Hybrid parallel neuro-controller for multirotor unmanned aerial vehicle
- 5 December 2016
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Abstract
This paper provides a new method of building a flight control system for multirotor unmanned aerial vehicle based on hybrid parallel neuro-controller that uses radial basis function artificial neural network. Activation functions of hidden layer neurons are optimized in a way that allows for online training. We show that proposed hybrid neuro-controller is more effective than traditional manually configured PID controller.Keywords
This publication has 7 references indexed in Scilit:
- A neuro-evolutionary approach to micro aerial vehicle control2010
- Robust neuro-control for a micro quadrotor2010
- Online Adaptive Critic Flight ControlJournal of Guidance, Control, and Dynamics, 2004
- Implementation of adaptive critic-based neurocontrollers for turbogenerators in a multimachine power systemIEEE Transactions on Neural Networks, 2003
- Adaptive predictive control of nonlinear time-varying systems using neural networks2002
- An on-line trained adaptive neural controllerIEEE Control Systems, 1995
- Identification and control of dynamical systems using neural networksIEEE Transactions on Neural Networks, 1990