Tim-Salzmann/l4casadi

Use PyTorch Models with CasADi for data-driven optimization or learning-based optimal control. Supports Acados.

53
/ 100
Established

This tool helps engineers and researchers integrate machine learning models, specifically those built with PyTorch, into optimization frameworks like CasADi. It allows you to use your trained PyTorch models to define complex system dynamics or cost functions within optimal control and data-driven optimization problems. The input is a traceable and differentiable PyTorch model, and the output is a highly efficient, potentially hardware-accelerated component for numerical optimization.

560 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to embed data-driven insights from PyTorch models directly into robust numerical optimization routines for control systems or complex planning tasks.

Not ideal if your primary goal is general-purpose machine learning model deployment without a strong need for integrated numerical optimization or optimal control.

optimal-control robotics trajectory-planning system-optimization predictive-control
Stale 6m
Maintenance 2 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 16 / 25

How are scores calculated?

Stars

560

Forks

46

Language

Python

License

MIT

Last pushed

Jun 05, 2025

Commits (30d)

0

Dependencies

3

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/Tim-Salzmann/l4casadi"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.