#258: DART: Noise injection for robust imitation learning, with Michael Laskey April 14, 2018

from Robohub Podcast· ·

Michael Laskey on training robots to fold bedsheets (and other things) through imitation learning.

Toyota HSR Trained with DART to Make a Bed.

In this episode, Audrow Nash speaks with Michael Laskey, PhD student at UC Berkeley, about a method for robust imitation learning, called DART. Laskey discusses how DART relates to previous imitation learning methods, how this approach has been used for folding bed sheets, and on the importance of robotics leveraging theory in other disciplines.