Abstract
An adaptive sliding mode control based on two neural networks is proposed in this paper for Quadrotor stabilization. This approach presents solutions to conventional control drawbacks as chattering phenomenon and dynamical model imprecision. For that reason two ANN for each quadrotor helicopter subsystem are implemented in the control loop, the first one is a Single Hidden Layer network used to approximate on line the equivalent control and the second feed-forward Network is used to estimate the ideal corrective term. The main purpose behind the use of ANN in the second part of SMC is to minimize the chattering phenomena and response time by finding optimal sliding gain and sliding surface slope. The learning algorithms of the two ANNs (equivalent and corrective controller) are obtained using the direct Lyapunov stability method. The simulation results are given to highlight the performances of the proposed control scheme.
Highlights
In the last years, unmanned aerial vehicles (UAV) have gained a strong interest
The present paper propose a new robust adaptive control that does not require any prior information on model dynamics based on the use of tow Neural Networks in parallel in the control loop to Quadrotor stabilization
A neural network adaptive control based on sliding mode technique for a class of unknown nonlinear MIMO system is proposed in this paper
Summary
In the last years, unmanned aerial vehicles (UAV) have gained a strong interest. The Quadrotor Helicopter is considered as one of the most popular UAV platform. The mains reasons for all this attention has stemmed from its simple construction and its large payload as compared with the conventional helicopter [1]. The dynamics of the Quadrotor are nonlinear and like the most flying robots, the Quadrotor helicopter is characterized by its under actuated nature which can make the difficult to control. The Quadrotor has six degrees of freedom and only four control inputs. To solve the Quadrotor UAV tracking control problem many techniques have been proposed [2, 3, 4, 5, 6, and 7] where the control objective is to tack three desired cartesian positions and a desired yaw angle
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
