A recurrent neural network model for generation of humanlike reaching movements

Yuta Tsuzuki, Naomichi Ogihara

Research output: Contribution to journalArticle

Abstract

We constructed a recurrent neural network model that can generate human reaching motion. Given a target position, the neural network model is capable of producing muscular activation signals that move the hand to the target endpoint, while solving the problem of musculoskeletal redundancy by dynamic relaxation of the energy functions embedded in the network. The proposed neural network model was integrated with a two-dimensional three-link eight muscle musculoskeletal model of the human arm to simulate arm reaching movements in the horizontal and sagittal planes. Our results demonstrate that the model is capable of generating natural arm movements that have spatiotemporal features, such as a slightly curved hand path and the characteristic bell-shaped velocity profile, that are similar to those of actual human movements. Some aspects of the proposed computational framework might be utilized in the central nervous system for generation of reaching movements.

Original languageEnglish
JournalAdvanced Robotics
DOIs
Publication statusAccepted/In press - 2018 Jan 1

Fingerprint

Recurrent neural networks
Neural networks
Neurology
Redundancy
Muscle
Chemical activation

Keywords

  • dynamics
  • motor control
  • muscle synergy
  • Musculoskeletal system
  • redundancy

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Software
  • Human-Computer Interaction
  • Hardware and Architecture
  • Computer Science Applications

Cite this

A recurrent neural network model for generation of humanlike reaching movements. / Tsuzuki, Yuta; Ogihara, Naomichi.

In: Advanced Robotics, 01.01.2018.

Research output: Contribution to journalArticle

@article{b942418a9c4e40feae61e91216c5763b,
title = "A recurrent neural network model for generation of humanlike reaching movements",
abstract = "We constructed a recurrent neural network model that can generate human reaching motion. Given a target position, the neural network model is capable of producing muscular activation signals that move the hand to the target endpoint, while solving the problem of musculoskeletal redundancy by dynamic relaxation of the energy functions embedded in the network. The proposed neural network model was integrated with a two-dimensional three-link eight muscle musculoskeletal model of the human arm to simulate arm reaching movements in the horizontal and sagittal planes. Our results demonstrate that the model is capable of generating natural arm movements that have spatiotemporal features, such as a slightly curved hand path and the characteristic bell-shaped velocity profile, that are similar to those of actual human movements. Some aspects of the proposed computational framework might be utilized in the central nervous system for generation of reaching movements.",
keywords = "dynamics, motor control, muscle synergy, Musculoskeletal system, redundancy",
author = "Yuta Tsuzuki and Naomichi Ogihara",
year = "2018",
month = "1",
day = "1",
doi = "10.1080/01691864.2018.1496031",
language = "English",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",

}

TY - JOUR

T1 - A recurrent neural network model for generation of humanlike reaching movements

AU - Tsuzuki, Yuta

AU - Ogihara, Naomichi

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We constructed a recurrent neural network model that can generate human reaching motion. Given a target position, the neural network model is capable of producing muscular activation signals that move the hand to the target endpoint, while solving the problem of musculoskeletal redundancy by dynamic relaxation of the energy functions embedded in the network. The proposed neural network model was integrated with a two-dimensional three-link eight muscle musculoskeletal model of the human arm to simulate arm reaching movements in the horizontal and sagittal planes. Our results demonstrate that the model is capable of generating natural arm movements that have spatiotemporal features, such as a slightly curved hand path and the characteristic bell-shaped velocity profile, that are similar to those of actual human movements. Some aspects of the proposed computational framework might be utilized in the central nervous system for generation of reaching movements.

AB - We constructed a recurrent neural network model that can generate human reaching motion. Given a target position, the neural network model is capable of producing muscular activation signals that move the hand to the target endpoint, while solving the problem of musculoskeletal redundancy by dynamic relaxation of the energy functions embedded in the network. The proposed neural network model was integrated with a two-dimensional three-link eight muscle musculoskeletal model of the human arm to simulate arm reaching movements in the horizontal and sagittal planes. Our results demonstrate that the model is capable of generating natural arm movements that have spatiotemporal features, such as a slightly curved hand path and the characteristic bell-shaped velocity profile, that are similar to those of actual human movements. Some aspects of the proposed computational framework might be utilized in the central nervous system for generation of reaching movements.

KW - dynamics

KW - motor control

KW - muscle synergy

KW - Musculoskeletal system

KW - redundancy

UR - http://www.scopus.com/inward/record.url?scp=85050995339&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050995339&partnerID=8YFLogxK

U2 - 10.1080/01691864.2018.1496031

DO - 10.1080/01691864.2018.1496031

M3 - Article

AN - SCOPUS:85050995339

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

ER -