Simple MPPI Implementation with Python

Model Predictive Path-Integral (MPPI) Control is a promising sampling-based optimal control algorithm.
This repository is for understanding the basic idea of the algorithm.

Dependency

poetry : seting up python environment easily.
ffmpeg : mp4 movie writer

Setup

git clone https://github.com/MizuhoAOKI/python_simple_mppi.git
cd python_simple_mppi
poetry install

Usage

Path-Tracking

Run path-tracking simulation

cd python_simple_mppi
poetry run jupyter notebook notebooks/mppi_pathtracking.ipynb

Pendulum

Run simulation to swing up a pendulum.

cd python_simple_mppi
poetry run python scripts/mppi_pendulum.py

Run notebook if you would like to check mathematical explanations on the algorithm.
```
cd python_simple_mppi
poetry run jupyter notebook notebooks/mppi_pendulum.ipynb
```

CartPole

Run simulation of cartpole

cd python_simple_mppi
poetry run python scripts/mppi_cartpole.py

Run notebook if you would like to check mathematical explanations on the algorithm.
```
cd python_simple_mppi
poetry run jupyter notebook notebooks/mppi_cartpole.ipynb
```

References

G. Williams et al. "Information-Theoretic Model Predictive Control: Theory and Applications to Autonomous Driving"
- URL : https://ieeexplore.ieee.org/document/8558663
- PDF : https://arxiv.org/pdf/1707.02342.pdf

jiemingChen/python_simple_mppi