stanfordnmbl/osim-rl
Reinforcement learning environments with musculoskeletal models
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.
Stars
944
Forks
250
Language
Python
License
MIT
Category
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.
Related frameworks
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild