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.
More from Embodied
- Robot shows up at Costco to fetch the famous $1.50 hotdog — majidmanzarpour · 2026-10-16
- 15 Leju Kuavo humanoid robots run 2 months at Hangzhou auto-parts line, 98% success rate — CyberRobooo · 2026-10-16
- Baidu to give 1,000+ Hong Kong residents free robotaxi rides in city-first public trial — Baidu_Inc · 2026-10-16
- Auki demos spatial harness: robots and devices share spatial context via AR — broodsugar · 2026-10-16
- Tesla's 2-DOF car becomes 6-DOF flying demo — easier control problem than humanoids — micoolcho · 2026-10-16
- XREAL Aura, Android XR glasses powered by Gemini, named a TIME Best Invention of 2026 — DuRuofei · 2026-10-16