A neural network control based on differential flatness for a quadrotor

Sebastião S. Cunha (1) , Benjamas Panomruttanarug (2) , Hamdam Al-Fazari (3) , Felix Mora-Camino (4)

1 Universidade Federal de Itajubá
2 King Mongkuts University of Technology
3 Oman Technological College
4 MAIAA - ENAC - Laboratoire de Mathématiques Appliquées, Informatique et Automatique pour l'Aérien

In this paper, a control strategy for a quadrotor using neural network and differential flatness is proposed. Since attitude and altitude of the quadrotor are differential flat outputs for its flight dynamics, neural networks are used to perform the inversion of the flight dynamics and provide the nominal input control for the quadrotor. Errors in modeling approximations and perturbations are fed back into an additional closed loop control structure in order to assure tracking accuracy. Numerical simulations are displayed for analysis

Mots clés: Artificial Neural Network; Differential Flatness; Non-linear Control

Domaines: Sciences de l'ingénieur [physics]; Automatique / Robotique

Sebastião S. Cunha, Benjamas Panomruttanarug, Hamdam Al-Fazari, Felix Mora-Camino. A neural network control based on differential flatness for a quadrotor. DINCON 2011, 10a Conferência Brasileira de Dinâmica, Controle e Aplicações, Aug 2011, Águas de Lindóia, SP, Brazil. pp.778-781, ⟨10.5540/DINCON.2011.001.1.0198⟩. ⟨hal-01346276⟩