Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING)

Research output: Contribution to journalConference articleResearchpeer review

Authors

Research Organisations

External Research Organisations

  • Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU Erlangen-Nürnberg)
View graph of relations

Details

Original languageEnglish
Pages (from-to)117-122
Number of pages6
JournalIFAC-PapersOnLine
Volume58
Issue number24
Early online date19 Nov 2024
Publication statusPublished - 2024
Event12th IFAC Symposium on Biological and Medical Systems, BMS 2024 - Villingen-Schwenningen, Germany
Duration: 11 Sept 202413 Sept 2024

Abstract

In this paper, we extend the Recurrent Inertial Graph-based Estimator (RING), a novel neural-network-based solution for Inertial Motion Tracking (IMT), to generalize across a large range of sampling rates, and we demonstrate that it can overcome four real-world challenges: inhomogeneous magnetic fields, sensor-to-segment misalignment, sparse sensor setups, and nonrigid sensor attachment. RING can estimate the rotational state of a three-segment kinematic chain with double hinge joints from inertial data, and achieves an experimental mean-absolute-(tracking)-error of 8.10 ± 1.19 degrees if all four challenges are present simultaneously. The network is trained on simulated data yet evaluated on experimental data, highlighting its remarkable ability to zero-shot generalize from simulation to experiment. We conduct an ablation study to analyze the impact of each of the four challenges on RING's performance, we showcase its robustness to varying sampling rates, and we demonstrate that RING is capable of real-time operation. This research not only advances IMT technology by making it more accessible and versatile but also enhances its potential for new application domains including non-expert use of sparse IMT with nonrigid sensor attachments in unconstrained environments.

Keywords

    Inertial Measurement Units, Magnetometer-free, Orientation Estimation, Recurrent Neural Networks, Sensor-to-Segment Alignment, Sparse Sensing

ASJC Scopus subject areas

Cite this

Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING). / Bachhuber, S.; Weygers, I.; Seel, T.
In: IFAC-PapersOnLine, Vol. 58, No. 24, 2024, p. 117-122.

Research output: Contribution to journalConference articleResearchpeer review

Bachhuber S, Weygers I, Seel T. Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING). IFAC-PapersOnLine. 2024;58(24):117-122. Epub 2024 Nov 19. doi: 10.48550/arXiv.2409.02502, 10.1016/j.ifacol.2024.11.022
Bachhuber, S. ; Weygers, I. ; Seel, T. / Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING). In: IFAC-PapersOnLine. 2024 ; Vol. 58, No. 24. pp. 117-122.
Download
@article{5e4b58fbb0854bcf9b75931734f6da71,
title = "Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING)",
abstract = "In this paper, we extend the Recurrent Inertial Graph-based Estimator (RING), a novel neural-network-based solution for Inertial Motion Tracking (IMT), to generalize across a large range of sampling rates, and we demonstrate that it can overcome four real-world challenges: inhomogeneous magnetic fields, sensor-to-segment misalignment, sparse sensor setups, and nonrigid sensor attachment. RING can estimate the rotational state of a three-segment kinematic chain with double hinge joints from inertial data, and achieves an experimental mean-absolute-(tracking)-error of 8.10 ± 1.19 degrees if all four challenges are present simultaneously. The network is trained on simulated data yet evaluated on experimental data, highlighting its remarkable ability to zero-shot generalize from simulation to experiment. We conduct an ablation study to analyze the impact of each of the four challenges on RING's performance, we showcase its robustness to varying sampling rates, and we demonstrate that RING is capable of real-time operation. This research not only advances IMT technology by making it more accessible and versatile but also enhances its potential for new application domains including non-expert use of sparse IMT with nonrigid sensor attachments in unconstrained environments.",
keywords = "Inertial Measurement Units, Magnetometer-free, Orientation Estimation, Recurrent Neural Networks, Sensor-to-Segment Alignment, Sparse Sensing",
author = "S. Bachhuber and I. Weygers and T. Seel",
note = "Publisher Copyright: {\textcopyright} 2024 Elsevier B.V.. All rights reserved.; 12th IFAC Symposium on Biological and Medical Systems, BMS 2024 ; Conference date: 11-09-2024 Through 13-09-2024",
year = "2024",
doi = "10.48550/arXiv.2409.02502",
language = "English",
volume = "58",
pages = "117--122",
number = "24",

}

Download

TY - JOUR

T1 - Dispelling Four Challenges in Inertial Motion Tracking with One Recurrent Inertial Graph-based Estimator (RING)

AU - Bachhuber, S.

AU - Weygers, I.

AU - Seel, T.

N1 - Publisher Copyright: © 2024 Elsevier B.V.. All rights reserved.

PY - 2024

Y1 - 2024

N2 - In this paper, we extend the Recurrent Inertial Graph-based Estimator (RING), a novel neural-network-based solution for Inertial Motion Tracking (IMT), to generalize across a large range of sampling rates, and we demonstrate that it can overcome four real-world challenges: inhomogeneous magnetic fields, sensor-to-segment misalignment, sparse sensor setups, and nonrigid sensor attachment. RING can estimate the rotational state of a three-segment kinematic chain with double hinge joints from inertial data, and achieves an experimental mean-absolute-(tracking)-error of 8.10 ± 1.19 degrees if all four challenges are present simultaneously. The network is trained on simulated data yet evaluated on experimental data, highlighting its remarkable ability to zero-shot generalize from simulation to experiment. We conduct an ablation study to analyze the impact of each of the four challenges on RING's performance, we showcase its robustness to varying sampling rates, and we demonstrate that RING is capable of real-time operation. This research not only advances IMT technology by making it more accessible and versatile but also enhances its potential for new application domains including non-expert use of sparse IMT with nonrigid sensor attachments in unconstrained environments.

AB - In this paper, we extend the Recurrent Inertial Graph-based Estimator (RING), a novel neural-network-based solution for Inertial Motion Tracking (IMT), to generalize across a large range of sampling rates, and we demonstrate that it can overcome four real-world challenges: inhomogeneous magnetic fields, sensor-to-segment misalignment, sparse sensor setups, and nonrigid sensor attachment. RING can estimate the rotational state of a three-segment kinematic chain with double hinge joints from inertial data, and achieves an experimental mean-absolute-(tracking)-error of 8.10 ± 1.19 degrees if all four challenges are present simultaneously. The network is trained on simulated data yet evaluated on experimental data, highlighting its remarkable ability to zero-shot generalize from simulation to experiment. We conduct an ablation study to analyze the impact of each of the four challenges on RING's performance, we showcase its robustness to varying sampling rates, and we demonstrate that RING is capable of real-time operation. This research not only advances IMT technology by making it more accessible and versatile but also enhances its potential for new application domains including non-expert use of sparse IMT with nonrigid sensor attachments in unconstrained environments.

KW - Inertial Measurement Units

KW - Magnetometer-free

KW - Orientation Estimation

KW - Recurrent Neural Networks

KW - Sensor-to-Segment Alignment

KW - Sparse Sensing

UR - http://www.scopus.com/inward/record.url?scp=85210855056&partnerID=8YFLogxK

U2 - 10.48550/arXiv.2409.02502

DO - 10.48550/arXiv.2409.02502

M3 - Conference article

AN - SCOPUS:85210855056

VL - 58

SP - 117

EP - 122

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8971

IS - 24

T2 - 12th IFAC Symposium on Biological and Medical Systems, BMS 2024

Y2 - 11 September 2024 through 13 September 2024

ER -

By the same author(s)