Learning One-Shot Imitation from Humans without Humans

TL;DR

This paper introduces a method enabling robots to learn one-shot imitation of human tasks without requiring real human demonstrations during training, using domain randomization and simulation data to achieve comparable real-world performance.

Contribution

The authors propose a novel approach using Task-Embedded Control Networks and domain randomization to enable sim-to-real transfer for one-shot imitation learning without real human data.

Findings

Achieves similar performance to real-data trained systems using only simulation data.

Successfully applies to pushing and placing tasks in both simulation and real-world environments.

Demonstrates effective sim-to-real transfer for human-like task imitation.

Abstract

Humans can naturally learn to execute a new task by seeing it performed by other individuals once, and then reproduce it in a variety of configurations. Endowing robots with this ability of imitating humans from third person is a very immediate and natural way of teaching new tasks. Only recently, through meta-learning, there have been successful attempts to one-shot imitation learning from humans; however, these approaches require a lot of human resources to collect the data in the real world to train the robot. But is there a way to remove the need for real world human demonstrations during training? We show that with Task-Embedded Control Networks, we can infer control polices by embedding human demonstrations that can condition a control policy and achieve one-shot imitation learning. Importantly, we do not use a real human arm to supply demonstrations during training, but instead leverage domain randomisation in an application that has not been seen before: sim-to-real transfer on humans. Upon evaluating our approach on pushing and placing tasks in both simulation and in the real world, we show that in comparison to a system that was trained on real-world data we are able to achieve similar results by utilising only simulation data.