smidmatej/mpc_quad_ros

Model Predictive Controller for a quadcopter model using online learning with recursive Gaussian process regression in ROS-Gazebo

36
/ 100
Emerging

This project helps robotics engineers and researchers improve how quadcopters fly, especially at high speeds and in unpredictable conditions like unknown air drag. It takes real-time flight data, learns from it during operation, and uses that information to adjust the quadcopter's flight path. The result is a more accurate and stable flight, with the quadcopter staying closer to its intended trajectory.

No commits in the last 6 months.

Use this if you are developing or testing quadcopter control systems and need to dynamically adapt to unmodeled forces like air drag without extensive pre-training.

Not ideal if you require static, pre-tuned flight controllers for environments where external disturbances are well-known and consistent.

quadcopter-control aerial-robotics trajectory-tracking online-learning aerodynamic-modeling
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 13 / 25

How are scores calculated?

Stars

26

Forks

4

Language

Jupyter Notebook

License

GPL-3.0

Last pushed

Apr 21, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/smidmatej/mpc_quad_ros"

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