The video shows a Barrett WAM robot 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.

For pancake day special, the skill is first demonstrated via kinesthetic teaching, and then refined by Policy learning by Weighting Exploration with the Returns (PoWER) algorithm. After 50 trials, the robot learns that the first part of the task requires a stiff behavior to throw the pancake in the air, while the second part requires the hand to be compliant in order to catch the pancake without having it bounced off the pan.

from Dr. Petar Kormushev

via HAL

f33e8a874a3ec28bec89a5c1f7ead3f027a1f4e216b8ecc177