Ubiquitous Robot Control Through Multimodal Motion Capture Using Smartwatch and Smartphone Data

TL;DR

This paper introduces WearMoCap, an open-source library enabling robot control through multimodal motion capture using smartphones and smartwatches, achieving high accuracy in real-robot tasks and offering a portable alternative to traditional systems.

Contribution

The paper presents a novel open-source library that combines smartwatch and smartphone data for seamless robot control in various modes, enhancing accessibility and accuracy.

Findings

Placement accuracy within 2 cm of standard motion capture

Effective in three different control modes

Suitable for environments requiring ubiquitous motion capture

Abstract

We present an open-source library for seamless robot control through motion capture using smartphones and smartwatches. Our library features three modes: Watch Only Mode, enabling control with a single smartwatch; Upper Arm Mode, offering heightened accuracy by incorporating the smartphone attached to the upper arm; and Pocket Mode, determining body orientation via the smartphone placed in any pocket. These modes are applied in two real-robot tasks, showcasing placement accuracy within 2 cm compared to a gold-standard motion capture system. WearMoCap stands as a suitable alternative to conventional motion capture systems, particularly in environments where ubiquity is essential. The library is available at: www.github.com/wearable-motion-capture.