Slashdot Mirror
MIT's Cheetah Robot Runs Untethered
An anonymous reader writes: It's easy to make a robot walk, but hard to keep it from falling over. We've seen a number of crazy robot prototypes, but they're usually tethered and/or stuck on a treadmill. Now, researchers from MIT have developed an algorithm that allows their giant robot cheetah to run around outdoors at up to 10mph. They expect the robot to eventually hit speeds of 30mph. "The key to the bounding algorithm is in programming each of the robot's legs to exert a certain amount of force in the split second during which it hits the ground, in order to maintain a given speed: In general, the faster the desired speed, the more force must be applied to propel the robot forward. ... Kim says that by adapting a force-based approach, the cheetah-bot is able to handle rougher terrain, such as bounding across a grassy field." The MIT cheetah-bot also runs on a custom electric motor, which makes it significantly quieter than gas-powered robots. "Our robot can be silent and as efficient as animals. The only things you hear are the feet hitting the ground."
That article is written as if that crowd invented running using force control. Of course you use force control. Everybody in the field knows that by now. I patented that 20 years ago. The Scout II robot at McGill, developed by Prof. Martin Buehler, used that approach. Buehler went on to become the designer of BigDog, but never got much public credit for it and quit to work for iRobot.
The key to legged running in non-trivial situations is careful management of ground traction. Traction is first priority, then balance, then foot placement. Historically, everybody worried about foot placement first, but that turns out to be backwards. As soon as you get off flat surfaces with good traction, traction control dominates.
The next unsolved problem in that area is not going fast. It's starting, stopping, and turning fast. Most of the legged robots accelerate very slowly, and don't make abrupt high-speed turns. Big Dog starts by trotting in place, then extending the gait out. Starting fast, stopping fast, and turning fast are all facets of the same problem. You have to take one stride using completely different control algorithms than you use for normal locomotion. That's all I'm going to say about this for now.
No, as the american researchers are too busy visiting the sororities ;)
Weight/Inertia... This is MIT?
I can just see the military getting hot and excited about a battle field robot that can run as fast as a cheetah, jump over obstacles, with either a bomb strapped to it's back or a gun of sorts.
Who's funding these guys?
It's great technology but I don't think I'm being too cynical in struggling to imagine any practical applications outside of defence.
Robot greyhound races?
Their robot may be stat of the art, but their website sure isn't.
#DeleteChrome
Now all they need are robotic gazelles. Its silent electric motor lets it sneak up on its prey on the robo-savannah, consuming its delicious battery juices so it can live another day.
Corruption is convincing someone that the selfless ideal is the same as their selfish ideal.
If this is an implementation of a cheetah's running locomotion, it is a complete fail.
- When running, a cheetah's spine flexes. Not this robot.
- When running, a cheetah's hind legs land in front of its forelegs. Not this robot.
- When running, a cheetah's legs land with a full pacing stagger, ie left first then right. The feet on this robot land simultaneously.
Check out a real cheetah running. It's like they didn't do any research at all.
When our name is on the back of your car, we're behind you all the way!
One of the things that makes US reasearch strong is the ability of it's universities to attract te best and brightest from all around the world. This is nothing new - it has always been thus - though perhals this is incresingly so as the state of secondary education seems to be in decline compared to opter parts of the world.
When researchers stop coming to the US, the state of
research there will go into rapid decline.The US isn't alone though - it's the same story in Australia too.
Given the already established centres for excellence in the US, it's a favoured destination for smart and motivated people from India and Asia, as well as other parts of the world to further their education and opportunities.
Half the world's population is Asian or India/Bangadesh/Pakistan, so naturally you are going to see many from those regions. Be glad for it - or they would be busy innovationg wherever they came from instead of the US.
European researchers work at MIT and nobody beats an eye,
Asian researchers work at MIT and everybody looses their mind.
we're all doomed
Why not roll like Droideka? Have one spring for jumping over obstacles.
So how long until I can commute to work on a 4 legged motorbike style vehicle?
In general, the faster the desired speed, the more force must be applied to propel the robot forward.
I could've told 'em that.
systemd is Roko's Basilisk.
Starting fast, stopping fast, and turning fast are all facets of the same problem.
Reminds me of the old joke: I'm an excellent driver. I only have three problems : Starting, Stopping and Turning.
It's like someone read Fahrenheit 451 and thought, "I could make a mechanical hound!" A few years ago I remember they made a fuel cell that could run on meat as well. Add a good gas chromatography and they'll have a viscious man eating robot dog!
Just wait until African researcher works at MIT ...
Somehow this robot doesn't seem as creepy as the "big dog" we have seen so much of.
from the mechanical hound.
Just hope they don't figure out the jump glitch, they'll become invincible!
Exceptionally cool and really fast legged robot. I really liked the ability to alter its gait to bound over an obstacle.
But the defining characteristic of cheetah locomotion is not just the 70mph speed. It is the use of a long, flexible, back to power and lengthen the stride. This bot has a completely inflexible body and is solely powered via the leg joints. Not very cheetah-like. More like a sheep.
But sheep-bot is just not very cool. And if I had built the thing, I would have named it a cheetah robot too. Or maybe Mechanical Hound or Robot 451.
The guys in the video are clearly experts in their field but I feel their place should be answering an interviewer's questions and not promoting their product (at least not in english). It's perfectly OK for them to speak in their native language and have subtitles, but having them speak English in a promo video just distracts from the true message the video should send.
As a scientific programmer, I beginning to see a 'too much choice' scenario. There is now Rust, Dart, Julia, Swift, Go in the 'immature' languages scene, and Python, Ruby, Java, C# etc. in the mature language scene.
None of the new languages though are being developed with a a definite specific goal or enhancement. They are hardly ever 'feature-complete', in the sense that they are multi-purpose, cross-platform, with good standardized development tools on all platforms.
Almost feels like they are being developed 'cause we can.'
It leads to a lot of divided effort writing libraries and packages for so many languages. I for one am happy the Apple won't open-source Swift.
It would be better to simply enhance something like Python with JIT and integration into the browser etc. Attempts are being made, I know, but they aren't progressing early fast enough to be useful.
Entia non sunt multiplicanda praeter necessitatem.
universities cost needs to come down the Foreigner are not locked into loans like the USC are.
Now all they need are robotic gazelles.
That sounds like something a gazelle might say.
Mit der Dummheit kämpfen Götter selbst vergebens
This is no cheetah. 10 mph makes this more of a pig.
I hate the name smart car too. The smart car has no smarts. It's more of a small car.
The problem is not imported researchers - minds migrate all the time, and the U.S. just as Europe has not exited forever, having been built on colonized settlements of "imported workforce" which in U.S.' case is England, Netherlands etc. The point I am trying to make is that arguably there is no such thing as Americans, just as there is no such thing as Europeans and even Englishmen etc. It's all a question about how far back you want to track ancestry before you throw it out calling it "imported".
That said, I personally consider an American a person who has decided in his mind to integrate into a form of American culture (a different thing to label, but nonetheless) and will not consider treason, i.e. selling or giving his work to another country, such as one of his emigrated origin. That obviously is the threat and concern here.
However, there is another thing - if we consider that formal education and early upbringing makes a person, then one would consider an Asian immigrant who were brought up and schooled in Asia, as an Asian, not an American, even if they have gotten a job and lived their entire grown life in U.S. On the other hand, if we consider the adult life as making a person, then this Asian would indeed be considered an American.
I don't think there is one way of looking at this. "importing researchers" is a gross generalization and factors outlined above must be taken into account, in my opinion. Not all imported researchers are alike, and there is no shame admitting that the brain of this or that researcher has been formed elsewhere than U.S. or vice versa.
To follow up on my post above, let us consider Thomas Edison, a famous American inventor and by most accounts, a great person (please, no Tesla-related discussions ;-)
He is reported to be of Dutch ancestry, but his American/Canadian ancestry goes centuries back, and this makes a good case for simply calling him American on most if not all factors. Simpler put, the man is American without a doubt for most discussion cases and purposes.
Whether todays "American" researchers like associate professor Kim (presented in the MIT video above) can be considered American, is debatable, and what is more clear is that they are definitely LESS American than Thomas Edison was.
European researchers work at MIT and nobody beats an eye,
Asian researchers work at MIT and everybody looses their mind.
Uh, who is "everybody"? Certainly not MIT itself. Stats on their international students show that about 50% of all international students and scholars come from Asia, much more than Europe.
MIT cares about "diversity" numbers, sure, but they already can claim that they are a "minority majority" campus with over 51% of undergraduates from minorities. So, they'd really have no reason to further inflate the Asian numbers... unless, well, the Asian students were actually more qualified.
Which means Asian researchers are probably working at MIT because MIT actually is looking for highly qualified people -- and thus, MIT hired/admitted them.
The only people "losing their mind" are racists, who clearly aren't "everybody." (If they were, MIT wouldn't have such high numbers of minorities in the first place.)
And why are we discussing this anyway? TFA has a photo of the lab team, which is certainly not all Asian in composition.
Does MIT cheetah Dream of Electric Sheep?
But will it suck your dick?
I want my own stealth killing cheetah since I can't have the real thing. Less chance of them turning on their owners and eating them...
Until the robot uprising happens that is. I bow down to you my Cheetah overlords!
My opinions are completely my own and do not reflect those of any entity I may be associated with - including the voices
As a scientific programmer, I beginning to see a 'too much choice' scenario. There is now Rust, Dart, Julia, Swift, Go in the 'immature' languages scene, and Python, Ruby, Java, C# etc. in the mature language scene.
None of the new languages though are being developed with a a definite specific goal or enhancement. They are hardly ever 'feature-complete', in the sense that they are multi-purpose, cross-platform, with good standardized development tools on all platforms.
Almost feels like they are being developed 'cause we can.'
It leads to a lot of divided effort writing libraries and packages for so many languages. I for one am happy the Apple won't open-source Swift.
It would be better to simply enhance something like Python with JIT and integration into the browser etc. Attempts are being made, I know, but they aren't progressing early fast enough to be useful.
Why does this comment belong in this thread? It's nothing to do with the MIT Cheetah...
Release the mechanical hounds.
Get free satoshi (Bitcoin) and Dogecoins
Why do we need sneaky, agile robots? It seems we are mindlessly building our overlords. How long before we are trying to stuff brain/brain stem into a robot?
I object to power without constructive purpose. --Spock
American passport? American. Simple as that. There's no need to get all racisty on it.
European researchers work at MIT and nobody beats an eye, Asian researchers work at MIT and everybody looses their mind.
One of my favorite (oh sorry, favourite for you spelling challenged Euros :-) .. things about grad school was that our group of friends was from all over the world. I enjoyed being a "minority" white boy.
Because they're cool!
http://i.cubeupload.com/T6cyLu.png
Never been to Hawaii huh? Get out more it could be good for you.
http://www.youtube.com/watch?v...
Can't you trailer trash come up with some new tricks to amuse your betters?
Hasn't this already been accomplished a few years ago. Boston Dynamics has been doing this for awhile.
https://www.youtube.com/watch?...
Why do they want to make the robot more quiet? I want to be able to hear them when they are coming after me.
The Scout II robot galloping work was improved upon with the PAW system. Even the PAW galloping trials (http://www.youtube.com/watch?v=eRLJB3glQjQ) predates the Cheetah by eight years.
Why does MIT constantly get into the news for doing such obvious things? It is as if the real research they are conducting is in how to get press attention for repeating the work of others and promoting the obvious. This was done by Boston Dynamics long ago, although they were a little more realistic about naming their robots... this one looks and runs more like a pug than a cheetah.
"Our robot can be silent and as efficient as animals. The only things you hear are the feet hitting the ground."
He doesn't have very good hearing. Real animals can be a lot quieter than his motors. His robots are making sounds - he just isn't hearing them.
Furthermore his future goal of 30 mph is pretty slow. I have dogs that run twice that. Real cheetahs run almost three times that.
Not to diss his achievements with his robots but he should stop spinning the PR so hard. Exaggeration isn't necessary.
Watching the last few seconds of the video all I could think was:
Cover it in wool and you've built something an android might dream of....
Visit CryptoGnome in his home.
Did you actually read the GP post I was jokingly replying to?
Can't the US innovate in one of its most prestigious technology universities without importing researchers from Asia?
Well at least some mods got the joke...