2.9 KiB
mpc_python
I keep here my Jupyter notebooks on R&D on Model Predictive Control applyied to path-following problems in driverless vehicles. Includes also a Pybullet simulation to showcase the results. This mainly uses CVXPY as a framework. This repo contains code from other projecs, check them out in thr special thanks section.
Contents
Python Scripts
The settings for tuning the MPC controller are in the mpc_config class.
Scripts for running the algorithm with/without the pybullet simulation, these require some tidy up :/
python mpc_pybullet_demo/mpc_demo_pybullet.py
A simpler demo wich does not use pybullet is also provided, this is useful for debugging
python mpc_pybullet_demo/mpc_demo_pybullet.py
Jupyter Notebooks
-
State space model derivation -> analytical and numerical derivaion of the model
-
MPC -> implementation and testing of various tweaks/improvements
-
Obstacle Avoidance -> Using halfplane constrains to avaoid track collisions -> Sill work in progress
Results
Racing car model is from: https://github.com/erwincoumans/pybullet_robots.
Results:
To run the pybullet demo:
python3 mpc_demo/mpc_demo_pybullet.py
To run the simulation-less demo:
python3 mpc_demo/mpc_demo_pybullet.py
Requirements
The dependencies can be installed using pip ():
pip3 install --user --requirement requirements.txt