MPC Controller with Data-Driven Model Identification

This project demonstrates how to identify a linear system model from data and then design a Model Predictive Controller (MPC) around it.

Project Structure

• model_exploration.ipynb Jupyter notebook for model identification. Uses data to fit a linear regression model of the system dynamics.

• main.py Implementation of a basic grid search MPC controller that leverages the identified model to compute optimal control inputs.

Installation

This project uses uv for dependency management.

1. Install uv (see the installation guide).
2. Sync dependencies:

   uv sync 
   

3. Activate the virtual environment:

   source .venv/bin/activate
   

Usage

Run model_exploration.ipynb to generate or inspect the identified linear model.

Run the controller: bash python main.py

All dependencies are pinned and managed via uv.