MASS(Muscle-Actuated Skeletal System)

Abstract

This code implements a basic simulation and control for full-body Musculoskeletal system. Skeletal movements are driven by the actuation of the muscles, coordinated by activation levels. Interfacing with python and pytorch, it is available to use Deep Reinforcement Learning(DRL) algorithm such as Proximal Policy Optimization(PPO).

Publications

Seunghwan Lee, Kyoungmin Lee, Moonseok Park, and Jehee Lee Scalable Muscle-actuated Human Simulation and Control, ACM Transactions on Graphics (SIGGRAPH 2019), Volume 37, Article 73.

Project Page : http://mrl.snu.ac.kr/research/ProjectScalable/Page.htm

Youtube : https://youtu.be/a3jfyJ9JVeM

Paper : http://mrl.snu.ac.kr/research/ProjectScalable/Paper.pdf

How to install

Install TinyXML, Eigen, OpenGL, assimp, Python3, etc...

sudo apt-get install libtinyxml-dev libeigen3-dev libxi-dev libxmu-dev freeglut3-dev libassimp-dev libpython3-dev python3-tk python3-numpy virtualenv ipython3 cmake-curses-gui libbullet-dev pybind11-dev

Install DART 6.8

Please refer to http://dartsim.github.io/ (Install version 6.8)

Manual from DART(http://dartsim.github.io/install_dart_on_ubuntu.html)

Install PIP things

You should first activate virtualenv.

virtualenv /path/to/venv --python=python3
source /path/to/venv/bin/activate

pytorch(https://pytorch.org/)
numpy, matplotlib

pip3 install numpy matplotlib ipython

How to compile and run

Resource

Our system require a reference motion to imitate. We provide sample references such as walking, running, and etc...

To learn and simulate, we should provide such a meta data. We provide default meta data in /data/metadata.txt. We parse the text and set the environment. Please note that the learning settings and the test settings should be equal.(metadata.txt should not be changed.)

Compile and Run

mkdir build
cd build
cmake .. 
make -j8

Run Training

cd python
source /path/to/virtualenv/
python3 main.py -d ../data/metadata.txt

All the training networks are saved in /nn folder.

Run UI

source /path/to/virtualenv/
./render/render ../data/metadata.txt

Run Trained data

source /path/to/virtualenv/
./render/render ../data/metadata.txt ../nn/xxx.pt ../nn/xxx_muscle.pt

If you are simulating with the torque-actuated model,

source /path/to/virtualenv/
./render/render ../data/metadata.txt ../nn/xxx.pt

Model Creation & Retargeting (This module is ongoing project.)

This requires Maya and MotionBuilder.

There is a sample model in data/maya folder that I generally use. Currently if you are trying to edit the model, you have to make your own export maya-python code and xml writer so that the simulation code correctly read the musculoskeletal structure. There is also a rig model that is useful to retarget a new motion.

lsw9021 / MASS