Despite all the recent advances in robotics, one fundamental task has always been very difficult: robot programming. New Research in the field of robotic programming is moving towards more natural and exciting directions.
To be sure, robot programming in industrial settings has evolved significantly, from a series of mechanical switches to advanced programming languages and teach-pendant devices for trajectory planning. But getting robots to do their jobs still requires a great deal of human labor -- and human intelligence.
The situation is even worse when it comes to programming robots to do things in non-industrial environments. Homes, offices, and hospitals are unstructured spaces, where robots need to deal with more uncertainty and act more safely.
To overcome this programming bottleneck, engineers need to create robots that are more flexible and adaptable -- robots that, like humans, learn by doing.
That's what a team led by Dr. Jan Peters at the Robot Learning Lab, part of the Max-Planck Institute for Biological Cybernetics, in Tübingen, Germany, is trying to do. Peters wants to transform robot programming into robot learning. In other words, he wants to design robots that can learn tasks effortlessly instead of requiring people to painstakingly determine their every move.
In the video below, you can see his students taking their robot "by the hand" to teach it motor skills needed for three tasks: paddle a ball on a string, play the ball-in-a-cup game, and hit a ping pong ball.
Here's how Dr. Peters explained to Automaton his team's approach: "Take the example of a person learning tennis. The teacher takes the student by the hand and shows basic movements: This is a forehand, this is a backhand, this is a serve. Still, it will take hours and hours of training before the student even feels comfortable at performing these behaviors. Even more practice is needed for the student to be able to play an actual game with these elementary behaviors." But still, he adds, humans succeed at learning the task. Why can't robots do the same? "That's what we're trying to do: Make our robots mimic the way humans learn new behaviors."
In the first part of the video, graduate student Katharina Muelling shows the robot how to paddle a ball on a string by performing the action while holding the robot's "hand." The robot decomposes the movement into primitive motor behaviors -- a discrete motor primitive that modulates the rhythmic paddling with an increasing amplitude until it becomes a stable rhythmic behavior -- and quickly "learns" how to perform the task.
For comparison purposes, the researchers tried to manually program the robot's motors to perform the same task. It took them three months and the result wasn't as good as the imitation learning experiment, which took less than an hour, Dr. Peters says.
In the second part of the video, Muelling teaches the robot the ball-in-a-cup game. [See photo on the right; the robot has to swing the yellow ball, which is att ached to a string, and make it land into the blue cup.] This skill is significantly more difficult than paddling the ball on a string, and the robot doesn't have enough data to simply imitate what the human did. In fact, when the robot attempts to reproduce the human action, it can't match the accelerations of the human hand and the ball misses the cup by a large margin. Here, self-improvement becomes key, Dr. Peters says.
"For every new attempt, when the robot reduces the distance by which the ball misses the cup, the robot receives a 'reward,' " he says. "The robot subsequently self-improves on a trial-by-trial basis. It usually gets the ball in the cup for the first time after 40 to 45 trials and it succeeds all the time after about 90 to 95 trials."
How does the robot's learning ability compare to a human being? PhD student Jens Kober , who led this particular experiment, wanted to find out: He went home for a holiday last year and enjoyed the benefit of an extended, large family -- always good subjects for a scientific experiment. He showed his many cousins the ball-in-a-cup game and rewarded them with chocolate. It turned out that the younger ones (around 6 years old) would not learn the behavior at all, the ones in their early teens (10 to 12) would learn it within 30 to 35 trials, and the grownups would be much faster.
"His supervisor may be the only person in his lab who has not managed to learn this task," Dr. Peters quips.
In the last part of the video, the researchers tackle an ever harder task: ping pong. Again, Muelling teaches the robot by holding its "hand," this time to hit a ping pong ball sent by a ball gun. The challenge here is to use -- and modify -- previously learned basic motions and combine them with visual stimuli: The robot needs to keep track of the ball, which may come from different directions, and then execute the right set of motions.
Some of their work, part of GeRT consortium, a program that aims at generalizing robot manipulation tasks, is still preliminary, Dr. Peters notes. But he's confident they can teach their robot to become a good ping pong player. How good? Maybe not as good as Forrest Gump, but good enough to beat everyone in the lab.
Once upon a time..... products were made to last. Then, at the beginning of the 1920s, a group of businessmen were struck by the following insight: 'A product that refuses to wear out is a tragedy of business' (1928). Thus Planned Obsolescence was born. Shortly after, the first worldwide cartel was set up expressly to reduce the life span of the incandescent light bulb, a symbol for innovation and bright new ideas, and the first official victim of Planned Obsolescence. During the 1950s, with the birth of the consumer society, the concept took on a whole new meaning, as explained by flamboyant designer Brooks Stevens: 'Planned Obsolescence, the desire to own something a little newer, a little better, a little sooner than is necessary...'. The growth society flourished, everybody had everything, the waste was piling up (preferably far away in illegal dumps in the Third World) - until consumers started rebelling... Can the modern growth society survive without Planned Obsolescence? Did the eternal light bulb ever exist? How can a tiny chip 'kill' a product? How did two artists from New York manage to extend the lives of millions of iPods? Is Planned Obsolescence itself becoming obsolete? Written by Cosima Dannoritzer
The Light Bulb Conspiracy (2010) This is the story of companies who engineered their products to fail. VIDEO DOCUMENTARY
Director: Cosima Dannoritzer Writer: Cosima Dannoritzer Stars: Mike Anane, Michael Braungart and Steve Bunn
At TEDSalon in London, Michael Pawlyn describes three habits of nature that could transform architecture and society: radical resource efficiency, closed loops, and drawing energy from the sun.
About Michael Pawlyn
Michael Pawlyn takes cues from nature to make new, sustainable architectural environments.
Michael Pawlyn established the architecture firm Exploration in 2007 to focus on environmentally sustainable projects that take their inspiration from nature.
Prior to setting up the company, Pawlyn worked with the firm Grimshaw for ten years and was central to the team that radically re-invented horticultural architecture for the Eden Project. He was responsible for leading the design of the Warm Temperate and Humid Tropics Biomes and the subsequent phases that included proposals for a third Biome for plants from dry tropical regions. In 1999 he was one of five winners in A Car-free London, an ideas competition for strategic solutions to the capital’s future transport needs and new possibilities for urban spaces. In September 2003 he joined an intensive course in nature-inspired design at Schumacher College, run by Amory Lovins and Janine Benyus. He has lectured widely on the subject of sustainable design in the UK and abroad.
When we physicists look in outer space for alien life we don't look for little green men. We look for type 1, type 2 and type 3 civilizations. A type one civilization has harnessed planetary power. They control earthquakes, the weather, volcanoes. They have cities on the ocean. Anything planetary they control, that's type one. A type two civilization is stellar. They've exhausted the power of a planet and they get their energy directly from their mother star. They don't just go and get a sun tan on a weekend, they use solar flares. They use the power of the sun itself to energize their huge machines. Eventually they exhaust the power of a star and they go galactic. They harness the power of billions of stars within a galaxy. Now, what are we on this scale? We are type zero. We don't even rate on this scale. We get our energy from -- not from stars or galaxies -- we get our energy from dead plants: oil and coal.
Historians will look back and say: "Holy shit! They were making materials, selling them for corporation profit over and over and over and over again with absolutely no reference to what the planet had and recycling protocols and everything else. They were burning fossil fuels at a million times the rate of their actual renewability." They're gonna laugh at us, wondering what the hell kind of a primitive dumb-ass species we actually were. If we even survive to reach that point.
From an extra-terrestial perspective our global civilization is clearly on the edge of failure in the most important task it faces: preserving the lives and well-being of its citizens and the future habitability of the planet.
This transition is also the most important because it's not clear if we're gonna make it. When we look at outer space we see no evidence of type 1, 2 or 3 anywhere. No evidence whatsoever. The mathematics say that there should be thousands of type 1, 2 and 3 civilizations in the galaxy. We see no evidence of any whatsoever. And why is that? Because the transition from type zero to type one is the most dangerous of all transitions. We may not make it.
I hope everyone out there will understand that either we change or we die.
War, poverty, corruption, hunger, misery, human suffering will not change in the monetary system. That is, there'll be very little significant change. It's going to take the re-design of our culture and our values and it has to be related to the carrying capacity of the Earth. Not some human opinion or some politicians' notions of the way the world ought to be or some religious notions of the conduct of human affairs.
So again, the generation now alive and our grandchildren are the most important generations ever to walk the surface of the Earth. We are the generations that will determine whether we make the transition from type zero to type one or we destroy ourselves because of our arrogance and our weapons. Now, every time I read the newspaper I see evidence of this historic transition from type zero to type one and I am privileged to be alive in the most important era in the history of the human race: the transition from type zero to type one.
The old appeals to racial, sexual and religious chauvinism and to rabid nationalist fervor are beginning not to work. A new consciousness is developing which sees the Earth as a single organism and recognizes that an organism at war with itsself is doomed. We are one planet.
Jacque Fresco (born March 13, 1916), is a self-educated structural designer, philosopher of science, concept artist, educator, and futurist. His interests span a wide range of disciplines including several in philosophy, science, and engineering.
Fresco writes and lectures extensively on his view of subjects ranging from the holistic design of sustainable cities, energy efficiency, natural resource management, cybernated technology, advanced automation, and the role of science in society, focusing on the benefits he claims this will bring. With his colleague, Roxanne Meadows, he is the founder and director of an organization known as The Venus Project, located in Venus, Florida.
In contemporary culture he has been popularized by three documentaries, Future By Design, Zeitgeist Addendum, and Zeitgeist: Moving Forward, His Venus Project has been inspirational worldwide, especially to activists.
If the game does not load, just Refresh the page (press F5 key)
There is another, lost chapter to the Bible no one has ever read. A grand contest of strength has been organized by the Almighty and now the greatest icons from both Testaments must engage in ferocious, bloody battle to determine who is most worthy to earn a seat at the right hand of the Lord himself.
Bible Fight features a cast of Bible-school regulars. Bring down a rain of frogs on your enemies as Moses, or teach your enemies something about the sanctity of motherhood with the Virgin Mary’s Immaculate Deception bomb toss. Play as both pre- and post-cross Jesus Christ of Nazareth, unleashing a holy fury of Cross Smashes, Crown of Thorns Tosses and Stigmata blasts. Noah, Adam and Eve and Satan round out the list of holy combatants, each with their own special powers and deadly moves.
Instructions:
Tournament mode: Fight your way through a slate of opponents until you reach the final fight with God himself.
Practice mode: Practice your moves versus any computer-controlled character you want to.
Right and left arrow keys – Character movement
Up arrow key – Jump
Down arrow key – Block
Z / X – Attack
Each character has its own special moves. In-game, click on the "c" in the lower right corner of the screen to toggle the command list on and off.
Tips: Fight as God: Type JEHOVAH at the character select screen
Every nation is known for their specialty goods. Switzerland has its chocolates, France has its wine… and Thailand has its robot waiters. MK Restaurant has over 300 locations in Thailand, and has been looking for ways to modernize their operation. That includes robot greeters and servers. The MK Robot Project has encouraged Bangkok University to develop several different models that could do the job. They’ll have competition from Thailand-based CT Asia Robotics, which has already developed one restaurant-bot (Dinsow) and will soon launch another (Yumbo). Check out Dinsow and Bangkok University’s serving robot in the videos below. With a major restaurant chain backing the idea, and both academic and industrial support, Thailand might be the proving ground for the future of automated dining.
Dinsow is a wheeled robot with some decent speed and an overly happy disposition. While its batteries only last two to three hours, its personality seems to say it could go for miles just to get you a cup of coffee. The bot can be controlled via voice commands or PC base station up to 80 meters away. 10 copies of the Dinsow have served as greeters in MK Restaurants, but not as waiters. Dinsow’s arms look to be mostly for show. Not true for its sibling, Yumbo. The second CT Asia robot will be able to carry a tray and deliver food.
Yumbo is CT Asia's robot directly targeted to restaurants as a way to boost their sales. It can carry trays and change its facial expressions.
Bangkok University looks to be experimenting with several different possible forms for the MK Robot Project, all wheeled. The most promising is a model with a tray built into its chest. It can follow a line, escort someone by the arm, and avoid collisions with ultrasonics. They’ve even put it on a limited test run in a real restaurant, though you’ll have to judge its success for yourself:
Of course, Thailand’s efforts towards robotic waiters aren’t unique. China recently unveiled its own robot-themed restaurant, with their own home grown bots. Japan, too, is clearly into the concept, considering all the weird ways they’ve gotten industrial robots to serve food. In fact, Thailand’s first bot-enabled restaurant featured Motoman robots from Japan. Yet the Thai are making a strong effort to get restaurant-friendly robots into their mainstream. Dinsow only costs about $30,000 – not bad for this kind of market where restaurants might spend close to a million dollars to attract a crowd with automated servers. A low price point might be what restaurants need to take a chance and invest in the technology. In any case, whether they be from Thailand or elsewhere the robots of the world are here to serve.
German robotics researchers have built a hyper-strong hand that can withstand hammer blows!
This hand and its high-tech robophalanges come to you courtesy of the Institute of Robotics and Mechatronics at The German Aerospace Center (Deutsches Zentrum für Luft- und Raumfahrt e.V.).
The DLR hand is one of the most durable robotic hands ever built and was specifically built tough for jobs that might ding it up.
As IE EE Spectrum describes: The hand has the shape and size of a human hand, with five articulated fingers powered by a web of 38 tendons, each connected to an individual motor on the forearm. The main capability that makes the DLR hand different from other robot hands is that it can control its stiffness. The motors can tension the tendons, allowing the hand to absorb violent shocks. In one test, the researchers hit the hand with a baseball bat-a 66 G impact. The hand survived.
The hand has a total of 19 degrees of freedom, or only one less than the real thing, and it can move the fingers independently to grasp varied objects. The fingers can exert a force of up to 30 newtons at the fingertips, which makes this hand also one of the strongest ever built.
Additionally, the hand can catch heavy balls, adjust its level of stiffness to accomplish tasks that require a daintier touch, and snap its fingers. That's right, we're looking at the next star of the future's all-robot revue of West Side Story.
This type of robot, which is so incredibly versaitile, can be applied in a number of areas. It could, for example, be used for manufacturing. In places where handling the product demands high strenght and durability. Or in places where machines are endangered of being damaged, like mining. On the other side, it also helps to give robot hands the flexibility of the human hand, with a dozen times its strenght. This could prove very usefull in household robots, for example.
This video is by the awesome internet philosopher Stefan Moleneux of freedomainradio. His website can be found here :
http://www.freedomainradio.com
and his channel can be found here :
http://www.youtube.com/user/stefbot
Stefan Basil Molyneux (born 24 September 1966) is a Canadian philosopher, blogger, essayist, author, and host of the Freedomain Radio series of podcasts, living in Mississauga, Canada. He has written numerous articles and smaller essays which have been published on libertarian websites such as LewRockwell.com, antiwar.com and Strike The Root, recorded over 1800 podcasts, produced over 500 videos, and written numerous books which are all self-published except for his first, which was published by Publish America. In 2006 Stefan Molyneux quit his previous job in the field of computer software and works full-time on Freedomain Radio, a philosophical community website which is funded through donations.
@rockerme4u fucking hell, you are such a facist, do you even realise that?
voting will never change anything, all your doing is choosing directors of the corporation that is run for profit and poses as the benevolent caring force of stability in society when infact its causing most of the problems!
Neither stef in the video or myself are americans you dumbass.
(p)Link
Commenti
Storico
Stampa
Feed RSS 0.91
Feed Atom 0.3
