Inferring control intent during seated balance using inverse model predictive control

Ahmed Ramadan, Jongeun Choi, Clark J. Radcliffe, John M. Popovich, N. Peter Reeves

Research output: Contribution to journalArticle

Abstract

Patients with low back pain are suggested to follow a protective coping strategy. Therefore, rehabilitation of these patients requires estimating their motor control strategies (the control intent). In this letter, we present an approach that infers the control intent by solving an inverse Model Predictive Control (iMPC) problem. The standard Model Predictive Control (MPC) structure includes constraints, therefore, it allows us to model the physiological constraints of motor control. We devised an iMPC algorithm to solve iMPC problems with experimentally collected output trajectories. We used experimental data of one healthy subject during a seated balance test that used a physical human-robot interaction. Results show that the estimated MPC weights reflected the task instructions given to the subject and yielded an acceptable goodness of fit. The iMPC solution suggests that the subject's control intent was dominated by minimizing the squared sum of a combination of the upper-body and lower-body angles and velocities.

Original languageEnglish
Article number8573906
Pages (from-to)224-230
Number of pages7
JournalIEEE Robotics and Automation Letters
Volume4
Issue number2
DOIs
Publication statusPublished - 2019 Apr 1

Fingerprint

Inverse Model
Model predictive control
Model Predictive Control
Motor Control
Control Problem
Human-robot Interaction
Human robot interaction
Rehabilitation
Pain
Goodness of fit
Patient rehabilitation
Control Algorithm
Control Strategy
Standard Model
Trajectories
Experimental Data
Trajectory
Angle
Output

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Human-Computer Interaction
  • Biomedical Engineering
  • Mechanical Engineering
  • Control and Optimization
  • Artificial Intelligence
  • Computer Science Applications
  • Computer Vision and Pattern Recognition

Cite this

Ramadan, Ahmed ; Choi, Jongeun ; Radcliffe, Clark J. ; Popovich, John M. ; Reeves, N. Peter. / Inferring control intent during seated balance using inverse model predictive control. In: IEEE Robotics and Automation Letters. 2019 ; Vol. 4, No. 2. pp. 224-230.
@article{5626f0a5dea9438bbdb411a2046a6226,
title = "Inferring control intent during seated balance using inverse model predictive control",
abstract = "Patients with low back pain are suggested to follow a protective coping strategy. Therefore, rehabilitation of these patients requires estimating their motor control strategies (the control intent). In this letter, we present an approach that infers the control intent by solving an inverse Model Predictive Control (iMPC) problem. The standard Model Predictive Control (MPC) structure includes constraints, therefore, it allows us to model the physiological constraints of motor control. We devised an iMPC algorithm to solve iMPC problems with experimentally collected output trajectories. We used experimental data of one healthy subject during a seated balance test that used a physical human-robot interaction. Results show that the estimated MPC weights reflected the task instructions given to the subject and yielded an acceptable goodness of fit. The iMPC solution suggests that the subject's control intent was dominated by minimizing the squared sum of a combination of the upper-body and lower-body angles and velocities.",
author = "Ahmed Ramadan and Jongeun Choi and Radcliffe, {Clark J.} and Popovich, {John M.} and Reeves, {N. Peter}",
year = "2019",
month = "4",
day = "1",
doi = "10.1109/LRA.2018.2886407",
language = "English",
volume = "4",
pages = "224--230",
journal = "IEEE Robotics and Automation Letters",
issn = "2377-3766",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Inferring control intent during seated balance using inverse model predictive control. / Ramadan, Ahmed; Choi, Jongeun; Radcliffe, Clark J.; Popovich, John M.; Reeves, N. Peter.

In: IEEE Robotics and Automation Letters, Vol. 4, No. 2, 8573906, 01.04.2019, p. 224-230.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Inferring control intent during seated balance using inverse model predictive control

AU - Ramadan, Ahmed

AU - Choi, Jongeun

AU - Radcliffe, Clark J.

AU - Popovich, John M.

AU - Reeves, N. Peter

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Patients with low back pain are suggested to follow a protective coping strategy. Therefore, rehabilitation of these patients requires estimating their motor control strategies (the control intent). In this letter, we present an approach that infers the control intent by solving an inverse Model Predictive Control (iMPC) problem. The standard Model Predictive Control (MPC) structure includes constraints, therefore, it allows us to model the physiological constraints of motor control. We devised an iMPC algorithm to solve iMPC problems with experimentally collected output trajectories. We used experimental data of one healthy subject during a seated balance test that used a physical human-robot interaction. Results show that the estimated MPC weights reflected the task instructions given to the subject and yielded an acceptable goodness of fit. The iMPC solution suggests that the subject's control intent was dominated by minimizing the squared sum of a combination of the upper-body and lower-body angles and velocities.

AB - Patients with low back pain are suggested to follow a protective coping strategy. Therefore, rehabilitation of these patients requires estimating their motor control strategies (the control intent). In this letter, we present an approach that infers the control intent by solving an inverse Model Predictive Control (iMPC) problem. The standard Model Predictive Control (MPC) structure includes constraints, therefore, it allows us to model the physiological constraints of motor control. We devised an iMPC algorithm to solve iMPC problems with experimentally collected output trajectories. We used experimental data of one healthy subject during a seated balance test that used a physical human-robot interaction. Results show that the estimated MPC weights reflected the task instructions given to the subject and yielded an acceptable goodness of fit. The iMPC solution suggests that the subject's control intent was dominated by minimizing the squared sum of a combination of the upper-body and lower-body angles and velocities.

UR - http://www.scopus.com/inward/record.url?scp=85063309222&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063309222&partnerID=8YFLogxK

U2 - 10.1109/LRA.2018.2886407

DO - 10.1109/LRA.2018.2886407

M3 - Article

AN - SCOPUS:85063309222

VL - 4

SP - 224

EP - 230

JO - IEEE Robotics and Automation Letters

JF - IEEE Robotics and Automation Letters

SN - 2377-3766

IS - 2

M1 - 8573906

ER -