ItalianInstituteOfTechnology
Latest
HyQ is the latest all-terrain quadruped bot, tells Big Dog to bring it on (video)
You might not know this, but you can literally never have enough all-terrain quadrupedal robots... at least according to us (John Connor might disagree). So, while HyQ from the Italian Institute of Technology might bear more than a passing resemblance to Boston Dynamic's Big Dog, we won't hold it against the creators. The Hydraulic Quadruped robot (HyQ for short) was first dreamed up in 2008, but the project is only now coming into its own. Researchers at IIT took the bot for a stroll outside of the confines of a laboratory and treadmill for the first time. They've also stepped up the treadmill testing by bumping up the incline and practically throwing obstacles at it. Impressively, HyQ holds his own, even as his creators pelt it with shipping pallets. Check out the video after the break to see the cybernetic crawler in action.
Fujitsu's HOAP-2 robot wipes whiteboards clean -- humankind next in line? (video)
They've taught them how to flip pancakes and shoot arrows, and now they're teaching humanoids to erase your whiteboard. That's right, the same folks who brought you iCub in a feathery headdress are back at it with Fujitsu's HOAP-2, a humanoid robot that looks like it's related to the Jetsons' maid, and can wipe a dry erase board clean via upper-body kinesthetic learning. While scientists force the robot's arm through a number of erasing movements, an attached force-torque sensor records the patterns, allowing HOAP-2 to mimic its previous actions, and voilà! You've got a blank slate. Sure, this little guy looks perfectly harmless in comparison with the bow-and-arrow-wielding iCub, but replace that eraser with a switchblade and the human race is in a whole world of hurt.
Robot arm learns to flip pancakes, can never know the joys of tasting one
We'd like to pretend to be all serious about the science behind teaching a robot arm to teach itself a complicated motion like pancake flipping. We'd drone on and on about how the combination of demonstrated motion, trial-and-error, and object motion tracking come together for some "Expectation-Maximization based Reinforcement Learning," but really we just can't stop giggling at all the pancake misses perpetrated by the robot on video, which can be found after the break.
