Image Processing for UAV Autonomous Navigation Applying Self-configuring Neural Network
Application and development of Unmanned Aerial Vehicles (UAV) have had a rapid growth. The flight control of these aircrafts can be performed remotely or autonomously. There are different strategies for the UAV autonomous navigation. The positioning estimation can be done by using inertial sensors and General Navigation Satellite Systems (GNSS). The use of the GNSS signal can present some difficulties: natural or not natural interference. An alternative for positioning adjustment is to use a data fusion from different sensors by a Kalman filter. A supervised artificial network (ANN) is trained to emulate the filter for reducing the computational effort. An automatic best topology for the neural network is obtained by minimizing a functional by a new meta-heuristic called Multi-Particle Collision Algorithm (MPCA). Our results show similar accuracy between the ANN and the Kalman filter, with better processing performance to the neural network.
The authors would like to thank the FAPESP and CNPq, Brazilian agencies for research support.
- [AnEtAl13]Anochi, J. A., Sambatti, S. B., Luz, E. F. P. d., and Campos Velho, H. F. d.: New learning strategy for supervised neural network: Mpca meta-heuristic approach. In Anais…, Congresso Brasileiro de Inteligência Computacional, (CBIC)., Sociedade Brasileira de Inteligência Computacional, 01, pp. 01–06 (2013).Google Scholar
- [BrEtAl15]Braga, J. R. G., Campos Velho, H. F., and Shiguemori, E. H.: Estimation of UAV position using LiDAR images for autonomous navigation over the ocean. In 9th International Conference on Sensing Technology (ICST), pp. 811–816 (2015).Google Scholar
- [BrEtAl16]Braga, J. R. G., Campos Velho, H. F., Conte, G., Doherty, P., and Shiguemori, E. H.: An image matching system for autonomous UAV navigation based on neural network. In 14th International Conference on Control, Automation, Robotics and Vision (ICARCV), pp. 1–6 (2016).Google Scholar
- [CoDo08]Conte, G. and Doherty, P. An integrated UAV navigation system based on aerial image matching. In IEEE Aerospace Conference, pp. 1–10 (2008).Google Scholar
- [SiEtAl15]Silva, W., Shiguemori, E. H., Vijaykumar, N. L., and Campos Velho, H. F.: Estimation of UAV position with use of thermal infrared images. In 9th International Conference on Sensing Technology (ICST), pp. 828–833 (2015).Google Scholar
- [FaEtAl18]Faria, L., Augusto, M. S., Correia, A. F., M., and Roso, N.: Susceptibility of GPS-dependent complex systems to spoofing, In Journal of Aerospace Technology and Management, Sâo José dos Campos - SP (2018), vol. 10.Google Scholar
- [Ha07]Haykin, S.: Neural networks: principles and practical. Artmed (2007).Google Scholar
- [Ma02]Maybeck, P.: Stochastic Models, Estimation, and Control - vol. 1, Academic Press (2002).Google Scholar
- [MiEtAl02]Michaelsen, E., Kirchhof, M., and Stilla, U. Stilla.: Sensor pose inference from airborne videos by decomposing homography estimates. In Accepted for ISPRS (2004).Google Scholar
- [Sa05]Sacco, W.: A new stochastic optimization algorithm based on a particle collision metaheuristic (2005).Google Scholar
- [SaEtAl12a]Sambatti, S. B. M., Anochi, J. A., Luz, E. F. P. d., Carvalho, A. R., Shiguemori, E. H., and Campos Velho, H. F.: Mpca meta-heuristics for automatic architecture optimization of a supervised artificial neural network. In Proceedings…World Congress on Computational Mechanics, 10 (2012).Google Scholar
- [SaEtAl12b]Sambatti, S. B. M., Furtado, H. C. M., Anochi, J. A., Luz, E. F. P. d., and Campos Velho, H. F.: Automatic configuration of an artificial neural network with application to data assimilation. In Proceedings…International Conference on Integral Methods in Science and Engineering, 12 (2012).Google Scholar
- [SaEtAl16]Sambatti, S. B. M., Campos Velho, H. F., Furtado, H. C. M., Gomes, V. C., and Charão, A. S.: Self-configured neural network for data assimilation using FPGA for ocean circulation. Conference of Computational Interdisciplinary Sciences, 4 (2016).Google Scholar