Converting Biomechanical Models from OpenSim to MuJoCo

TL;DR

This paper introduces a framework to convert OpenSim biomechanical models into MuJoCo, enabling faster simulations suitable for machine learning applications, with validated similarity between the models' outputs.

Contribution

The authors present an automated conversion method from OpenSim to MuJoCo models, significantly increasing simulation speed and enabling new research in motor control and reinforcement learning.

Findings

Converted models run up to 600 times faster.

Simulations of both models produce similar results after optimization.

Framework simplifies integration of biomechanics with machine learning.

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.