Converting Biomechanical Models from OpenSim to MuJoCo

Aleksi Ikkala*, Perttu Hämäläinen

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Abstract

OpenSim is a widely used biomechanics simulator with several anatomically accurate human musculo-skeletal models. While OpenSim provides useful tools to analyse human movement, it is not fast enough to be routinely used for emerging research directions, e.g., learning and simulating motor control through deep neural networks and Reinforcement Learning (RL). We propose a framework for converting OpenSim models to MuJoCo, the de facto simulator in machine learning research, which itself lacks accurate musculo-skeletal human models. We show that with a few simple approximations of anatomical details, an OpenSim model can be automatically converted to a MuJoCo version that runs up to 600 times faster. We also demonstrate an approach to computationally optimize MuJoCo model parameters so that forward simulations of both simulators produce similar results.

Original languageEnglish
Title of host publicationConverging Clinical and Engineering Research on Neurorehabilitation IV
Pages277-281
Number of pages5
ISBN (Electronic)978-3-030-70316-5
DOIs
Publication statusPublished - 2022
MoE publication typeA4 Article in a conference publication
EventInternational Conference on NeuroRehabilitation - Virtual, Online
Duration: 13 Oct 202016 Oct 2020
Conference number: 5

Publication series

NameBiosystems and Biorobotics
PublisherSpringer
Volume28
ISSN (Print)2195-3562
ISSN (Electronic)2195-3570

Conference

ConferenceInternational Conference on NeuroRehabilitation
Abbreviated titleICNR
CityVirtual, Online
Period13/10/202016/10/2020

Fingerprint

Dive into the research topics of 'Converting Biomechanical Models from OpenSim to MuJoCo'. Together they form a unique fingerprint.

Cite this