Rhythmic EKF for pose estimation during gait

Vladimir Joukov; Vincent Bonnet; Michelle Karg; Gentiane Venture; Dana Kulić

doi:10.1109/HUMANOIDS.2015.7363510

Rhythmic EKF for pose estimation during gait

Vladimir Joukov, Vincent Bonnet, Michelle Karg, Gentiane Venture, Dana Kulić

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

9 Citations (Scopus)

Abstract

Accurate estimation of lower body pose during gait is useful in a wide variety of applications, including design of bipedal walking strategies, active prosthetics, exoskeletons, and physical rehabilitation. In this paper an algorithm is developed to estimate joint kinematics during rhythmic motion such as walking, using inertial measurement units attached at the waist, knees, and ankles. The proposed approach combines the extended Kalman filter with a canonical dynamical system to estimate joint angles, positions, and velocities for 3 dimensional rhythmic lower body movement. The system incrementally learns the rhythmic motion over time, improving the estimate over a regular extended Kalman filter, and segmenting the motion into repetitions. The algorithm is validated in simulation and on real human walking data. It is shown to improve joint acceleration and velocity estimates over regular extended Kalman Filter by 40% and 37% respectively.

Original language	English
Title of host publication	2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015)
Editors	Frank Chongwoo Park
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	1167-1172
Number of pages	6
ISBN (Electronic)	9781479968855, 9781479968848
ISBN (Print)	9781479968862
DOIs	https://doi.org/10.1109/HUMANOIDS.2015.7363510
Publication status	Published - 28 Dec 2015
Externally published	Yes
Event	IEEE-RAS International Conference on Humanoid Robots 2015 - Seoul, Korea, Republic of (South) Duration: 3 Nov 2015 → 5 Nov 2015 Conference number: 15th

Publication series

Name	IEEE-RAS International Conference on Humanoid Robots
Publisher	IEEE, Institute of Electrical and Electronics Engineers
ISSN (Print)	2164-0572
ISSN (Electronic)	2164-0580

Conference

Conference	IEEE-RAS International Conference on Humanoid Robots 2015
Abbreviated title	Humanoids 2015
Country	Korea, Republic of (South)
City	Seoul
Period	3/11/15 → 5/11/15

Keywords

Acceleration
Accelerometers
Angular velocity
Kalman filters
Kinematics
Legged locomotion
Robot sensing systems

Access to Document

10.1109/HUMANOIDS.2015.7363510

Link to publication in Scopus

Cite this

Joukov, V., Bonnet, V., Karg, M., Venture, G., & Kulić, D. (2015). Rhythmic EKF for pose estimation during gait. In F. C. Park (Ed.), 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015) (pp. 1167-1172). (IEEE-RAS International Conference on Humanoid Robots). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/HUMANOIDS.2015.7363510

Joukov, Vladimir ; Bonnet, Vincent ; Karg, Michelle ; Venture, Gentiane ; Kulić, Dana. / Rhythmic EKF for pose estimation during gait. 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015). editor / Frank Chongwoo Park. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 1167-1172 (IEEE-RAS International Conference on Humanoid Robots).

@inproceedings{552c4c68b8e144aeb5a508d5783e0ed7,

title = "Rhythmic EKF for pose estimation during gait",

abstract = "Accurate estimation of lower body pose during gait is useful in a wide variety of applications, including design of bipedal walking strategies, active prosthetics, exoskeletons, and physical rehabilitation. In this paper an algorithm is developed to estimate joint kinematics during rhythmic motion such as walking, using inertial measurement units attached at the waist, knees, and ankles. The proposed approach combines the extended Kalman filter with a canonical dynamical system to estimate joint angles, positions, and velocities for 3 dimensional rhythmic lower body movement. The system incrementally learns the rhythmic motion over time, improving the estimate over a regular extended Kalman filter, and segmenting the motion into repetitions. The algorithm is validated in simulation and on real human walking data. It is shown to improve joint acceleration and velocity estimates over regular extended Kalman Filter by 40% and 37% respectively.",

keywords = "Acceleration, Accelerometers, Angular velocity, Kalman filters, Kinematics, Legged locomotion, Robot sensing systems",

author = "Vladimir Joukov and Vincent Bonnet and Michelle Karg and Gentiane Venture and Dana Kuli{\'c}",

year = "2015",

month = dec,

day = "28",

doi = "10.1109/HUMANOIDS.2015.7363510",

language = "English",

isbn = "9781479968862",

series = "IEEE-RAS International Conference on Humanoid Robots",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "1167--1172",

editor = "Park, {Frank Chongwoo}",

booktitle = "2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015)",

address = "United States of America",

note = "IEEE-RAS International Conference on Humanoid Robots 2015, Humanoids 2015 ; Conference date: 03-11-2015 Through 05-11-2015",

}

Joukov, V, Bonnet, V, Karg, M, Venture, G & Kulić, D 2015, Rhythmic EKF for pose estimation during gait. in FC Park (ed.), 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015). IEEE-RAS International Conference on Humanoid Robots, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 1167-1172, IEEE-RAS International Conference on Humanoid Robots 2015, Seoul, Korea, Republic of (South), 3/11/15. https://doi.org/10.1109/HUMANOIDS.2015.7363510

Rhythmic EKF for pose estimation during gait. / Joukov, Vladimir; Bonnet, Vincent; Karg, Michelle; Venture, Gentiane; Kulić, Dana.

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015). ed. / Frank Chongwoo Park. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 1167-1172 (IEEE-RAS International Conference on Humanoid Robots).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - Rhythmic EKF for pose estimation during gait

AU - Joukov, Vladimir

AU - Bonnet, Vincent

AU - Karg, Michelle

AU - Venture, Gentiane

AU - Kulić, Dana

N1 - Conference code: 15th

PY - 2015/12/28

Y1 - 2015/12/28

N2 - Accurate estimation of lower body pose during gait is useful in a wide variety of applications, including design of bipedal walking strategies, active prosthetics, exoskeletons, and physical rehabilitation. In this paper an algorithm is developed to estimate joint kinematics during rhythmic motion such as walking, using inertial measurement units attached at the waist, knees, and ankles. The proposed approach combines the extended Kalman filter with a canonical dynamical system to estimate joint angles, positions, and velocities for 3 dimensional rhythmic lower body movement. The system incrementally learns the rhythmic motion over time, improving the estimate over a regular extended Kalman filter, and segmenting the motion into repetitions. The algorithm is validated in simulation and on real human walking data. It is shown to improve joint acceleration and velocity estimates over regular extended Kalman Filter by 40% and 37% respectively.

AB - Accurate estimation of lower body pose during gait is useful in a wide variety of applications, including design of bipedal walking strategies, active prosthetics, exoskeletons, and physical rehabilitation. In this paper an algorithm is developed to estimate joint kinematics during rhythmic motion such as walking, using inertial measurement units attached at the waist, knees, and ankles. The proposed approach combines the extended Kalman filter with a canonical dynamical system to estimate joint angles, positions, and velocities for 3 dimensional rhythmic lower body movement. The system incrementally learns the rhythmic motion over time, improving the estimate over a regular extended Kalman filter, and segmenting the motion into repetitions. The algorithm is validated in simulation and on real human walking data. It is shown to improve joint acceleration and velocity estimates over regular extended Kalman Filter by 40% and 37% respectively.

KW - Acceleration

KW - Accelerometers

KW - Angular velocity

KW - Kalman filters

KW - Kinematics

KW - Legged locomotion

KW - Robot sensing systems

UR - http://www.scopus.com/inward/record.url?scp=84962270037&partnerID=8YFLogxK

U2 - 10.1109/HUMANOIDS.2015.7363510

DO - 10.1109/HUMANOIDS.2015.7363510

M3 - Conference Paper

AN - SCOPUS:84962270037

SN - 9781479968862

T3 - IEEE-RAS International Conference on Humanoid Robots

SP - 1167

EP - 1172

BT - 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015)

A2 - Park, Frank Chongwoo

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

T2 - IEEE-RAS International Conference on Humanoid Robots 2015

Y2 - 3 November 2015 through 5 November 2015

ER -

Joukov V, Bonnet V, Karg M, Venture G, Kulić D. Rhythmic EKF for pose estimation during gait. In Park FC, editor, 2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids 2015). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 1167-1172. (IEEE-RAS International Conference on Humanoid Robots). https://doi.org/10.1109/HUMANOIDS.2015.7363510