stanfordnmbl/osim-rl

Reinforcement learning environments with musculoskeletal models

51
/ 100
Established

This project helps biomechanical engineers and rehabilitation specialists simulate and develop controllers for 3D human musculoskeletal models. It takes in velocity commands and a simulated human model (with or without a prosthesis) and outputs optimal muscle activation patterns to achieve desired movements like walking or running with minimal effort. The primary users are researchers in biomechanics and prosthetics development.

944 stars. No commits in the last 6 months.

Use this if you need to design, test, or fine-tune prosthetic devices or develop robust control strategies for human movement in a physics-based simulation environment.

Not ideal if you are looking for a tool to analyze existing human motion data without needing to develop new control algorithms or simulate prosthetic interactions.

biomechanics prosthetics-design rehabilitation-engineering motor-control-simulation human-movement-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 25 / 25

How are scores calculated?

Stars

944

Forks

250

Language

Python

License

MIT

Last pushed

Jan 24, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/stanfordnmbl/osim-rl"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.