Suche nach Personen

plus im Publikationsserver
plus bei Google Scholar

Bibliografische Daten exportieren
 

Reinforcement learning control of a biomechanical model of the upper extremity

DOI zum Zitieren der Version auf EPub Bayreuth: https://doi.org/10.15495/EPub_UBT_00005873
URN zum Zitieren der Version auf EPub Bayreuth: urn:nbn:de:bvb:703-epub-5873-4

Titelangaben

Fischer, Florian ; Bachynskyi, Myroslav ; Klar, Markus ; Fleig, Arthur ; Müller, Jörg:
Reinforcement learning control of a biomechanical model of the upper extremity.
In: Scientific Reports. Bd. 11 (2021) . - No. 14445.
ISSN 2045-2322
DOI der Verlagsversion: https://doi.org/10.1038/s41598-021-93760-1

Volltext

[thumbnail of s41598-021-93760-1.pdf]
Format: PDF
Name: s41598-021-93760-1.pdf
Version: Veröffentlichte Version
Verfügbar mit der Lizenz Creative Commons BY 4.0: Namensnennung
Download (2MB)

Angaben zu Projekten

Projekttitel:
Offizieller Projekttitel
Projekt-ID
Open Access Publizieren
Ohne Angabe

Abstract

Among the infinite number of possible movements that can be produced, humans are commonly assumed to choose those that optimize criteria such as minimizing movement time, subject to certain movement constraints like signal-dependent and constant motor noise. While so far these assumptions have only been evaluated for simplified point-mass or planar models, we address the question of whether they can predict reaching movements in a full skeletal model of the human upper extremity. We learn a control policy using a motor babbling approach as implemented in reinforcement learning, using aimed movements of the tip of the right index finger towards randomly placed 3D targets of varying size. We use a state-of-the-art biomechanical model, which includes seven actuated degrees of freedom. To deal with the curse of dimensionality, we use a simplified second-order muscle model, acting at each degree of freedom instead of individual muscles. The results confirm that the assumptions of signal-dependent and constant motor noise, together with the objective of movement time minimization, are sufficient for a state-of-the-art skeletal model of the human upper extremity to reproduce complex phenomena of human movement, in particular Fitts’ Law and the 2/3 Power Law. This result supports the notion that control of the complex human biomechanical system can plausibly be determined by a set of simple assumptions and can easily be learned.

Weitere Angaben

Publikationsform: Artikel in einer Zeitschrift
Keywords: Reinforcement Learning; Aimed Movements; Human Motor Control; Arm Dynamics; Upper Extremity; Modeling; Analysis; Fitts’ Law; Two-Thirds Power Law; 2/3 Power Law; Torque-driven; Minimum Time; SAC; Optimal Control; Optimization
Themengebiete aus DDC: 000 Informatik,Informationswissenschaft, allgemeine Werke
Institutionen der Universität: Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik > Lehrstuhl Angewandte Informatik VIII > Lehrstuhl Angewandte Informatik VIII - Univ.-Prof. Dr. Jörg Müller
Fakultäten
Fakultäten > Fakultät für Mathematik, Physik und Informatik
Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik
Fakultäten > Fakultät für Mathematik, Physik und Informatik > Institut für Informatik > Lehrstuhl Angewandte Informatik VIII
Sprache: Englisch
Titel an der UBT entstanden: Ja
URN: urn:nbn:de:bvb:703-epub-5873-4
Eingestellt am: 28 Okt 2021 09:11
Letzte Änderung: 02 Nov 2021 09:08
URI: https://epub.uni-bayreuth.de/id/eprint/5873

Downloads

Downloads pro Monat im letzten Jahr