CHECK IT OUT
Normally, when a robot wants to pick something up that it's never seen
before, it either has to download a 3D model of the object, make its own 3D
model and analyze it, or be trained by a human on the right way to grip.
Unfortunately, none of these things are really practical to do in the fast paced
world of grocery checkout lines.
Researchers at Stanford University have figured out that in order to pick
something up, all you really need to know is whether a piece of it has the same
basic shape as the shape of your gripper. If it does, then you can most likely grip
it fairly well, and experimentally the success rate is better than 90 percent. Best
of all, you can extract this shape information from one simple (and quick) 3D scan, even if you've got a big cluttered pile
of stuff. Once the robot has picked up an object, it holds it up to its cameras to scan for the barcode, adds it to your tab,
and bags it for you. While you probably aren't going to see PR2s down at your local Trader Joe's, the code that's being
developed here could conceivably find its way into some kind of grocery robot in the future, or even into a robot that
picks up and puts away stuff in your house.
NASA GETS A SCOOP ON ASTEROID
Humberto Campins — the University of Central Florida professor who discovered ice on asteroids last year — is now
working on a new NASA project. The $8 million OSIRIS-REx is unmanned and will be launched in 2016 to map and take pieces
of asteroid 1999 RQ36 with its robotic arm.After returning to Earth to turn over the samples, it will then go into orbit around
the sun for other experiments. NASA is hoping to gain knowledge about our planet and track asteroids in the future.
The mission is a first of its kind. The actual flight to the nearby asteroid will pose challenges because asteroids have unusual
gravity fields and can rotate much quicker than planets. Navigating their space vehicle to land on this type of asteroid – millions
of miles away from Earth – and scoop up a sample of “primitive” space rock
also will be a first for the team. While Campins is leaving the navigation to
others on the team, he will work with lead investigator Michael Drake (from
the Lunar and Planetary Laboratory at the University of Arizona) on
choosing the best spot on the asteroid for obtaining the sample and what
this sample will tell us about the origins of life on Earth. The non-manned
mission could launch as early as 2016.
Money for the project will cover the cost to circle and analyze the
asteroid for a year with an array of special instruments to help select the
optimal sampling spot. That’s where a mechanism will scoop up the sample
and place it in a capsule. That capsule will later come back to Earth, splashing
in an ocean with the help of a parachute. Funds also cover the design of the
instrument that will lasso the sample and bring it back to Earth.
“The even harder work will begin once we have our sample,” Campins
said. “We will spend at least two years going over every piece of information we gather.”
The target — asteroid RQ36 — is about 600 yards in diameter and comes relatively close to Earth. The asteroid has even
been designated as “potentially hazardous” because there is a one in 1,800 chance that it could slam into Earth in 2170.
Ruth — a Robotized Unit for Tactility and Haptics — has been used by Ford in their
research center in Germany to help develop better vehicles. Engineers taught her to "feel"
what humans like with sensitive fingers and so that she can predict what new components
will be desirable to them. Ruth has worked on the operation of switches and textures of
material. The center claims the recent attempt at developing a better steering wheel
ended up with a 92% accuracy of judging what humans would prefer.
Ford engineers have recently been using Ruth to help design the optimal steering
wheel by comparing the robot’s measurements with detailed market research into
customer perceptions of quality, such as the softness of leather and foam combinations.
26 SERVO 07.2011