Identification of Prototypical Task Executions Based on Smoothness as Basis of Human-to-Robot Kinematic Skill Transfer

TL;DR

This paper presents a method for human-to-robot skill transfer by identifying prototypical task executions through clustering based on smoothness and kinematic features, demonstrated with a tool-touching task.

Contribution

It introduces a novel approach to transfer human demonstrated skills to robots by clustering and identifying prototypical executions based on smoothness and kinematic data.

Findings

Prototypical task executions can be effectively identified using clustering.

Transferred task models improve robot performance in simulated tasks.

Skill and performance features are useful for analyzing and designing robotic applications.

Abstract

In this paper we investigate human-to-robot skill transfer based on the identification of prototypical task executions by clustering a set of examples performed by human demonstrators, where smoothness and kinematic features represent skill and task performance, respectively. We exemplify our skill transfer approach with data from an experimental task in which a tool touches a support surface with a target velocity. Prototypical task executions are identified and transferred to a generic robot arm in simulation. The results illustrate how task models based on skill and performance features can provide analysis and design criteria for robotic applications.