SERVO 07.2014 27
Continued on page 68
WHAT’S THE CATCH?
Robots that deal with fast-moving objects tend to handle them in one
of two ways: they assume that the object is going to keep doing whatever
it's been doing, allowing them to predict what's going to happen; or they
constantly watch what the object is doing, and then continually update
what's going to happen to it by working very hard. The first way is unreliable
because the universe is unreliable and assumptions are dangerous. The
second way is very computationally intensive, which often makes it too slow
to feed useful instructions through a controller to a robot.
At the Learning Algorithms and Systems Laboratory at EPFL, they're
leveraging fast vision, fast computers, fast controllers, fast motors,
programming by demonstration, and object modeling to be able to snatch
unpredictably unbalanced flying objects straight out of the air.
The most impressive thing here is that the robot is able to catch objects that are both statically and
dynamically unbalanced. A baseball is balanced in that when you throw it, it will (with a few exceptions) follow a
predictable trajectory that depends on its speed, direction, and gravity. It's relatively easy to model. A hammer is
statically unbalanced in that when you throw it, the fact that it's substantially heavier on one end will cause it to
tumble somewhat erratically, making it harder to model. Something like a half full bottle of water is dynamically
unbalanced in that its changing center of gravity (caused by the mass of the water sloshing around inside it) can
cause it to spin in all sorts of crazy ways. Have fun trying to model that.
To catch things like this, the robot creates a model of the object that it's about to try to catch while the
object is flying through the air, after having been thrown from just a few feet away.
Also recently on the TED stage was techno-illusionist and veteran speaker Marco Tempest
with a new friend: EDI (pronounced “Eddie”) the robot. EDI — which stands for Electronic
Deceptive Intelligence — is Tempest’s latest techno-aide; a friendly Baxter robot who ponders
the difference between artificial and human intelligence.
“Robot,” the newly awakened EDI interrupts, was coined in 1921 in a science-fiction story
by Czech playwright Karel Capek. It comes from “robota,” meaning “forced labor.” According to
Tempest, mechanical robots of yore — the Victorian’s performing “thinking machines” — were
mere illusions compared to today’s intelligent robots. EDI, on the other hand, is very real with a
360 degree sonar detection system and two seven-axis arms.
“We are intrigued by the possibility of creating a mechanical version of ourselves. The
perfect robot would be indistinguishable from the human — and that scares us,” says Tempest.
Since we can’t read the facial features of robots, for example, we can’t anticipate their actions
— but that goes both ways. EDI agrees: “Humans are unpredictable. And irrational! I literally
have no idea what you guys are going to do next.”