If you were hoping that, after the Robopocalypse, you could earn your soylent green by flipping pancakes for our robot overlords, you're out of luck. Human researchers at the Italian Institute of Technology have taught a robot how to do it. No, they didn't refine it's programming; the robot learned how to complete the task:
The video shows a Barrett WAM 7 DOFs manipulator learning to flip pancakes by reinforcement learning. The motion is encoded in a mixture of basis force fields through an extension of Dynamic Movement Primitives (DMP) that represents the synergies across the different variables through stiffness matrices. An Inverse Dynamics controller with variable stiffness is used for reproduction.
The skill is first demonstrated via kinesthetic teaching, and then refined by Policy learning by Weighting Exploration with the Returns (PoWER) algorithm. Compared to policy-gradient approaches, the reward is treated as a pseudo-probability, which allows Reinforcement Learning to use probabilistic estimation methods such as Expectation-Maximization (EM).
After fifty attempts, the robot became a competent pancake-flipper.
via Popular Science | Previously: Rapid Pancake Sorting Robot