Reinforcement Learning of 3D Musculoskeletal Model for Walking or Running with Minimum Efforts

Abstract

In this work we are trying to build a controller for a musculoskeletal model that has the goal of matching a given time-varying velocity vector. The major objective is building a musculoskeletal model which is fully comprehensive and reproduces realistic human movements driven by muscle contraction dynamics. Spectrum of human movement will be generated through variations in the anatomic model.