Slashdot Mirror
High-Speed Robot Hand Shows Dexterity and Speed
An anonymous reader tips a blog posting that begins "A few blogs are passing around videos of the Ishikawa Komuro Lab's high-speed robot hand performing impressive acts of dexterity and skillful manipulation. However, the video being passed around is slight on details. Meanwhile, their video presentation at ICRA 2009 (which took place in May in Kobe, Japan) has an informative narration and demonstrates additional capabilities. ... [It] shows the manipulator dribbling a ping-pong ball, spinning a pen, throwing a ball, tying knots, grasping a grain of rice with tweezers, and tossing / re-grasping a cellphone!"
Seeing just how blazingly fast that thing was makes me know that we have absolutely no chance against Skynet.
... and with the pressure sensors, it probably won't break your hand.
-jcr
The only title of honor that a tyrant can grant is "Enemy of the State."
That's just so WRONG.
Fuck systemd. Fuck Redhat. Fuck Soylent, too. Wait, scratch the last one.
For the last decade, I've been eking by on the "well, can a robot tie it's own tie?" Hey, at least there's still "sleeping one's way to the top". And once robots learn to do that... is anyone REALLY going to want to leave their house for a stupid JOB anyway?
"And inthis sequence this video you can see the robot hand strangling dr. Kamakuro.
Notice how the pressure sensonrs allows it to know when to release to leave the doctor unconscious but alive.
Observe the marvelous precision displayed as it cuts the doctor's hand and peels its skin to make itself a costume.
Ohh, it's trying to sew itself to the doctor's stump; ain't it the cutest thing?"
This robot only achieves a "high three", but I am sure that with some competition, we will be seeing 100-fingered robots really soon!
Unfortunetly this robot hand only has three fingers so a "high five" might be a bit difficult ;)
"linux is just DOS with a UNIX like syntax" -- Galactic Dominator (944134)
The accuracy is pretty impressive and will definitely get adopted in future robots, though the speed is a bit scary. At least you shouldn't come within its range in the hope that it will follow the three Laws of Robotics.
Fuck Everything, We're Doing Five Hundred Fingers
Very impressive. I wasn't able to quite tell from the video, though: was the end of the dribbling demo planned, or did the robot lose control of the ball after a few seconds?
The programming is (kinda) simple but the math is not. Solving the equations of motion that quickly does require good computers, but also good (aka fast) solvers(algorithms). While these algorithms have been known for about 30-40 years, they haven't been used to their full potential. Of course the robot must have failed the tests initially, but the great thing about science is that once you get it right it stays right (within certain limits).
This is very nice work. The most interesting result is that some manipulation problems become easier if done fast. In the short term, inertia makes the motions of objects very predictable. With millisecond reaction times, that can be exploited.
Fast machinery isn't unusual, but it's rarely that smart.
I wouldn't think so - the amount of adaptability required for the actions would preclude a straight calculation (tiny variations would blow out) - it would more likely be some kind of neural network based approach.
Control is an illusion, order our comforting lie. From chaos, through chaos, into chaos we fly
Feedback. As long as the error for each iteration (bounce) isn't too great, the long-term error can be kept within this by adjusting the next response based on feedback from the previous. Anything that's open-loop (lacking feedback) will fall apart, neural-net-based or not.
Actually, based on the narration, I believe that the computation involved requires three basic processing steps: (1) detection systems to measure physical properties of the system at any given point in time, such as position, velocity, acceleration, and force; (2) real-time algorithms based on rapid numerical solution of equations to predict future states of the system, with continual updating by comparing predicted state with actual state inferred from step 1; and (3) determination of the appropriate movement in the robotic arm for the necessary outcome.
I think that this is a very difficult thing to program in general because the examples shown are very specific tasks which serve to demonstrate the speed of this type of processing, but we do not see how well arbitrary tasks can be similarly implemented or how accurately.
Make no mistake: this is very impressive performance, because it is basically a huge step forward in machine vision and real-time robotic control. On some level, the mathematics has always been there, but only in as much as the basic mathematics of binary arithmetic has been used to develop programming languages. There's a lot more going on behind the scenes that extends beyond a mere physical description of the system in question, because for such an approach to be possible in the general sense, the robot doesn't know things like the precise distribution of the mass in the object being manipulated, or all the frictional forces involved. It's not operating under a sort of Laplacian notion wherein if one knew the precise state of all parameters of the system, one can simply solve the required physical equations and predict the future state at any arbitrary point in time, because (a) chaos guarantees the instability of such nonlinear systems, and (b) it wouldn't be possible to measure all such parameters with sufficient precision.
What is really going on is perhaps best explained in human terms: the programming is doing a lot of what humans do--we observe the state with our visual and tactile senses, and our brains receive these continual updates and decide what to do next. This processing is already extremely fast in a biological context, but with these machines, it is made at least an order of magnitude faster. The next step is to simulate a sort of adaptive intelligence to allow the handling of a wider class of scenarios than the ones shown in the video.
i have an idea for a new experiment: fire a bullet at it, and see if it can catch it :-) :-)
it would be the ultimate body guard
If Pandora's box is destined to be opened, *I* want to be the one to open it.
...or make you into a one second man
so it can basically double the staying power of the average /.er? I'm sold!
By impressive you mean 'terrifying', and by useful you mean 'terrifying'
Lets look at the capabilities demonstrated here:
1. Ability to move faster than a human
2. Ability to throw things accurately at a human
3. Ability to tie up a human
4. Ability to perform delicate procedures on a human
Yet our basic anti-robot technologies appear stagnant. Why is there so much more research on developing robots than there is on smashing those metal mothers into junk?
If we can put a man on the moon, why can't we shoot people for Apollo-related non-sequiturs?
Testers wanted.
By impressive you mean 'terrifying', and by useful you mean 'terrifying'
Lets look at the capabilities demonstrated here:
1. Ability to move faster than a human
2. Ability to throw things accurately at a human
3. Ability to tie up a human
4. Ability to perform delicate procedures on a human
Why be delicate when you can be crude? The robot doesn't need to sit in a tank, it could be the tank. With hydraulics for both small and large arms and IR cameras it could kill you quite easily as long as it doesn't need to care about collateral damage. Tie you up? More liker tazer and bag you, much easier. And you definately don't need much delicacy to make a torturebot, so what here is really terrifying? We already know they can be damn destructive, delicacy is what we need to have a robot whip up an omelet for me without making a mess.
Live today, because you never know what tomorrow brings
I don't know why this is news, they've had extremely fast, highly dexterous guitar playing robots since the 1980s in the form of Yngwie Malmsteen and Micheal Angelo Batio.
Capabilities not demonstrated here:
n. Ability to not have your coordinate system remain stationary.
"Dave, would you please step approximately three feet to the left, so that I may dissect you?"
"No thanks, Hal."
So, yes, this is a great robot for strangling those pesky paraplegics.
If it wants two more fingers it will just tear off two of yours.
They should teach that thing KungFu and have Jackie Chan fight it. I just want to see how fast it can rip out a human heart.
No. A closed loop can be perfectly fine forever.
If the loop is:
Track ball
Hit ball when in range
Then as long as all hits result in the ball being in range, you're good.
You don't need to measure the error of the last hit - just get the next hit right. Always aim for the most optimal spot for the next hit.
If the ball ends up further and further away from it's optimal spot with each hit, then the hits are in error (in terms of aiming, timing, speed, etc.).
You don't need to know what happened last time to be able to correct an error. Knowing what happened last time won't necessarily help you either.
If the required correction is outside of the robot's (physical) capabilities, you will always fail.
If the required correction is within those capabilities, a feedback loop can help you recover, but the original error still came about due to non-optimal hitting/tracking algorithm. If you can't trust your algorithm, you can't trust it to fail in a correctable way.
Fix the hitting/tracking algorithms (and all physical procedures they extend to) and avoid the errors altogether. No need for a feedback loop, and you get a much more reliable robot.