Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems

Minas V. Liarokapis, Panagiotis Artemiadis, Pantelis T. Katsiaris, Kostas J. Kyriakopoulos, Elias S. Manolakos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

34 Citations (Scopus)

Abstract

Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.

Original languageEnglish (US)
Title of host publicationProceedings - IEEE International Conference on Robotics and Automation
Pages2287-2292
Number of pages6
DOIs
StatePublished - 2012

Fingerprint

Robotic arms
End effectors
Chemical activation
Musculoskeletal system
Muscle

Keywords

  • Boxplot Zones
  • Classification
  • ElectroMyoGraphy (EMG)
  • Learning Scheme
  • Muscular Co-Activation Patterns
  • Random Forests
  • Synergistic Profiles

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Liarokapis, M. V., Artemiadis, P., Katsiaris, P. T., Kyriakopoulos, K. J., & Manolakos, E. S. (2012). Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems. In Proceedings - IEEE International Conference on Robotics and Automation (pp. 2287-2292). [6225047] https://doi.org/10.1109/ICRA.2012.6225047

Learning human reach-to-grasp strategies : Towards EMG-based control of robotic arm-hand systems. / Liarokapis, Minas V.; Artemiadis, Panagiotis; Katsiaris, Pantelis T.; Kyriakopoulos, Kostas J.; Manolakos, Elias S.

Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 2287-2292 6225047.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Liarokapis, MV, Artemiadis, P, Katsiaris, PT, Kyriakopoulos, KJ & Manolakos, ES 2012, Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems. in Proceedings - IEEE International Conference on Robotics and Automation., 6225047, pp. 2287-2292. https://doi.org/10.1109/ICRA.2012.6225047
Liarokapis MV, Artemiadis P, Katsiaris PT, Kyriakopoulos KJ, Manolakos ES. Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems. In Proceedings - IEEE International Conference on Robotics and Automation. 2012. p. 2287-2292. 6225047 https://doi.org/10.1109/ICRA.2012.6225047
Liarokapis, Minas V. ; Artemiadis, Panagiotis ; Katsiaris, Pantelis T. ; Kyriakopoulos, Kostas J. ; Manolakos, Elias S. / Learning human reach-to-grasp strategies : Towards EMG-based control of robotic arm-hand systems. Proceedings - IEEE International Conference on Robotics and Automation. 2012. pp. 2287-2292
@inproceedings{8b523872d0cf472d8f5e8c3cd6cc18cf,
title = "Learning human reach-to-grasp strategies: Towards EMG-based control of robotic arm-hand systems",
abstract = "Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.",
keywords = "Boxplot Zones, Classification, ElectroMyoGraphy (EMG), Learning Scheme, Muscular Co-Activation Patterns, Random Forests, Synergistic Profiles",
author = "Liarokapis, {Minas V.} and Panagiotis Artemiadis and Katsiaris, {Pantelis T.} and Kyriakopoulos, {Kostas J.} and Manolakos, {Elias S.}",
year = "2012",
doi = "10.1109/ICRA.2012.6225047",
language = "English (US)",
isbn = "9781467314039",
pages = "2287--2292",
booktitle = "Proceedings - IEEE International Conference on Robotics and Automation",

}

TY - GEN

T1 - Learning human reach-to-grasp strategies

T2 - Towards EMG-based control of robotic arm-hand systems

AU - Liarokapis, Minas V.

AU - Artemiadis, Panagiotis

AU - Katsiaris, Pantelis T.

AU - Kyriakopoulos, Kostas J.

AU - Manolakos, Elias S.

PY - 2012

Y1 - 2012

N2 - Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.

AB - Reaching and grasping of objects in an everyday-life environment seems so simple for humans, though so complicated from an engineering point of view. Humans use a variety of strategies for reaching and grasping anything from the simplest to the most complicated objects, achieving high dexterity and efficiency. This seemingly simple process of reach-to-grasp relies on the complex coordination of the musculoskeletal system of the upper limbs. In this paper, we study the muscular co-activation patterns during a variety of reach-to-grasp motions, and we introduce a learning scheme that can discriminate between different strategies. This scheme can then classify reach-to-grasp strategies based on the muscular co-activations. We consider the arm and hand as a whole system, therefore we use surface ElectroMyoGraphic (sEMG) recordings from muscles of both the upper arm and the forearm. The proposed scheme is tested in extensive paradigms proving its efficiency, while it can be used as a switching mechanism for task-specific motion and force estimation models, improving EMG-based control of robotic arm-hand systems.

KW - Boxplot Zones

KW - Classification

KW - ElectroMyoGraphy (EMG)

KW - Learning Scheme

KW - Muscular Co-Activation Patterns

KW - Random Forests

KW - Synergistic Profiles

UR - http://www.scopus.com/inward/record.url?scp=84864495491&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84864495491&partnerID=8YFLogxK

U2 - 10.1109/ICRA.2012.6225047

DO - 10.1109/ICRA.2012.6225047

M3 - Conference contribution

AN - SCOPUS:84864495491

SN - 9781467314039

SP - 2287

EP - 2292

BT - Proceedings - IEEE International Conference on Robotics and Automation

ER -