Robust learning from demonstrations using multidimensional SAX

Abstract

Learning from demonstrations (LID) is gaining more popularity in robotics due to its promise of providing a human-friendly technique for teaching robots new skills by robotics-naive users. The two main approaches to LID are dynamic motor primitives (DMP) which models demonstrated motions as dynamical systems with the advantage flexibility in changing the motion's starting position, goal or speed and Gaussian Mixture Modelling/ Gaussian Mixture Regression (GMMlGMR) which represents demonstrated motions as mixt…