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.Continue reading Robot arm learns to flip pancakes, can never know the joys of t
