Titlebar

Export bibliographic data
Literature by the same author
plus on the publication server
plus at Google Scholar

 

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 to cite this document: urn:nbn:de:bvb:703-epub-5873-4

Title data

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

[img]
Format: PDF
Name: s41598-021-93760-1.pdf
Version: Published Version
Available under License Creative Commons BY 4.0: Attribution
Download (2MB)

Project information

Project title:
Project's official titleProject's id
Open Access PublizierenNo information

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.

Further data

Item Type: Article in a journal
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
DDC Subjects: 000 Computer Science, information, general works
Institutions of the University: Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Computer Science > Chair Applied Computer Science VIII > Chair Applied Computer Science VIII - Univ.-Prof. Dr. Jörg Müller
Faculties
Faculties > Faculty of Mathematics, Physics und Computer Science
Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Computer Science
Faculties > Faculty of Mathematics, Physics und Computer Science > Department of Computer Science > Chair Applied Computer Science VIII
Language: English
Originates at UBT: Yes
URN: urn:nbn:de:bvb:703-epub-5873-4
Date Deposited: 28 Oct 2021 09:11
Last Modified: 02 Nov 2021 09:08
URI: https://epub.uni-bayreuth.de/id/eprint/5873

Downloads

Downloads per month over past year