Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot

Fares J. Abu-Dakka; A. Valera; J. A. Escalera; M. Valles; V. Mata; Mohamed Abderrahim

doi:10.1007/978-3-319-22876-1_41

Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot

Fares J. Abu-Dakka^*
, A. Valera
, J. A. Escalera
, M. Valles
, V. Mata
, Mohamed Abderrahim

^*Tämän työn vastaava kirjoittaja

Ei julkaistu Aalto-yliopiston affiliaatiolla

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

11 Viittaukset (Web of Science)

Abstrakti

This paper presents a methodology for learning and adaptation of a 3-PRS parallel robot skills for ankle rehabilitation. Passive exercises have been designed to train dorsi/plantar flexion, inversion/eversion ankle movements. During exercises, forces may be high because patient cannot follow the desired trajectory. While small errors in the desired trajectory can cause important deviations in the desired forces, pure position control is inappropriate for tasks that require physical contact with the environment. The proposed algorithm takes as input the reference trajectory and force profile, then adapts the robot movement by introducing small offsets to the reference trajectory so that the resulting forces exerted by the patient match the reference profile. The learning procedure is based on Dynamic Movement Primitives (DMPs).

Alkuperäiskieli	Englanti
Otsikko	INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II
Toimittajat	H Liu, N Kubota, Zhu, R Dillmann, D Zhou
Kustantaja	Springer
Sivut	483-494
Sivumäärä	12
ISBN (painettu)	978-3-319-22875-4
DOI - pysyväislinkit	https://doi.org/10.1007/978-3-319-22876-1_41
Tila	Julkaistu - 2015
OKM-julkaisutyyppi	A4 Artikkeli konferenssijulkaisussa
Tapahtuma	International Conference on Intelligent Robotics and Applications - Portsmouth, Iso-Britannia Kesto: 24 elok. 2015 → 27 elok. 2015 Konferenssinumero: 8

Julkaisusarja

Nimi	Lecture Notes in Artificial Intelligence
Kustantaja	SPRINGER-VERLAG BERLIN
Vuosikerta	9245
ISSN (painettu)	0302-9743

Conference

Conference	International Conference on Intelligent Robotics and Applications
Lyhennettä	ICIRA
Maa/Alue	Iso-Britannia
Kaupunki	Portsmouth
Ajanjakso	24/08/2015 → 27/08/2015

Pääsy asiakirjaan

10.1007/978-3-319-22876-1_41

Siteeraa tätä

Abu-Dakka, F. J., Valera, A., Escalera, J. A., Valles, M., Mata, V., & Abderrahim, M. (2015). Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot. teoksessa H. Liu, N. Kubota, Zhu, R. Dillmann, & D. Zhou (Toimittajat), INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II (Sivut 483-494). (Lecture Notes in Artificial Intelligence; Vuosikerta 9245). Springer. https://doi.org/10.1007/978-3-319-22876-1_41

@inproceedings{60f8feb37700460887b6d19820410344,

title = "Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot",

abstract = "This paper presents a methodology for learning and adaptation of a 3-PRS parallel robot skills for ankle rehabilitation. Passive exercises have been designed to train dorsi/plantar flexion, inversion/eversion ankle movements. During exercises, forces may be high because patient cannot follow the desired trajectory. While small errors in the desired trajectory can cause important deviations in the desired forces, pure position control is inappropriate for tasks that require physical contact with the environment. The proposed algorithm takes as input the reference trajectory and force profile, then adapts the robot movement by introducing small offsets to the reference trajectory so that the resulting forces exerted by the patient match the reference profile. The learning procedure is based on Dynamic Movement Primitives (DMPs).",

keywords = "Parallel robots, Rehabilitation robots, Force control, Motion control, GAIT, KINEMATICS, TRAINER",

author = "Abu-Dakka, \{Fares J.\} and A. Valera and Escalera, \{J. A.\} and M. Valles and V. Mata and Mohamed Abderrahim",

year = "2015",

doi = "10.1007/978-3-319-22876-1\_41",

language = "English",

isbn = "978-3-319-22875-4",

series = "Lecture Notes in Artificial Intelligence",

publisher = "Springer",

pages = "483--494",

editor = "H Liu and N Kubota and Zhu and R Dillmann and D Zhou",

booktitle = "INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II",

address = "Germany",

note = "International Conference on Intelligent Robotics and Applications, ICIRA ; Conference date: 24-08-2015 Through 27-08-2015",

}

Abu-Dakka, FJ, Valera, A, Escalera, JA, Valles, M, Mata, V & Abderrahim, M 2015, Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot. julkaisussa H Liu, N Kubota, Zhu, R Dillmann & D Zhou (toim), INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II. Lecture Notes in Artificial Intelligence, Vuosikerta 9245, Springer, Sivut 483-494, International Conference on Intelligent Robotics and Applications, Portsmouth, Iso-Britannia, 24/08/2015. https://doi.org/10.1007/978-3-319-22876-1_41

Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot. / Abu-Dakka, Fares J.; Valera, A.; Escalera, J. A. et al.
INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II. toim. / H Liu; N Kubota; Zhu; R Dillmann; D Zhou. Springer, 2015. s. 483-494 (Lecture Notes in Artificial Intelligence; Vuosikerta 9245).

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussa › Conference article in proceedings › Scientific › vertaisarvioitu

TY - GEN

T1 - Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot

AU - Abu-Dakka, Fares J.

AU - Valera, A.

AU - Escalera, J. A.

AU - Valles, M.

AU - Mata, V.

AU - Abderrahim, Mohamed

N1 - Conference code: 8

PY - 2015

Y1 - 2015

N2 - This paper presents a methodology for learning and adaptation of a 3-PRS parallel robot skills for ankle rehabilitation. Passive exercises have been designed to train dorsi/plantar flexion, inversion/eversion ankle movements. During exercises, forces may be high because patient cannot follow the desired trajectory. While small errors in the desired trajectory can cause important deviations in the desired forces, pure position control is inappropriate for tasks that require physical contact with the environment. The proposed algorithm takes as input the reference trajectory and force profile, then adapts the robot movement by introducing small offsets to the reference trajectory so that the resulting forces exerted by the patient match the reference profile. The learning procedure is based on Dynamic Movement Primitives (DMPs).

AB - This paper presents a methodology for learning and adaptation of a 3-PRS parallel robot skills for ankle rehabilitation. Passive exercises have been designed to train dorsi/plantar flexion, inversion/eversion ankle movements. During exercises, forces may be high because patient cannot follow the desired trajectory. While small errors in the desired trajectory can cause important deviations in the desired forces, pure position control is inappropriate for tasks that require physical contact with the environment. The proposed algorithm takes as input the reference trajectory and force profile, then adapts the robot movement by introducing small offsets to the reference trajectory so that the resulting forces exerted by the patient match the reference profile. The learning procedure is based on Dynamic Movement Primitives (DMPs).

KW - Parallel robots

KW - Rehabilitation robots

KW - Force control

KW - Motion control

KW - GAIT

KW - KINEMATICS

KW - TRAINER

U2 - 10.1007/978-3-319-22876-1_41

DO - 10.1007/978-3-319-22876-1_41

M3 - Conference article in proceedings

SN - 978-3-319-22875-4

T3 - Lecture Notes in Artificial Intelligence

SP - 483

EP - 494

BT - INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II

A2 - Liu, H

A2 - Kubota, N

A2 - Zhu, null

A2 - Dillmann, R

A2 - Zhou, D

PB - Springer

T2 - International Conference on Intelligent Robotics and Applications

Y2 - 24 August 2015 through 27 August 2015

ER -

Abu-Dakka FJ, Valera A, Escalera JA, Valles M, Mata V, Abderrahim M. Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot. julkaisussa Liu H, Kubota N, Zhu, Dillmann R, Zhou D, toimittajat, INTELLIGENT ROBOTICS AND APPLICATIONS (ICIRA 2015), PT II. Springer. 2015. s. 483-494. (Lecture Notes in Artificial Intelligence). doi: 10.1007/978-3-319-22876-1_41

Trajectory Adaptation and Learning for Ankle Rehabilitation Using a 3-PRS Parallel Robot

Abstrakti

Julkaisusarja

Conference

Pääsy asiakirjaan

Sormenjälki

Siteeraa tätä