HILO-MPC is a Python toolbox for easy, flexible and fast development of machine-learning-supported optimal control and estimation problems
HILO-MPC is a Python toolbox for easy, flexible and fast development of machine-learning-supported optimal control and estimation problems
HILO-MPC is a Python toolbox for easy, flexible and fast realization of machine-learning-supported optimal control, and estimation problems developed mainly at the Control and Cyber-Physical Systems Laboratory, TU Darmstadt, and the Laboratory for Systems Theory and Control, Otto von Guericke University. It can be used for model predictive control, moving horizon estimation, Kalman filters, solving optimal control problems and has interfaces to embedded model predictive control tools.
HILO-MPC can interface directly to TensorFlow and PyTorch to create machine learning models and the CasADi framework to efficiently build control and estimation problems. The machine learning models can be used (almost) everywhere in the setup of these problems.
Currently the following machine learning models are supported:
The following machine learning models are currently under development:
At the moment the following MPC and optimal control problems can be solved:
All the nonlinear MPCs support soft constraints, time-variant systems, time-varying parameters and can be used to solve minimum-time problems. They work for continuous-time and discrete-time models, in DAE or ODE form. Linear MPC is currently limited towards discrete-time models.
A rich set of examples is available, spanning:
Using Poetry (recommended):
poetry installOptional extras:
poetry install -E vizpoetry install -E mlFrom PyPI using pip:
pip install hilo-mpcPython support: 3.10–3.12 (aligned to current CasADi wheels). Newer versions may work once CasADi adds support.
HILO-MPC uses a minimal core installation by default. Additional features require optional dependencies, which are kept optional to avoid forcing users to install heavy packages they may not need.
Install specific feature sets using Poetry extras:
# Machine learning utilities (scikit-learn)
poetry install -E ml
# Plotting backends (Bokeh, Matplotlib)
poetry install -E viz
# TensorFlow backend for neural networks
poetry install -E tensorflow
# PyTorch backend for neural networks
poetry install -E pytorch
# Install multiple extras
poetry install -E ml -E viz -E tensorflowOr with pip:
pip install hilo-mpc[ml,viz,tensorflow]| Extra | Packages | Version Constraints | Purpose |
|---|---|---|---|
ml |
scikit-learn | ≥0.19.2 | Data preprocessing and normalization |
viz |
Bokeh | ≥2.3.0 | Interactive plotting |
| Matplotlib | ≥3.0.0 | Static plotting | |
tensorflow |
TensorFlow | ≥2.8.0 | Neural network training (TensorFlow backend) |
| TensorBoard | ≥2.8.0 | Training visualization | |
pytorch |
PyTorch | ≥1.2.0 | Neural network training (PyTorch backend) |
| TorchVision | ≥0.4.0 | PyTorch utilities |
Note: The package will raise informative errors if you try to use features that require uninstalled optional dependencies. This design keeps the core installation lightweight while allowing users to install only what they need.
Core Dependencies: CasADi, NumPy, SciPy, pandas, and prettytable are installed automatically with the base package.
The documentation can be found here. Note that this documentation is not complete and will be updated over time.
If you use HILO-MPC for your research, please cite the following publication:
@misc{pohlodek2022hilompc,
title = {Flexible development and evaluation of machine-learning-supported optimal control and estimation methods via {HILO-MPC}},
author = {Pohlodek, Johannes and Morabito, Bruno and Schlauch, Christian and Zometa, Pablo and Findeisen, Rolf},
publisher = {arXiv},
year = {2022},
doi = {10.48550/ARXIV.2203.13671}
}No open issues yet, or sync has not completed.