ARMADA: Augmented Reality for Robot Manipulation and Robot-Free Data Acquisition

TL;DR

This paper introduces ARMADA, a system that uses augmented reality to enable natural human data collection for robot imitation learning without requiring physical robots, by providing real-time virtual robot feedback.

Contribution

ARMADA demonstrates how augmented reality can be used to collect high-quality robot manipulation data without physical robot access, improving data quality for imitation learning.

Findings

Live virtual robot feedback enhances data quality

Participants successfully performed tasks with improved accuracy

Physical robot replay confirms the effectiveness of the collected data

Abstract

Teleoperation for robot imitation learning is bottlenecked by hardware availability. Can high-quality robot data be collected without a physical robot? We present a system for augmenting Apple Vision Pro with real-time virtual robot feedback. By providing users with an intuitive understanding of how their actions translate to robot motions, we enable the collection of natural barehanded human data that is compatible with the limitations of physical robot hardware. We conducted a user study with 15 participants demonstrating 3 different tasks each under 3 different feedback conditions and directly replayed the collected trajectories on physical robot hardware. Results suggest live robot feedback dramatically improves the quality of the collected data, suggesting a new avenue for scalable human data collection without access to robot hardware. Videos and more are available at https://nataliya.dev/armada.