Using Machine Teaching to Boost Novices' Robot Teaching Skill

TL;DR

This paper presents a machine teaching framework that significantly improves novices' ability to teach robots, with retained and generalized skills demonstrated through a controlled study.

Contribution

It introduces a novel machine teaching approach for robot training that enhances novice teaching skills and generalizes to untrained skills.

Findings

Training improved teaching accuracy by 78.83%.

Subjects showed 63.69% improvement in teaching new skills.

The framework enables better generalization beyond trained tasks.

Abstract

Recent evidence has shown that, contrary to expectations, it is difficult for users, especially novices, to teach robots tasks through LfD. This paper introduces a framework that leverages MT algorithms to train novices to become better teachers of robots, and verifies whether such teaching ability is retained beyond the period of training and generalises such that novices teach robots more effectively, even for skills for which training has not been received. A between-subjects study is reported, in which novice teachers are asked to teach simple motor skills to a robot. The results demonstrate that subjects that receive training show average 78.83% improvement in teaching ability (as measured by accuracy of the skill learnt by the robot), and average 63.69% improvement in the teaching of new skills not included as part of the training.