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

All Science Journal Classification (ASJC) codes

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

Fingerprint Dive into the research topics of 'Inferring control intent during seated balance using inverse model predictive control'. Together they form a unique fingerprint.

  • Cite this