Ergodic imitation: Learning from what to do and what not to do

TL;DR

This paper introduces a novel learning from demonstration framework that uses ergodic metrics and negative demonstrations to enable robots to learn robust tasks efficiently, even from imperfect or suboptimal examples.

Contribution

It proposes a new algorithmic approach combining ergodic metrics and negative demonstrations for more robust and data-efficient robot learning from demonstrations.

Findings

Negative demonstrations can compensate for imperfect positive demonstrations.

Combined positive and negative demonstrations improve task learning efficiency.

Negative demonstrations alone can successfully teach certain skills.

Abstract

With growing access to versatile robotics, it is beneficial for end users to be able to teach robots tasks without needing to code a control policy. One possibility is to teach the robot through successful task executions. However, near-optimal demonstrations of a task can be difficult to provide and even successful demonstrations can fail to capture task aspects key to robust skill replication. Here, we propose a learning from demonstration (LfD) approach that enables learning of robust task definitions without the need for near-optimal demonstrations. We present a novel algorithmic framework for learning tasks based on the ergodic metric -- a measure of information content in motion. Moreover, we make use of negative demonstrations -- demonstrations of what not to do -- and show that they can help compensate for imperfect demonstrations, reduce the number of demonstrations needed, and highlight crucial task elements improving robot performance. In a proof-of-concept example of cart-pole inversion, we show that negative demonstrations alone can be sufficient to successfully learn and recreate a skill. Through a human subject study with 24 participants, we show that consistently more information about a task can be captured from combined positive and negative (posneg) demonstrations than from the same amount of just positive demonstrations. Finally, we demonstrate our learning approach on simulated tasks of target reaching and table cleaning with a 7-DoF Franka arm. Our results point towards a future with robust, data-efficient LfD for novice users.