Identification of the Dynamics of a Moving Object with the Use of Neural Networks
Tóm tắt
A method for identification of the dynamics of a quadrotor-type vehicle is proposed. The method is based on the Elman recurrent neural network, which corresponds to the canonical form of a dynamic system in the space of states and does not require structural correction. The results of a numerical experiment reveal the convergence of the network learning algorithm with the use of an extended Kalman filter.
Tài liệu tham khảo
S. Khaikin, Neural Networks: Full Course (Williams Publishing House, Moscow, 2006) [in Russian].
V. S. Brusov and Yu. V. Tyumentsev, Neural Modeling of Motion of Flying Vehicles (MAI, Moscow, 2016) [in Russian].
S. A. Belokon’, Yu. N. Zolotukhin, and M. N. Filippov, “Method of Test Signal Design for Estimating the Aircraft Aerodynamic Parameters,” Avtometriya 53 (4), 59–65 (2017) [Optoelectron., Instrum. Data Process. 53 (4), 358–363 (2017)].
D. T. Pham and X. Liu, Neural Networks for Identification, Prediction and Control (Springer-Verlag, London, 1995).
R. S. M. Munoz, C. Rossi, and A. B. Cruz, “Modelling and Identification of Flight Dynamics in Mini-Helicopters Using Neural Networks,” in Aerial Vehicles, Ed. by T. M. Lam (InTech, Rijeka, Croatia, 2009), pp. 601–620.
S. A. Belokon’, Yu. N. Zolotukhin, A. S. Mal’tsev, et al., “Control of Flight Parameters of a Quadrotor Vehicle Moving over a Given Trajectory,” Avtometriya 48 (5), 32–41 (2012) [Optoelectron., Instrum. Data Process. 48 (5), 454–461 (2012)].
J. L. Elman, “Finding Structure in Time,” Cognitive Sci. 14 (2), 179–211 (1990). https://doi.org/www.sciencedirect.com/science/article/pii/036402139090002E.
R. J. Williams, “Some Observations on the Use of the Extended Kalman Filter as a Recurrent Network Learning Algorithm,” Tech. rep. NU-CCS-92-1 (Northeastern University, College of Computer Science, Boston, 1992). https://doi.org/pdfs.semanticscholar.org/4cc2/a29b33266a52afba78d9bd570f3480749aa8.pdf.
N. P. Rougier, Neural-Networks (GitHub, Inc.). https://doi.org/github.com/rougier/neuralnetworks.