Open-Sourced Neural Adaptive MPC for Quadcopter Control

rsasaki0109 · x · 2026-08-13

A GitHub project demonstrates controlling a quadcopter using Constrained Model Predictive Control (MPC) integrated with an adaptive nonlinear-in-parameter neural network (NLPNN) acting as an observer/identifier for prediction.

The controller operates on a 20-step horizon and enforces various physical constraints, including actuator limits, input rates, altitude, velocity, attitude, and body rates. Developers can easily run the code via pip install and python main.py to visualize the results.

Original post →

More from Embodied

Embodied channel →