1
$\begingroup$

I am building a drone using the raspberry pi and I am using 6*PID controllers to control the speed and the value for each angle, can I use a recurrent neural network (RNN) or other neural network to stabilize the angles. If so what can the training data be? What type of neural network (NN) is best suited for this kind of application?

| improve this question | | | | |
$\endgroup$
  • $\begingroup$ What do you mean by "drove"? $\endgroup$ – DaemonMaker Oct 22 '14 at 19:56
  • $\begingroup$ Drone sorry, that was a typo ! $\endgroup$ – e-nouri Oct 23 '14 at 6:27
  • $\begingroup$ There are quite a few academic results that come up when googling "neural network PID". Why aren't those results helpful to you? $\endgroup$ – Ian Oct 23 '14 at 16:45
  • $\begingroup$ Thanks for the suggestion I already saw many of them, but most use the nn to tune the Ki,Kp,Kd values no the control action itself. $\endgroup$ – e-nouri Oct 23 '14 at 20:25
  • $\begingroup$ If you don't want to use a PID or a fuzzy logic controller, you could look into On Replacing PID Controller with Deep Learning Controller for DC Motor System. $\endgroup$ – koverman47 Jul 6 '18 at 21:15

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.