|(Folks from the media, look here for more info)
Q: What does Cog stand for?
A: It doesn't actually stand for anything. It's a play on the term "cognition" and a mechanical cog. Try finding something that clever in a baby book.
Q: Is Cog a boy or a girl?
A: No. The robot has no gender, and we try to use the pronoun "it" whenever it comes up. We also carefully construct our sentences to avoid third person references.
Q: Is Cog right or left-handed?
A: The arms are completely symmetric, and (as of yet) the robot has no preference for one or the other. If the videos show Cog using one arm or the other, that's simply because that arm was less likely to reach anything it could damage.
Q: Are you ever worried that your robot might get "too intelligent" or "too powerful"?
A: No -- we have programmed the robot to spare our lives in the event that it ever attempts to organize its brethren in a bloody revolution against the human race.
JUST KIDDING! The truth is that our lab focuses on building robots that are as human as possible. Even if we were successful in all of our goals (which is, in technical terms, "not likely"), the robot would have no "super-human" abilities. It would be no more likely to take over the world than, say, Pulitzer-Prize winning film critic Roger Ebert. In truth, its arms aren't nearly as strong than yours, its cameras cannot see as well as your eyes, and it doesn't even have legs! We wouldn't lose any sleep over it.
Could our research be used to harm people? Unfortunately, it probably could. But almost every type of research (both inside and outside the field of Artificial Intelligence) has this dual nature. Any technological advance can be used to help or hurt people. Like most researchers, we sincerely hope (and believe) that our work will ultimately serve the greater good. By the way -- the Cog Shop gives two mechanical thumbs up to The Matrix. We love you, Neo and Trinity!
Q: Is Cog conscious?
A: We try to avoid using the c-word in our lab. For the record, no. Off the record, we have no idea what that question even means. And, still, no.
Q: When will Cog be getting legs?
A: Our research involves studying the interactions between people and robots. Consequently, legs aren't really necessary (Cog is so charming, people tend to walk up to it, strike up conversation, ask it out fora drink...). We have no current plans to add them. If you are interested in legged locomotion, check out the Leg Lab here at MIT.
Q: Does Cog remember things?
A: The robot doesn't currently have a long-term memory. None of the research areas we have been investigating have required one. As such, the robot has no idea what it did two minutes ago (let alone two days ago). However, we're always changing and improving the robot, so perhaps there will be memory sometime in the future (or perhaps there was memory in the past and we've all forgotten about it ...).
Q: Can Cog pass the Turing Test?
A: No ... but then again, neither could an infant.
Q: Can you send me more information about your project?
A: These pages have been designed to give you an introductory look at what we do with Cog. If you find that you still have questions, download (and read) a relevant paper. If you still have questions, send email to the Cog Documentation Project (but if the answer is on this site, we will laugh wildly at your email using an extremely derisive tone, and then forward it to all of our friends with an insulting remark at the top, such as "Look at this doorknob's question!". Don't let this happen to you.).
Q: Where else can I find out about humanoid robots?
A: What, Cog isn't good enough for you? You've got a lot of nerve, mister.
I suppose you can find other humanoid robot web pages at:
Q: Can you send me more information about artificial intelligence?
A: Artificial Intelligence is a huge topic and (as a computer-based field), it has a huge presence on the web. As of this writing, typing "Artificial Intelligence" into google.com gives us 477,000 hits. We'd start there. If you'd like a pointer to some "big" pages, try
Q: Can you send me the plans/blueprints/schematics/drawings for your robot?
A: We can't, but not because they're secret or because we don't want to share them ... it's because we don't have any! Cog is a prototype robot, and as such, we didn't take steps to formalize the design process or make it reproducible in any way. The robot is just hack on a kludge to a "temporary solution," held together with Velcro, 24AWG wire, and solder. The most mechanically sound device in the whole lab is a rack we made to hold up our plasma display. It was constructed using plywood and an 8' 2x4. For the plans for that rack, please contact Matt Marjanovic (maddog).
Q: Where can I learn more about how to build a robot?
A: This book is a tried-and-true starting point for building a robot:
Mobile Robots: From Inspiration to Implementation (First Edition)
You can order it from amazon.com. We don't recommend the second edition (which is, unfortunately, all that's available from Amazon) because it has an inaccurate list of authors and contains many errors.
If that book doesn't do it for you, check out http://www.robotbooks.com.
A: The best place to start is by contacting Elizabeth Thomson at the MIT News Office (http://web.mit.edu/newsoffice/www). Not only does she have a great deal of stock footage, she can often provide you with the answers you're looking for. If you want a real-person interview, contact Theresa Langston, phone: 617.452.2651.
Q: I'm a fan of Cog, can I come visit the robot?
A: We love visitors! For the casual observer, lab tours are available by appointment. You'll get to see Cog. If you're a diehard Cog devotee and want a personal tour, send a 1-page essay on what you would do if you had six months and $10,000 to work on Cog (references to papers are worth bonus points) to the Cog Documentation Project, and we'll go from there.
Q: Can I link to your site and use your pictures?
A: If you would like to link to our site, be our guest. We dig web traffic. The pictures, though, are a stickier wicket. Sam Ogden (http://www.samogdenphoto.com) and Peter Menzel took most of the nice ones on the web site, and you should contact them for permission to use their images.
Q: Can you help me write my report?
A: Though we like to help out anyone who has questions about the robot, we can't help individuals write their reports (we have our own reports we should be writing). If you can't find an answer to your question on this page, and you've tried everything you can think of, you can send mail to the Cog Documentation Project (though we can't promise a speedy reply).
Q: I would love to come work with your project. May I?
A: Unfortunately, this is an MIT lab, so it is populated by MIT graduate students. Your best bet is to apply to MIT's graduate school (http://web.mit.edu/admissions/www), and then join us once you're here. Though, if coming to MIT for graduate school is your "best bet," you should rethink your life choices.
Q: What should I learn if I'm interested in working on robots?
A: Robotics requires a very robust background (or, alternatively, a person with just about any background can work in robotics). There are elements of computer science, mechanical engineering, cognitive science, and lots of mathematics in the work that we do. There's also a great deal of "hacking" involved. "Hacking" is the art of taking something apart, breaking it, putting it back together with improvements, and then acting like you knew what you were doing all along.
Q: I have a great idea for how to turn used tissues into gold (or whatever). Are you interested in seeing my plans?
A: While turning used tissues into gold would be useful (and extremely profitable for those of us with allergies), we have more projects going on than we can handle. No matter how clever your idea may be, we just wouldn't be able to get to it in a reasonable amount of time. If you have a great idea, you should look into finding venture capital and starting a business. The world needs great ideas!
Q: Cog looks great! Can I buy one?
A: Just like you, Cog is a one-of-a-kind, and we wouldn't part with it for all the money in the world (also, it's shoulders won't quite squeeze out the second-to-last door leading to the lobby). There are no extras or spares.
Q: Where can I get that dog robot (I think it's called an AIBO)?
A: From Sony.
Q: Don't you realize that artificial intelligence will never work? Or that you've been going about it all wrong? Or that I've figured it out and would like to tell you why your project is a failure?
A: While your lengthy harangues about our philosophy or methodology usually go unanswered, we enjoy reading them. Feel free to send us one (1) copy.
Q: I'd like to attach a really big binary/html/MSWord file. Should I do that?
A: No. Believe it or not, we still have people without easy attachment-decoding capabilities. A pointer to the file on the web will keep these people from going on a multi-office killing spree.
Q: Dude! Did you see that battlebots thing on pay-per-view? Wasn't that totally awesome?
Q: Would you like to buy ...?
A: No. We are very poor from spending all our money on robots.
Q: Congratulations! You've been selected by an automatic-email-address-finding program to take part in some blatant scam! Would you like more information?
A: No. And don't add us to your mailing list, either.
Q: I'd like to send you a long list of toner cartridge prices. Can I do that?
A: No. Quit it.
Q: Can you stop me?
A: Sadly, no.
[Overview], [People], [Video], [Publications]