Modeling of Endpoint Feedback Learning Implemented Through Point-to-Point Learning Control

Shou Han Zhou, Ying Tan, Denny Oetomo, Chris Freeman, Etienne Burdet, Iven Mareels

Research output: Contribution to journalArticleResearchpeer-review

Abstract

In the last decade, several experiments were conducted to investigate human motor control behavior for the task of arm reaching, using only visual feedback of the final hand position at the end of each reaching motion. Current computational frameworks have yet to model that the humans learn to complete such a task by feedforward action based on the feedback of a displacement error at the end of past reaching motions. This paper demonstrates how such learning can be formulated as an optimization problem. By designing a cost function which weighs the tracking of the target and the smoothness of human motion, the constructed framework, implemented in the form of point-to-point learning control, inherently embeds the feedforward control and enables learning over repeated trials using only the available feedback from past observations, here the endpoint errors of a reaching motion trajectory. The proposed framework is able to reproduce the human learning behavior observed in experiments.

Original languageEnglish
Article number7707419
Pages (from-to)1576-1585
Number of pages10
JournalIEEE Transactions on Control Systems Technology
Volume25
Issue number5
DOIs
Publication statusPublished - 1 Sep 2017
Externally publishedYes

Keywords

  • Computational
  • computational neuroscience
  • human motor control
  • learning control (LC)
  • modeling
  • visuomotor learning

Cite this

Zhou, Shou Han ; Tan, Ying ; Oetomo, Denny ; Freeman, Chris ; Burdet, Etienne ; Mareels, Iven. / Modeling of Endpoint Feedback Learning Implemented Through Point-to-Point Learning Control. In: IEEE Transactions on Control Systems Technology. 2017 ; Vol. 25, No. 5. pp. 1576-1585.
@article{2bf489fafff945f78e1ec19dd274a5ae,
title = "Modeling of Endpoint Feedback Learning Implemented Through Point-to-Point Learning Control",
abstract = "In the last decade, several experiments were conducted to investigate human motor control behavior for the task of arm reaching, using only visual feedback of the final hand position at the end of each reaching motion. Current computational frameworks have yet to model that the humans learn to complete such a task by feedforward action based on the feedback of a displacement error at the end of past reaching motions. This paper demonstrates how such learning can be formulated as an optimization problem. By designing a cost function which weighs the tracking of the target and the smoothness of human motion, the constructed framework, implemented in the form of point-to-point learning control, inherently embeds the feedforward control and enables learning over repeated trials using only the available feedback from past observations, here the endpoint errors of a reaching motion trajectory. The proposed framework is able to reproduce the human learning behavior observed in experiments.",
keywords = "Computational, computational neuroscience, human motor control, learning control (LC), modeling, visuomotor learning",
author = "Zhou, {Shou Han} and Ying Tan and Denny Oetomo and Chris Freeman and Etienne Burdet and Iven Mareels",
year = "2017",
month = "9",
day = "1",
doi = "10.1109/TCST.2016.2615083",
language = "English",
volume = "25",
pages = "1576--1585",
journal = "IEEE Transactions on Control Systems Technology",
issn = "1063-6536",
publisher = "IEEE, Institute of Electrical and Electronics Engineers",
number = "5",

}

Modeling of Endpoint Feedback Learning Implemented Through Point-to-Point Learning Control. / Zhou, Shou Han; Tan, Ying; Oetomo, Denny; Freeman, Chris; Burdet, Etienne; Mareels, Iven.

In: IEEE Transactions on Control Systems Technology, Vol. 25, No. 5, 7707419, 01.09.2017, p. 1576-1585.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Modeling of Endpoint Feedback Learning Implemented Through Point-to-Point Learning Control

AU - Zhou, Shou Han

AU - Tan, Ying

AU - Oetomo, Denny

AU - Freeman, Chris

AU - Burdet, Etienne

AU - Mareels, Iven

PY - 2017/9/1

Y1 - 2017/9/1

N2 - In the last decade, several experiments were conducted to investigate human motor control behavior for the task of arm reaching, using only visual feedback of the final hand position at the end of each reaching motion. Current computational frameworks have yet to model that the humans learn to complete such a task by feedforward action based on the feedback of a displacement error at the end of past reaching motions. This paper demonstrates how such learning can be formulated as an optimization problem. By designing a cost function which weighs the tracking of the target and the smoothness of human motion, the constructed framework, implemented in the form of point-to-point learning control, inherently embeds the feedforward control and enables learning over repeated trials using only the available feedback from past observations, here the endpoint errors of a reaching motion trajectory. The proposed framework is able to reproduce the human learning behavior observed in experiments.

AB - In the last decade, several experiments were conducted to investigate human motor control behavior for the task of arm reaching, using only visual feedback of the final hand position at the end of each reaching motion. Current computational frameworks have yet to model that the humans learn to complete such a task by feedforward action based on the feedback of a displacement error at the end of past reaching motions. This paper demonstrates how such learning can be formulated as an optimization problem. By designing a cost function which weighs the tracking of the target and the smoothness of human motion, the constructed framework, implemented in the form of point-to-point learning control, inherently embeds the feedforward control and enables learning over repeated trials using only the available feedback from past observations, here the endpoint errors of a reaching motion trajectory. The proposed framework is able to reproduce the human learning behavior observed in experiments.

KW - Computational

KW - computational neuroscience

KW - human motor control

KW - learning control (LC)

KW - modeling

KW - visuomotor learning

UR - http://www.scopus.com/inward/record.url?scp=84994376764&partnerID=8YFLogxK

U2 - 10.1109/TCST.2016.2615083

DO - 10.1109/TCST.2016.2615083

M3 - Article

VL - 25

SP - 1576

EP - 1585

JO - IEEE Transactions on Control Systems Technology

JF - IEEE Transactions on Control Systems Technology

SN - 1063-6536

IS - 5

M1 - 7707419

ER -