COACH: Cooperative Robot Teaching

TL;DR

This paper introduces COACH, a framework for cooperative robot teaching modeled as a Markov game, enabling robots to effectively teach physical tasks through interactive learning, demonstrated in simulation and real-world experiments.

Contribution

It formalizes cooperative robot teaching as a Markov game and provides an efficient approximate solution for interactive robot teaching tasks.

Findings

Successful application in simulated video game task

Effective real robot teaching demonstration

Framework enables scalable robot teaching

Abstract

Knowledge and skills can transfer from human teachers to human students. However, such direct transfer is often not scalable for physical tasks, as they require one-to-one interaction, and human teachers are not available in sufficient numbers. Machine learning enables robots to become experts and play the role of teachers to help in this situation. In this work, we formalize cooperative robot teaching as a Markov game, consisting of four key elements: the target task, the student model, the teacher model, and the interactive teaching-learning process. Under a moderate assumption, the Markov game reduces to a partially observable Markov decision process, with an efficient approximate solution. We illustrate our approach on two cooperative tasks, one in a simulated video game and one with a real robot.