Plug-and-Play Sparse Inertial Motion Tracking With Sim-to-Real Transfer

Bachhuber S, Lehmann D, Dorschky E, Koelewijn A, Seel T, Weygers I (2023)

Publication Type: Journal article

Publication year: 2023

Journal

IEEE Sensors Letters IEEE

Book Volume: 7

Article Number: 7004904

Journal Issue: 10

DOI: 10.1109/LSENS.2023.3307122

Abstract

Inertial measurement units (IMUs) are used for inertial motion tracking (IMT) in a growing number of applications as sensor fusion methods are being advanced in three directions: magnetometer-free IMT methods that eliminate the effect of magnetic disturbances; sparse IMT approaches that lead to reduced setup complexity; and automatic self-calibration of sensor-to-segment positions or orientations. In this letter, we propose an approach that combines all three achievements and, for the first time, enables plug-and-play, magnetometer-free, and sparse IMT. This is accomplished by training a recurrent neural-network-based observer (RNNo) on just-in-time generated simulated motion data of kinematic chains. We demonstrate that domain-specific training data augmentations lead to a trained RNNo which zero shot generalizes to previously unseen experimental data and, thus, overcomes the sim-to-real gap. The trained RNNo achieves a tracking error of < 4 degrees when estimating the relative pose of a three-segment kinematic chain with two hinge joints. The proposed method offers a novel simulation-data-driven approach for solving complex sparse sensing problems while assuring robust and plug-and-play generalizability to experimental data.

Authors with CRIS profile

Simon Bachhuber Professur für Intelligente Sensomotorische Systeme Eva Dorschky Machine Learning and Data Analytics Lab Anne Koelewijn Juniorprofessur für Computational Movement Science (Stiftungsprofessur) Ive Weygers Professur für Intelligente Sensomotorische Systeme

Involved external institutions

Technische Universität Berlin DE Germany (DE) Gottfried Wilhelm Leibniz Universität Hannover DE Germany (DE)

How to cite

APA:

Bachhuber, S., Lehmann, D., Dorschky, E., Koelewijn, A., Seel, T., & Weygers, I. (2023). Plug-and-Play Sparse Inertial Motion Tracking With Sim-to-Real Transfer. IEEE Sensors Letters, 7(10). https://dx.doi.org/10.1109/LSENS.2023.3307122

MLA:

Bachhuber, Simon, et al. "Plug-and-Play Sparse Inertial Motion Tracking With Sim-to-Real Transfer." IEEE Sensors Letters 7.10 (2023).

BibTeX: Download