Data Selection for Training the Neural Fuser Applied to Autonomous UAV Navigation

Authors

  • G. Penha Neto Laboratório Associado de Computação e Matemática Aplicada, LABAC, Instituto Nacional de Pesquisas Espaciais, Av. dos Astronautas, 1.758 - Jardim da Granja, São José dos Campos - SP, 12227-010.
  • H. F. Campos Velho Laboratório Associado de Computação e Matemática Aplicada, LABAC, Instituto Nacional de Pesquisas Espaciais, Av. dos Astronautas, 1.758 - Jardim da Granja, São José dos Campos - SP, 12227-010.
  • E. H. Shiguemori Instituto de Estudos Avançados, IEAv,Trevo Coronel Aviador José Alberto Albano do Amarante 01 - Putim, São José dos Campos - SP, 12228-001.

DOI:

https://doi.org/10.5540/tcam.2022.024.01.00159

Keywords:

Self-configured neural network, Unmanned aerial vehicle, Cross-validation, k-fold

Abstract

Over the past few years, there has been a steady increase in the use of aircraft vehicles, in particular unmanned aerial vehicles (UAV). UAV navigation is generally controlled by a human pilot. But the challenge for the scientific community is to carry out autonomous navigation. Some solutions have been proposed for the UAV autonomous navigation. Studies indicate as a solution to use data fusion and/or image processing navigation. Kalman Filter (KF) can be employed as a data fuser, but the KF has disadvantages. An alternative to the KF is based on artificial intelligence. Here, the KF is replaced by a self-configured neural network. This work investigates a way to select data for training the neural fuser, based on crossvalidation techniques. The results are compared to the data fusion done by a KF.

Author Biographies

G. Penha Neto, Laboratório Associado de Computação e Matemática Aplicada, LABAC, Instituto Nacional de Pesquisas Espaciais, Av. dos Astronautas, 1.758 - Jardim da Granja, São José dos Campos - SP, 12227-010.

Engenheiro da Computação e Mestre em Computação Aplicada. Atualmente é aluno de Doutorado no Instituto Nacional de Pesquisas Espaciais - INPE, sob a orientação do Prof. Haroldo Fraga de Campos Velho. É professor assistente II na Faculdade Estadual de Tecnologia de São Paulo, campus São José dos Campos - SP.

H. F. Campos Velho, Laboratório Associado de Computação e Matemática Aplicada, LABAC, Instituto Nacional de Pesquisas Espaciais, Av. dos Astronautas, 1.758 - Jardim da Granja, São José dos Campos - SP, 12227-010.

Engenheiro químico (Pontifícia Universidade Católica do Rio Grande do Sul ? PUCRS, Brasil, 1983), Mestre e Doutor em ciências em Engenharia Mecânica (Universidade Federal do Rio Grande do Sul ? UFRGS, Brasil, 1988 and 1992), com ênfase em Engenharia Nuclear e Dinâmica dos Fluidos Computacional, respectivamente. A carreira acadêmica iniciou na Universidade de Caxias do Sul (UCS, Caxias do Sul, Brasil, 1987-1988), como professor de teoria de controle e métodos numéricos. É pesquisador do Instituto Nacional de Pesquisas Espaciais (INPE, Brazil) de 1988 até o momento, atuando no Laboratório Associado de Computação e Matemática Aplicada (LABAC), tornando-se Pesquisador Titular A-III desde 2005. Foi também Coordenador do programa de Pós-graduação de Computação Aplicada (CAP, 1999-2002) no INPE. Foi Chefe do LABAC-INPE (2001-2004), e vice-Coordenador da Coordenação de Tecnologias Especiais (COCTE-INPE, 2001-2004). Durante 2 períodos, foi membro eleito do Conselho Técnico-Científico do INPE (CTC-INPE, 2005-2008, 2012-2015). Foi Diretor Associado de Espaço e Ambiente (INPE, 2008-2010). Atuando em Associações profissionais como membro eleito do Conselho da Sociedade Brasileira de Matemática Aplicada e Computacional ? SBMAC (2005-2007) e é Presidente da Pan-American Association of Interdisciplinary Computational Sciences (PACIS, 2013 até o presente). Foi supervisor de 6 pesquisadores visitantes e pós-doutores, 26 doutore e 18 mestres em ciências. Seu interesse de pesquisa inclui problemas inversos em pesquisa espacial, modelagem matemática de turbulência atmosférica, aprendizado de máquina aplicado à geociências, redes neurais como uma nova técnica para assimilação de dados, computação científica e computação híbrida. Recebeu o prêmio da Academia de Ciências de Cuba em 2016, com a pesquisa intitulada <Aplicaciones de Inteligencia Artificial y minería de datos al diagnóstico de fallos y la estimación de parámetros> (http://www.revistaccuba.cu/index.php/revacc/issue/view/27/showToc). Em 2004, prêmio NEC Award, como um dos autores do <The best paper in the area of Applications in High-Performance Systems> - 16th Symposium on Computer Architecture and High Performance Computing (SBAC-PAD, Foz do Iguaçu, Brazil).

E. H. Shiguemori, Instituto de Estudos Avançados, IEAv,Trevo Coronel Aviador José Alberto Albano do Amarante 01 - Putim, São José dos Campos - SP, 12228-001.

É pesquisador do Instituto de Estudos Avançados (IEAv) do Departamento de Ciência e Tecnologia Aeroespacial (DCTA). Doutor em computação aplicada pelo Instituto Nacional de Pesquisas Espaciais (INPE) (2007). Mestre em Computação Aplicada pelo INPE (2002), possui graduação em Engenharia da Computação (1998) e em Ciências da Computação pela UBC (1999). É professor na Universidade Paulista (UNIP). É coordenador do curso de Engenharia da Computação da UNIP. Tem experiência na área de Ciência da Computação, atuando principalmente nos seguintes temas: Navegação Autônoma, Navegação Aérea Autônoma, Processamento de Imagens, Redes Neurais Artificiais, Problemas Inversos.

References

C. M. Gevaert, J. Tang, F. J. García-Haro, J. Suomalainen, and L. Kooistra, Combining hyperspectral uav and multispectral formosat-2 imagery for precision agriculture applications, 6th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2014.

J. P. Dash, M. S. Watt, G. D. Pearse, M. Heaphy, and H. S. Dungey, Assessing very high resolution uav imagery for monitoring forest health during a simulated disease outbreak, ISPRS Journal of Photogrammetry and Remote Sensing, 2017.

H. Daryanavard and A. Hari, Implementing face detection system on uav using raspberry pi platform, Iranian Conference on Electrical Engineering, 2018.

X. Yang, D. Lin, F. Zhang, T. Song, and T. Jiang, High accuracy active stando target geolocation using uav platform, IEEE International Conference on Signal, Information and Data Processing, 2019.

Y. Yamazaki, M. Tamaki, C. Premachandra, C. J. Perera, S. Sumathipala, and B. H. Sudantha, Victim detection using uav with on-board voice recognition system, Third IEEE International Conference on Robotic Computing, 2019.

V. P. Subba Rao and S. G. Rao, Design and modelling of anafordable uav based pesticide sprayer in agriculture applications, Fifth International Conference on Electrical Energy Systems, 2019.

X. Gao, H. Jia, Z. Chen, G. Yuan, and S. Yang, Uav security situation awareness method based on semantic analysis,IEEE International Conference on Power, Intelligent Computing and Systems, 2020.

K. P. Valavanis and G. J. Vachtsevanos, Handbook of Unmanned Aerial Vehicles. Springer Publishing Company, Incorporated, 2014.

E. Elezi, G. Cankaya, A. Boyaci, and S. Yarkan, The efect of electronic jammers on gps signals, 16th International Multi-Conference on Systems, Signals Devices (SSD), 2019.

H. Mei, H. Changyi, and W. Guangming, Novel method to evaluate the eectiveness of uav navigation spoong, IEEE International Conference on Electronic Measurement Instruments (ICEMI), 2019.

W. C. Jin, K. Kim, and W. J. Choi, Robust jamming algorithm for

location-based uav jamming system, IEEE Asia-Pacic Microwave Conference (APMC), 2019.

M. P. Arthur, Detecting signal spoong and jamming attacks in uav networks using a lightweight ids, International Conference on Computer, Information and Telecommunication Systems (CITS), 2019.

M. Grewal, A. Andrews, and C. Bartone, Global Navigation Satellite Systems, Inertial Navigation, and Integration. Wiley, 2019.

X. Sun, Z. Zhang, Y. Ji, S. Yan, W. Fu, and Q. Chen, Algorithm of ionospheric scintillation monitoring, in 7th International Conference on Digital Home (ICDH), 2018.

I. Gulati, H. Li, S. Stainton, M. Johnston, and S. Dlay, Investigation of ionospheric phase scintillation at middle-latitude receiver station, in International Symposium ELMAR, 2019.

A. Al-Ka, D. Martín, F. García, A. Escalera, and J. María Armingol, Survey of computer vision algorithms and applications for unmanned aerial vehicles, Expert Systems with Applications, 2018.

A. Khaldi, C. Bensalah, A. C. Braham, and B. Cherki, Uav attitude estimation using visual and inertial data fusion based on observer in so(3), in International Conference on Advanced Electrical Engineering (ICAEE), 2019.

B. Zhang and C. Xu, Research on uav attitude data fusion algorithm based on quaternion gradient descent, in International Conference on Communications, Information System and Computer Engineering (CISCE), 2019.

C. Corrado and K. Panetta, Data fusion and unmanned aerial vehicles (uavs) for rst responders, in IEEE International Symposium on Technologies for Homeland Security (HST), 2017.

G. Stamatescu, I. Stamatescu, D. Popescu, and C. Mateescu, Sensor fusion method for altitude estimation in mini-uav applications, in 7th International Conference on Electronics, Computers and Articial Intelligence (ECAI), 2015.

W. You, F. Li, L. Liao, and M. Huang, Data fusion of uwb and imu based on unscented kalman lter for indoor localization of quadrotor uav, 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), vol. 8, 2020.

X. Kong, G. Fang, L. Liu, and T. P. Tran, Low computational data fusion approach using ins and uwb for uav navigation tasks in gps-denied environments, in 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), 2019.

G. Conte and P. Doherty, Vision-based unmanned aerial vehicle navigation using geo-referenced information, Journal on Advances in Signal Processing, 2009.

X. Wang and W. Wang, Nonlinear signal-correction observer and application to uav navigation, IEEE Transactions on Industrial Electronics, 2019.

S. Adusumilli, D. Bhatt, H. Wang, V. Devabhaktuni, and P. Bhattacharya, A novel hybrid approach utilizing principal component regression and random forest regression to bridge the period of gps outages, Neurocomputing, 2015.

G. P. Neto, A. C. Paulino, H. F. Campos Velho, L. N. F. Guimarães, and E. H. Shiguemori, Computational intelligence for uav autonomous navigation with multisensor data fusion, in Proceedings of the Conference of Computational Interdisciplinary Science (CCIS 2019), 2019.

K. Bahador, K. Alaa, F. O. K., and S. N. R., Multisensor data fusion: A

review of the state-of-the-art, Information Fusion, vol. 14, no. 1, 2013.

Z. Nian and C. Jung, Cnn-based multi-focus image fusion with light eld

data, in IEEE International Conference on Image Processing (ICIP), 2019.

S. Yousuf and M. B. Kadri, Robot localization in indoor and outdoor environments by multi-sensor fusion, in 14th International Conference on Emerging Technologies (ICET), 2019.

X. Chen, Z. Xuelong, Z. Wang, M. Li, Y. Ou, and S. Yufan, Multi-frequency data fusion for attitude estimation based on multi-layer perception and cubature kalman lter, IEEE Access, 2020.

G. P. Neto, H. F. Campos Velho, and E. H. Shiguemori, Uav autonomous navigation by data fusion and fpga, Mecánica Computacional, vol. 37, pp. 609 - 618, 2019.

J. A. Anochi and H. F. Campos Velho, Neural network for seasonal climate precipitation prediction on the brazil, Ciência e Natura, vol. 42, no. 0, p. 15, 2020.

J. Anochi, H. F. Campos Velho, H. Furtado, and E. P. Luz, Self-conguring two types of neural networks by mpca, Journal of Mechanics Engineering and Automation, 2015.

A. Paulino, L. Guimarÿes, and E. H. Shiguemori, Hybrid adaptive computational intelligence-based multisensor data fusion applied to real-time uav autonomous navigation, INTELIGENCIA ARTIFICIAL, vol. 22, pp. 162 - 195, 02 2019.

Z. Yingkun, Flight path planning of agriculture uav based on improved artificial potential eld method, in Chinese Control And Decision Conference,

A. Rabinowicz and S. Rosset, Cross-validation for correlated data, Journal of the American Statistical Association, 2020.

A. Rabinowicz and S. Rosset, Cross-validation for correlated data, Journal of the American Statistical Association, 2020.

R. F. Ausas, F. S. Sousa, and G. C. Buscaglia, An improved nite element space for discontinuous pressures, Comput Methods Appl Mech Engrg, vol. 199, no. 17-20, pp. 10191031, 2010.

T. S. Chihara, An introduction to orthogonal polynomials. Mathematics and its Applications Series, New York: Gordon and Breach, 1978.

R. J. Leveque, Finite volume methods for hyperbolic problems. Cambridge, 1998.

D. F. Cordeiro, F. S. Sousa, A. Castelo, and J. M. Nóbrega, Uma técnica de correção de interface para o método ISPH, TEMA - Tendências em Matemática Aplicada e Computacional, vol. 14, no. 3, pp. 347358, 2013.

R. Courant, Variational methods for the solution of problems of equilibrium and vibrations, Bull Amer Math Soc, vol. 49, pp. 1-23, 1943.

O. L. Linhares, Sobre a racionalização de dois algoritmos numéricos. PhD thesis, EESC, Universidade de São Paulo, São Carlos, SP, 1968.

W. Gautschi, A survey of gauss-christofel quadrature formulae, in E. B.

Christofel: The inuence of his work in mathematics and physics series (P. L.

Butzer and F. Feher, eds.), (Basel), pp. 72-147, Birkhäuser Verlag, 1981.

W. B. Jones, O. Njåstad, and W. J. Thron, Schur fractions, Perron

Carathéodory fractions and Szegö polynomials, a survey, in Analythic Theory of Continued Fractions II (W. J. Thron, ed.), vol. 1199, (Berlin), pp. 127-158, Springer Verlag, 1986.

L. M. Silva and A. R. L. Oliveira, Melhoria do desempenho da fatoração controlada de Cholesky no precondicionamento de sistemas lineares oriundos dos métodos de pontos interiores, in Proceeding Series of the Brazilian Society of Computational and Applied Mathematics, vol. 3, pp. 1-7, SBMAC, 2015.

Downloads

Published

2023-03-14

How to Cite

Penha Neto, G., Campos Velho, H. F., & Shiguemori, E. H. (2023). Data Selection for Training the Neural Fuser Applied to Autonomous UAV Navigation. Trends in Computational and Applied Mathematics, 24(1), 159–175. https://doi.org/10.5540/tcam.2022.024.01.00159

Issue

Vol. 24 No. 1 (2023)

Section

Original Article

License

Copyright

Authors of articles published in the journal Trends in Computational and Applied Mathematics retain the copyright of their work. The journal uses Creative Commons Attribution (CC-BY) in published articles. The authors grant the TCAM journal the right to first publish the article.

Intellectual Property and Terms of Use

The content of the articles is the exclusive responsibility of the authors. The journal uses Creative Commons Attribution (CC-BY) in published articles. This license allows published articles to be reused without permission for any purpose as long as the original work is correctly cited.

The journal encourages Authors to self-archive their accepted manuscripts, publishing them on personal blogs, institutional repositories, and social media, as long as the full citation is included in the journal's website version.