Let's assume that someday you will have, in your home, a humanoid robot helper. The robot, because it's shaped like you, can use your tools and move easily around your house. It folds the laundry, it helps your elderly mother up the stairs, and on Sundays it makes brunch for the family. It's capable of handling almost any household chore you can throw at it.
Now let's imagine that you're out on the lawn, kicking a ball around with your son. Your robot helper is in another part of the yard, its back to you both, fixing a drainpipe.
Your son misses a kick, and the ball winds up a few feet from the robot. "Hey, robot!" you shout. "A little help?" The robot turns in place, spots the ball, walks over, and kicks it back to you. The game resumes.
Of all the tasks you would undoubtedly love to hand off to a robot assistant, fetching a soccer ball is probably low on the list. And yet in 2010, there is no humanoid robot on Earth that can consistently do something as simple as turn, spot, approach, and kick. Never mind helping Grandma to bed or starching your shirts. Broken into a daisy chain of input, calculation and action, just kicking a ball is incredibly hard. It's so difficult, in fact, that engineers from all over the world have embraced it as the modern era's standardized test of humanoid-robot sophistication, and they converge each June at an event called RoboCup to try it. This year, only one adult-size, self-contained, humanoid robot in this country can even attempt it.
Its name is CHARLI-L (the "L" stands for "Lightweight" and the rest for "Cognitive Humanoid Autonomous Robot with Learning Intelligence"). Created at Virginia Tech, it's America's first true humanoid, in that it requires no remote power source or computer, it stands roughly five feet tall and has arms and legs, and it walks—left, right, left, right—like a human.
As such, CHARLI-L belongs to an exclusive international club of humanoid robots (see an illustrated overview of said club here), each of them designed to hasten the day when robots play a central role in all of our lives. Japan and South Korea dominate this club, together outspending the U.S. in civilian robotics many times over. Japan's Asimo, a humanoid first built in 1986 by the Honda Corporation and now in its 12th generation, and Korea's Hubo, built to compete with Asimo in 2004 by Jun-Ho Oh of the Korea Advanced Institute of Science and Technology (KAIST), are the pride of their nations. Honda is said to have put $300 million and more than 100 worker-years into the first Asimo. Dennis Hong, an associate professor of mechanical engineering at VT, laughs at the idea. "That guy," he says, pointing at CHARLI-L, "was 12 undergrad and grad students in a year and a half, with seed money of $20,000."
For a look at CHARLI-L's fellow humanoid 'bots from around the world, launch the photo gallery
Dennis Hong is the founder of VT's Robotics and Mechanisms Laboratory and the leader of the student team that built CHARLI-L. We're seated at a workbench inside the University of Pennsylvania's robotics lab, run by Hong's friend and collaborator Daniel Lee. Hong's students are here to show CHARLI-L to Lee's students, to prepare for RoboCup 2010, held in June in Singapore, and to discuss upcoming partnerships. Hong (winner of a 2009 Popular Science Brilliant 10 award) and his students have produced chemically driven, amoeba-like robots; a spider-like 'bot called STRiDEr, whose swinging walk is modeled on the human gait; and a system by which blind adults can make guided yet independent decisions as the drivers of their own cars. Lee's students build complex software to govern robot behavior and human-robot interaction. These are some of the most accomplished robotics engineers in the field. But as I watch the students fiddle with CHARLI-L, it begins to dawn on me how much work stands between CHARLI-L and the RoboCup trophy, to say nothing of how much work it will take to reach a future full of robot helpers.
The sheer scale of the challenge is the point, Hong says. "I think a full-size humanoid is the Holy Grail of robotics," he explains. "It's a system of systems. It combines all the disciplines of robotics, from artificial intelligence to autonomous behavior to dynamics to controls to mechanical design—everything!"
At the moment, however, VT junior Taylor Pesek, Ph.D. student Jeakweon Han and master's student Seungmoon Song are just trying to get CHARLI-L to stand upright. "Uh-oh," Han says, catching the robot as it lolls forward, knees buckling. "Stop putting in commands," Pesek says. "I'm not," Song responds. Pesek turns the power off and on and, with a bit of wrestling, the robot stands at quiet attention.
If standing still is so difficult, how hard is kicking a ball? The rules of RoboCup, in which six teams will compete for the title of "Best Humanoid" in the Adult Size Humanoid division, require that the robot be facing away from the ball when the event begins, so the machine has to turn around and find it. "It's a high-end academic exercise dressed up as an entertainment event," Hong says. Break the goals—kicking balls at a target, basic dribbling, and trying to slowly block the very slow shots from other robots—into individual processes, and the to-do list grows very long. To eventually build the brunch-making 'bot of the future, Hong must first win RoboCup. And that's hard. "Just getting it to turn around in place is ridiculous," says master's student and CHARLI-L team member Robert Nguyen. Is it also pointless?
AMERICA'S HUMANOID DILEMMA
Nearly everyone would want a dutiful, reliable robot helper, so why is there only one such humanoid made in this country? And why is it the work of a small team of unpaid students? To get at the answer, consider the machines in your life. Your dishwasher, your car, your DVR all serve a practical, well-defined purpose. Today's humanoids, meanwhile, serve almost no practical function. "They represent incredible research and technology that's then backed into an application" says Colin Angle, the CEO of iRobot, which makes domestic cleaning robots and military models. Roboticists working on humanoids, he says, "are doing amazing, exciting work, but it's just not going to drive the robot industry—unless it's for entertainment purposes."
Asimo, the most sophisticated Japanese humanoid, is famous for its balance and adaptability. It can even run, in an awkward, distinctively robotic way. But if it encounters a closed door, the show's over, because the calculations necessary to reach out, grasp the knob, turn it, and walk forward, pushing the door ahead of itself, are still too complicated. (The fragility doesn't end there. "Our products can survive a two-story fall," Angle says. "See what happens with an Asimo.") Japan has embraced Asimo, however, as a broad, long-term investment in a wide range of scientific challenges, from materials science to artificial intelligence. It's not a robo-butler. It's a stake in the ground, a totem of Japan's belief that our future will be full of helpful, sentient, Japanese-made machines.
That kind of open-ended vision doesn't work here, where our funding environment rewards near-term products, not totems. As a result, the U.S., though it is filled with robotics projects, lags behind Japan and South Korea in the development of humanoids. In 2006, sponsored by the National Science Foundation and others, the nonprofit World Technology Evaluation Center (WTEC) published a report entitled "International Assessment of Research and Development in Robotics," comparing America's activities with the rest of the world's. The report concluded that while this country leads the world in military and medical robotics, it is quickly losing that advantage and falls short when it comes to robot mobility and humanoid robotics. Although "robotics is a very active field, worldwide," the authors wrote, "Japan, Korea and the European Community invest significantly larger funds in robotics research and development for the private sector than the U.S."
There is another Humanoid robot built in the USA called the
ATOM-7xp and was introduced to the world on Jan 4 2010 in Engaget magazine.
It's funny how Professor Hong knew about the ATOM-7xp humanoid project and did not say anything to Pop Science to include it a little in the article of USA built humanoid robots, I find that just plain wrong not to help a fellow robot builder, I guess it's all about him as always, it's not what you know, it's who you know..
I apologize for accusing professor Hong for not giving me a shout out in the Pop. Science article, I guess I was caught up in the moment, but that does not change the face there are other humanoid robots being built in the United States and Pop. Science needs to report them and give them some credit also.
Why build a humanoid robot?
This was answered generations ago by science fiction writers. Our entire infrastructure is designed around the human form. To be of greatest utility, it is only reasonable to build robots in the same form and on the same scale.
Why? Is that the question? It's because engineering school (hell school in general) costs so damn much. Once you finish you get into your real job and it sucks. Your stuck with big bills and debt to your ears. So how in the hell would you get time to be creative. Your not given space or funding to use what you learned to create new things. You are given a task that has been corporate ordered to complete. Most engineering jobs pay well enough to put your kids into college. Hopefully they will be able to produce stuff like this. The 20 somethings that actually have imaginations to create this stuff are to busy trying to make a buck and pull our rear ends out of the hole while the rich people (most without a college education) keep trying to make money with their same stupid ideas. Right now it doesn't seem feasible to spend big money on cool things. If it doesn't have a warhead, gun, or gas guzzling engine attached to it, then we don't really have a use for it.
I would like to know if any of these machines were developed specifically to do high-risk activities or work. They all seem too frail/clumsy to be effective as such.
i see a new mac vs windows dispute in the coming years, tank tread(windows) robots vs bipedal(mac) robots. one looks better and does somethings better, but other is better all around. but with better technology bipedal will eventually over take treads. similar to mac and windows today. pro's and con's to both.
,eh non humanoid robots are far more useful sooner so let them mess with that tech morerobotic cars, sewer cleaners and the like are far more practical atm
They also forgot about robonaut which is vaguely humanoid and NASA is planning on adding legs so it can be used on the Moon and Mars.
I think 99% of all robot research funds should go to AI. Once human-like AI is achieved, the rest of the robot problems will be considered solved, since you have now a sentient being able to figure out on his own how to use those mechanical arms and legs and whatever is linked to its "brain".
In addition to the above, I wouldn't mind being the last to create a humanoid robot, as long as I will be the first to create a working AI capable of human-like cognition.
I still see Popular Science has a bias towards other USA based humanoid robot projects by not including my ATOM-7xp humanoid in there photo gallery or article of which they know about.
The ATOM-7xp will be the most humanoid robot in the USA an 8 year project, I guess with Popular Science magazine the little robot builder guy don't need to apply.
That picture looks like one of the sets from a James Bond movie! The one with Jaws you know??
Japanese and Korean humanoid robotics suffers, so far, from the fact that their robots do not produce human-like locomotion. They walk with bending knees because their control laws are based on the so-called zero-moment point ZMP-concept. These robots use trajectory-tracking controllers that have proved much inefficient as regards the energy consumption. Their control laws are not based on the natural dynamics and control of human locomotion, where joint movements are performed in an open-loop manner. My research is devoted to design and control of humanoid robots in such a natural way, exploiting the gravity and the inherent robot dynamics. An approach for efficient learning of optimal control functions in performing steps is being developed. The learning control parameters are similar to those that human has to learn to produce a step in an optimal manner. The learning procedure is proved to be convergent within minimum number of trials. It can be very useful in designing efficient neurorehabilitation procedures as well.
Build the AI first, then have it design its own container
It's OK if we fall behind. We'll just outlaw the technology.
Interesting! I hope that everyone has a great weekend.
Interesting! I hope that everyone has a great weekend.
I just attended some super interesting robotics classes last semester. In a matter of no time I could build up a tracked robotic vehicle from some LEGO components and get it to follow a black line on a white table.
I am dazzled about the complicatedness of such a humanly simple task as kicking a ball. Not that I am so good at kicking balls, but one would think experts could surely program something like that...
Visit Budapest: http://www.hungriabonita.com/budapeste.html
I still see Popular Science has a blind eye and is still promoting their lie this month that there is only one Humanoid Robot made in the United States. When there a another USA based humanoid robot project the ATOM-7xp humanoid and was in featured in there face book page photo gallery on April 29, and featured on Engadget on Jan 4, and in Robot and Servo magazine way before this other so called humanoid project. The ATOM-7xp will be and is the most humanoid robot in the USA. I guess the little company guy need not apply to Popular Science for help in getting the word out, I guess if your not some big company, Gov. organization or professor Popular Science is in love with you need not apply. Wow selective journalism only hides the truth of which the truth you cannot stop.
^^nice spam...(as if anyone reading this will be interested)
Maybe they haven't recognized it because there are no videos I could find at least ATOM 7xp walking or even standing up without supports...Yes I know it is difficult to do this especially as it looks like your doing it by yourself unless i'm wrong... or maybe popular Science realizes how bad windows operating systems are and thinks that you should have used Linux :p(that was a joke even though Linux is much better).
Although by the looks of things i'm taking a guess that your more of a mechanical Engineer than a programmer by a bit, judging by what it seems you've done so far which is quite impressive on a small budget with only 1 person. But i believe you will find some trouble when you try to get it to walk as it seems that will be quite a challenge mechanical wise and programming wise, especially with limited resources. Well hopefully you have success in making it walk. Although really this is just the beginning of what humanoids begin to do. Also maybe popular science will recognize you when your Bot gets more developed, as currently it doesn't seem enough to write a article on.
p.s. i apologize for my terrible writing as I am not and never will be a writer.
The subtitle of the article includes the following "Walking, self-contained, adult-size robots". Unless you can prove otherwise, the only criteria of the three the ATOM meets is 'adult-size'. You're not winning any support by repeatedly whining in the comments section of this article. You could have chosen a vastly different approach in which you could have garnered support instead of coming off like an angry teenager.
Well, there is another Humanoid robot built in the USA called the ATOM-7xp...
Humanoid Robots are pursued due to the fact that the world is designed for humans. Advances in humanoid robotics affect the disabled, injured (especially war related) and many of the infirmed. PS has produced stories of the blind seeing and invalids and aputees walking. The technology can address many of human's physical shortcomings.
More importantly, Robot technology will aid humans in their next step in evolution, which is cyborgism. Cyborgs live with us today in so many limited forms. It is clear to me that many will embrace cyborg technology. At first to repair damaged or nonfumction assemblies, then to enhance human ability. Recent advances with respect to the mind machine interface are the second phase of cyborgs. Within a couple of decades, some of us will appear much like the cyborgs of (currently) Science Fiction soon to be Science Reality.
This type of robot I believe is not popular in the USA because of the mind of the American in general. A robot that can be operated through a full Haptic suit as an avatar interface seems more like something the American mind set would like.
Off-world exploration with robots is something we will be capable of long before we are capable of human space travel. It also seems likely that working through a robotic exoskeleton will allow us do work in new fields of exploration here on earth.
Robots like these here may be of interest to the fat and lazy but my bet is on robots that augment and extend the human potential.
I don't see why it would be so much trouble to have a robot open a door; I think it can be solved through stance. When we open doors, we simply reach out our hand, grasp the doorknob, twisting it, pull back, and to the side, letting go, all the while making constant adjustments to our center of gravity that is changing due to the constant appliance of force. If someone could tell Charli to spread his feet from front to back as he opened doors, it should dramatically reduce the required calculations, because he doesnt need to balance over as many axis.
Your description of this article in the overview of the issue on the right panel made me laugh:
"We go in-depth with America's first (and only) humanoid"
I think you've missed the word robotic (or equivalent) there...
With this XP robot thing, why not do what the universitys are doing, set it up in a room with webcams, and make the project open source to the public. so it would be like having linux programed on your robot. and by open source, you have thousands of minds working at this rather then just one, and then everyoen will have some good code, to use from here and there.
I say a world wide open source project is the way to go, however, you will need to be around to pick him up if he falls and etc.
Can we see a video please? I am very interested in your work