Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units

P.J. Kieliba, Petrus H. Veltink, T. Lisini Baldi, D. Prattichizzo, G. Santaera, A. Bicchi, M. Bianchi, Bernhard J.F. van Beijnum

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

1 Downloads (Pure)

Abstract

The correct estimation of human hand kinematics has received a lot of attention in many research fields of neuroscience and robotics. Not surprisingly, many works have addressed hand pose reconstruction (HPR) problem and several technological solutions have been proposed. Among them, Inertial and Magnetic Measurement Unit (IMMU) based systems offer some elegant characteristics (including cost-effectiveness) that make these especially suited for wearable and ambulatory HPR. However, what still lacks is an exhaustive characterization of IMMU-based orientation tracking algorithms performance for hand tracking purposes. In this work, we have developed an experimental protocol to compare the performance of three of the most widely adopted HPR computational techniques, i.e. extended Kalman filter (EKF), Gauss-Newton with Complementary filter (CF) and Madgwick filter (MF), on the same dataset acquired through an IMMU-based sensing glove. The quality of the algorithms has been benchmarked against the ground truth measurement provided by an optical motion tracking system. Results suggest that performance of the three algorithms is similar, though the MF algorithm appears to be slightly more accurate in reconstructing the individual joint angles during static trials and to be the fastest one to run.
Original languageEnglish
Title of host publication 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)
PublisherIEEE
Pages676-683
Number of pages8
ISBN (Electronic)978-1-5386-7283-9
DOIs
Publication statusPublished - 6 Nov 2018
Event18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018 - Beijing Friendship Hotel, Beijing, China
Duration: 6 Nov 20189 Nov 2018
Conference number: 18
http://humanoids2018.csp.escience.cn/dct/page/1

Conference

Conference18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018
Abbreviated titleHumanoids 2018
CountryChina
CityBeijing
Period6/11/189/11/18
Internet address

Fingerprint

Units of measurement
Magnetic variables measurement
Extended Kalman filters
End effectors
Cost effectiveness
Kinematics
Robotics

Keywords

  • Hand Pose Reconstruction Algorithms, IMMUs, User Study, Comprison of Algorithms

Cite this

Kieliba, P. J., Veltink, P. H., Lisini Baldi, T., Prattichizzo, D., Santaera, G., Bicchi, A., ... van Beijnum, B. J. F. (2018). Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units. In 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids) (pp. 676-683). IEEE. https://doi.org/10.1109/HUMANOIDS.2018.8624929
Kieliba, P.J. ; Veltink, Petrus H. ; Lisini Baldi, T. ; Prattichizzo, D. ; Santaera, G. ; Bicchi, A. ; Bianchi, M. ; van Beijnum, Bernhard J.F. / Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units. 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE, 2018. pp. 676-683
@inproceedings{2d98fbc4595944198d0a98fb996707eb,
title = "Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units",
abstract = "The correct estimation of human hand kinematics has received a lot of attention in many research fields of neuroscience and robotics. Not surprisingly, many works have addressed hand pose reconstruction (HPR) problem and several technological solutions have been proposed. Among them, Inertial and Magnetic Measurement Unit (IMMU) based systems offer some elegant characteristics (including cost-effectiveness) that make these especially suited for wearable and ambulatory HPR. However, what still lacks is an exhaustive characterization of IMMU-based orientation tracking algorithms performance for hand tracking purposes. In this work, we have developed an experimental protocol to compare the performance of three of the most widely adopted HPR computational techniques, i.e. extended Kalman filter (EKF), Gauss-Newton with Complementary filter (CF) and Madgwick filter (MF), on the same dataset acquired through an IMMU-based sensing glove. The quality of the algorithms has been benchmarked against the ground truth measurement provided by an optical motion tracking system. Results suggest that performance of the three algorithms is similar, though the MF algorithm appears to be slightly more accurate in reconstructing the individual joint angles during static trials and to be the fastest one to run.",
keywords = "Hand Pose Reconstruction Algorithms, IMMUs, User Study, Comprison of Algorithms",
author = "P.J. Kieliba and Veltink, {Petrus H.} and {Lisini Baldi}, T. and D. Prattichizzo and G. Santaera and A. Bicchi and M. Bianchi and {van Beijnum}, {Bernhard J.F.}",
year = "2018",
month = "11",
day = "6",
doi = "10.1109/HUMANOIDS.2018.8624929",
language = "English",
pages = "676--683",
booktitle = "2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)",
publisher = "IEEE",
address = "United States",

}

Kieliba, PJ, Veltink, PH, Lisini Baldi, T, Prattichizzo, D, Santaera, G, Bicchi, A, Bianchi, M & van Beijnum, BJF 2018, Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units. in 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE, pp. 676-683, 18th IEEE-RAS International Conference on Humanoid Robots, Humanoids 2018, Beijing, China, 6/11/18. https://doi.org/10.1109/HUMANOIDS.2018.8624929

Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units. / Kieliba, P.J.; Veltink, Petrus H.; Lisini Baldi, T.; Prattichizzo, D.; Santaera, G.; Bicchi, A.; Bianchi, M.; van Beijnum, Bernhard J.F.

2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE, 2018. p. 676-683.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units

AU - Kieliba, P.J.

AU - Veltink, Petrus H.

AU - Lisini Baldi, T.

AU - Prattichizzo, D.

AU - Santaera, G.

AU - Bicchi, A.

AU - Bianchi, M.

AU - van Beijnum, Bernhard J.F.

PY - 2018/11/6

Y1 - 2018/11/6

N2 - The correct estimation of human hand kinematics has received a lot of attention in many research fields of neuroscience and robotics. Not surprisingly, many works have addressed hand pose reconstruction (HPR) problem and several technological solutions have been proposed. Among them, Inertial and Magnetic Measurement Unit (IMMU) based systems offer some elegant characteristics (including cost-effectiveness) that make these especially suited for wearable and ambulatory HPR. However, what still lacks is an exhaustive characterization of IMMU-based orientation tracking algorithms performance for hand tracking purposes. In this work, we have developed an experimental protocol to compare the performance of three of the most widely adopted HPR computational techniques, i.e. extended Kalman filter (EKF), Gauss-Newton with Complementary filter (CF) and Madgwick filter (MF), on the same dataset acquired through an IMMU-based sensing glove. The quality of the algorithms has been benchmarked against the ground truth measurement provided by an optical motion tracking system. Results suggest that performance of the three algorithms is similar, though the MF algorithm appears to be slightly more accurate in reconstructing the individual joint angles during static trials and to be the fastest one to run.

AB - The correct estimation of human hand kinematics has received a lot of attention in many research fields of neuroscience and robotics. Not surprisingly, many works have addressed hand pose reconstruction (HPR) problem and several technological solutions have been proposed. Among them, Inertial and Magnetic Measurement Unit (IMMU) based systems offer some elegant characteristics (including cost-effectiveness) that make these especially suited for wearable and ambulatory HPR. However, what still lacks is an exhaustive characterization of IMMU-based orientation tracking algorithms performance for hand tracking purposes. In this work, we have developed an experimental protocol to compare the performance of three of the most widely adopted HPR computational techniques, i.e. extended Kalman filter (EKF), Gauss-Newton with Complementary filter (CF) and Madgwick filter (MF), on the same dataset acquired through an IMMU-based sensing glove. The quality of the algorithms has been benchmarked against the ground truth measurement provided by an optical motion tracking system. Results suggest that performance of the three algorithms is similar, though the MF algorithm appears to be slightly more accurate in reconstructing the individual joint angles during static trials and to be the fastest one to run.

KW - Hand Pose Reconstruction Algorithms, IMMUs, User Study, Comprison of Algorithms

U2 - 10.1109/HUMANOIDS.2018.8624929

DO - 10.1109/HUMANOIDS.2018.8624929

M3 - Conference contribution

SP - 676

EP - 683

BT - 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids)

PB - IEEE

ER -

Kieliba PJ, Veltink PH, Lisini Baldi T, Prattichizzo D, Santaera G, Bicchi A et al. Comparison of Three Hand Pose Reconstruction Algorithms Using Inertial and Magnetic Measurement Units. In 2018 IEEE-RAS 18th International Conference on Humanoid Robots (Humanoids). IEEE. 2018. p. 676-683 https://doi.org/10.1109/HUMANOIDS.2018.8624929