Adaptiveness and consistency of expert based learning algorithms selecting reactions to human movements

摘要

Expert based learning algorithms have been used by robots to choose satisfying reactions to human movements. These algorithms often demonstrate random performance that tries to hit a balance between adaptiveness and consistency that matches human's preferences intuitively. This paper provides a rigorous way to quantify the adaptiveness and consistency of the expert based learning algorithms in the context of human robot interaction. It is discovered that a Markov chain model can be used to allow the analysis of both adaptiveness and consistency for several popular expert based learning algorithms. Success of the method has been seen in both simulation and experimental work.