. It's how your immune system works. It's why spiders don't chew off their own legs. The mirror test is not a test of consciousness but of self-recognition under optical circumstances which don't often occur in nature. It's neat to program that into a robot, but it doesn't mean the robot has suddenly woken up into a world of subjective experience.
login and replyreport this commentGood Ai Work - But Don't OverinterpretWed Aug 22 11:49:30 BST 2012 by Polemoshttp://2012wiki.com/index.php?title=The_end_of_the_world
"It's neat to program that into a robot, but it doesn't mean the robot has suddenly woken up into a world of subjective experience."
It's good that you know it. But the point is to understand why it is so.
All comments should respect the New Scientist House Rules. If you think a particular comment breaks these rules then please use the "Report" link in that comment to report it to us.
If you are having a technical problem posting a comment, please contact technical support.
One day all robots will be aware (Image: Phillip Inger/Getty Images)ADVERTISEMENTMoreLatest newsWaste water harnessed to make electricity and plastics09:00 03 September 2012The treatment of waste water can be used to create energy and biodegradable plastics
Unsure robots make better teachers than know-alls16:41 31 August 2012Students learn best from a robot when it makes mistakes that they can correct
Bendy battery lets you wear gadgets' power supply11:08 30 August 2012Flexible battery design lets you wear your gadget's power source on the wrist, neck or any part of the body you fancy
Let's get lost: Apps that help you wander to happiness08:00 30 August 2012From GPS to book recommendations, technology is eradicating uncertainty from life. But what if happiness depends on taking chances?
see all related stories
MoreLatest newsMoon's magnetic umbrellas may shield future spaceships18:43 03 September 2012New insights into lunar anomalies could inspire deflector shields for spaceships that would protect astronauts against solar storms
Today on New Scientist: 3 September 201218:00 03 September 2012All today's stories on newscientist.com, including: stem cells return some feeling to paralysed patients, satellite images of Brazil's ravaged rainforests, the ultimate food scare, and more
Retracing the stardust trail17:34 03 September 2012In The Stardust Revolution, Jacob Berkowitz explains how stars have shaped the universe and asks if we may soon discover life outside the solar system
Brain diabetes: the ultimate food scare15:51 03 September 2012Big trouble lies ahead if Alzheimer's is proven to be a form of diabetes
see all latest news
Most readMost commented Epigenetics gives clues to human cancer susceptibility Two dead stars provide low-tech way to test Einstein Rosacea may be caused by mite faeces in your pores Mirrors take root in pitch-black nanotube forest Protein discovery could lead to 'genomic debuggers' Most readMost commented Fracking could be combined with carbon capture plans Rosacea may be caused by mite faeces in your pores Big burn theory: Why humans spontaneously combust Bonobo genius makes stone tools like early humans did Food for thought: Eat your way to dementia TWITTERNew Scientist is on TwitterGet the latest from New Scientist: sign up to our Twitter feed
LATEST JOBS PIC: Laboratory Technician SEC Recruitment: Senior Statistical Programmers | Perm | UK or Germany SEC Recruitment: Senior Lead Programmer |Germany |Global Company Meet Recruitment: Regulatory Affairs Publisher, Vienna Meet Recruitment: Fantastic Senior Regulatory Affairs function @ top Pharma, Berks/Bucks This week's issueSubscribeFor exclusive news and expert analysis, subscribe to New Scientist.
Gain full online accessCurrent issue contentContent of past issues01 September 2012ADVERTISEMENTBack to topLoginEmailPassword Remember meYour login is case sensitive
I have forgotten my password
Register nowActivate my subscriptionInstitutional loginAthens logincloseAbout usNew ScientistSyndicationRecruitment AdvertisingStaff at New ScientistAdvertiseRBI JobsUser HelpContact UsFAQ / HelpDisclaimerTs & CsCookiesPrivacy PolicySubscriptionsSubscribeRenewGift subscriptionMy accountBack issuesCustomer ServiceLinksSite MapBrowse all articlesMagazine archiveNewScientistJobsThe LastWordRSS FeedsOnline StoreAndroid AppMobile site homeScience JobsBiology JobsChemistry JobsClinical JobsSales JobsEarth & Environment JobsEngineering JobsMaths & IT JobsGraduate Jobs© Copyright Reed Business Information Ltd.
No comments:
Post a Comment