Human-Robot Copilot for Data-Efficient Imitation Learning

TL;DR

This paper introduces a Human-Robot Copilot framework that enhances data-efficient imitation learning by enabling dexterous teleoperation across various manipulators, improving performance with fewer demonstrations.

Contribution

The proposed framework allows scalable, dexterous teleoperation compatible with diverse manipulators, reducing data collection effort while maintaining high imitation learning performance.

Findings

Higher performance with the same number of demonstrations.

Intermittent corrections make data collection more efficient.

Framework supports a wide range of manipulators.

Abstract

Collecting human demonstrations via teleoperation is a common approach for teaching robots task-specific skills. However, when only a limited number of demonstrations are available, policies are prone to entering out-of-distribution (OOD) states due to compounding errors or environmental stochasticity. Existing interactive imitation learning or human-in-the-loop methods try to address this issue by following the Human-Gated DAgger (HG-DAgger) paradigm, an approach that augments demonstrations through selective human intervention during policy execution. Nevertheless, these approaches struggle to balance dexterity and generality: they either provide fine-grained corrections but are limited to specific kinematic structures, or achieve generality at the cost of precise control. To overcome this limitation, we propose the Human-Robot Copilot framework that can leverage a scaling factor for dexterous teleoperation while maintaining compatibility with a wide range of industrial and research manipulators. Experimental results demonstrate that our framework achieves higher performance with the same number of demonstration trajectories. Moreover, since corrective interventions are required only intermittently, the overall data collection process is more efficient and less time-consuming.