how can I modelize a Quadrotor using neural networks

1 次查看（过去 30 天）
fessi rabii
fessi rabii 2016-3-7
评论： chafea stiti 2022-11-18
Hello everyone;
I'am doing my PhD Thesis intitled "Diagnostic and neuronal predictive control fault tolerent of a Quadrotor", my actually task is How to modelize a Quadrotor using recurrent neural networks based on differential dynamic equations without data input / output beforehand. The model below is controlled with four controls [U1, U2, U3 and U4] to give the position and attitude statements and their velocities [roll, rollpoint, pitch, pitchpoint, yaw, yawpoint, x, xpoint, y, ypoint, z, zpoint]. [K1,......K6] are the aerodynamic constants of linear and rotational drag forces, the vector I=[Ix, Iy, Iz] is the inertial coefficients of drone and finally Jr is the inertial coefficient of each motor
How create these fonctions with multi-layer neurons and what is the type of suitable learning that i must follow it.
cordially.

请先登录，再回答此问题。

回答（0 个）

类别

在 Help Center 和 File Exchange 中查找有关 Deep Learning Toolbox 的更多信息

标签

产品

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by