smidmatej/mpc_quad_ros
Model Predictive Controller for a quadcopter model using online learning with recursive Gaussian process regression in ROS-Gazebo
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.
Stars
26
Forks
4
Language
Jupyter Notebook
License
GPL-3.0
Category
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.
Higher-rated alternatives
LucasAlegre/sumo-rl
Reinforcement Learning environments for Traffic Signal Control with SUMO. Compatible with...
hilo-mpc/hilo-mpc
HILO-MPC is a Python toolbox for easy, flexible and fast development of...
reiniscimurs/DRL-robot-navigation
Deep Reinforcement Learning for mobile robot navigation in ROS Gazebo simulator. Using Twin...
kyegomez/RoboCAT
Implementation of Deepmind's RoboCat: "Self-Improving Foundation Agent for Robotic Manipulation"...
OpenQuadruped/spot_mini_mini
Dynamics and Domain Randomized Gait Modulation with Bezier Curves for Sim-to-Real Legged Locomotion.