Simulations of the human Musculoskeletal system can help in treatment of injuries, planning surgeries and prosthesis design. OpenSim provides a freely available open source software for the development of Musculoskeletal models and creating dynamic simulations of movement. This enables the learning of control and activations of the Musculoskeletal system with modern optimization methods. The use ofReinforcement Learning allows for direct control of activations via communicated actions. This thesis aims at demonstrating an implementation of a Deep Reinforcement Learning approach called Proximal Policy Optimization (PPO) to control muscle activation of an OpenSim model with one active muscle. Muscle activations arelearned given current position and velocity as well as target position and velocity. The results show a PPO-approach to muscle control of an OpenSim model that can be built upon for more advanced use with several active muscles and training withparallel environments .


    Access

    Download


    Export, share and cite



    Title :

    Reinforcement Learning for Musculoskeletal Control with an OpenSim Model


    Contributors:

    Publication date :

    2021-01-01


    Type of media :

    Theses


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629




    OpenSim Model Improvements to Support High Joint Angle Resistive Exercising

    Gallo, Christopher / Thompson, William / Lewandowski, Beth et al. | NTRS | 2016


    OpenSim Model Improvements to Support High Joint Angle Resistive Exercising

    C. Gallo / W. Thompson / B. Lewandowski et al. | NTIS | 2016


    Computational Modeling Using OpenSim to Simulate a Squat Exercise Motion

    Gallo, C. A. / Thompson, W. K. / Lewandowski, B. E. et al. | NTRS | 2015


    Learning to Ascend Stairs and Ramps:Deep Reinforcement Learning for a Physics-Based Human Musculoskeletal Model

    Adriaenssens, Aurelien J. C. / Raveendranathan, Vishal / Carloni, Raffaella | BASE | 2022

    Free access