[waps]

Take it from someone who's tried making it work : grasping is too fucking hard. It looks so simple, a baby could do it. A hand grasping objects.

Many things that many people believe robots can do are in this category. The absolute state of the art is balancing (not walking) on 2 legs (which does allow you to move, but ...), and walking on 4 legs (it's not really walking like for example a cat does, but it's better than balancing)

But the control loop for grasping arbitrary 3d objects given a camera image of the object and the hand ... such a stupid thing is a completely unsolved problem, and it's we're not anywhere near solving it.

Here's how amazon sidesteps that problem : http://www.youtube.com/watch?v=6KRjuuEVEZs&noredirect=1

[emilga]

On the problem of grasping, can you please comment on this video [1]? Instead of making a robot "hand", they have filled a balloon with ground coffee beans. "Grasping" and "ungrasping" then simply becomes sucking air out of, and pushing air into the balloon.

Is there some downside to this that I'm not seeing?

[1] http://www.youtube.com/watch?v=ZKOI_lVDPpw

[VLM]

"Is there some downside to this that I'm not seeing?"

Most real world engineering problems boil down to long term reliability. Its just assumed you'll get your statics and dynamics correct and all that basic stuff, the actual brain power burned on the job is designing stuff that actually works 1M times and tolerates every component being 5% off the exact value or whatever. I think this would be a huge headache in the very long term reliability category.

[emilga]

Thanks. I did not know this.

[waps]

What you see in that movie, the uncooked egg pickup, is becoming somewhat of a litmus test. Trying to reliably instruct a robot to put some 20 eggs from one basket into another without breaking any, and without prior knowledge of the position of the eggs and so on, that'll mean a lot.

[arethuza]

That's a pretty clever solution - move the shelving to the picker, rather than the picker wandering about.