Luciana Claudia Martins Ferreira Diogenes1, *
Luciana Claudia Martins Ferreira Diogenes
1 Frutal - MG, Brazil
*Corresponding Author: Luciana Claudia Martins Ferreira Diogenes, Email: [email protected]
This paper explores autonomous robot navigation using two types of sensors: encoders and a pair of cameras. The robot is tasked with navigating through obstacles of varying color intensities to reach a designated goal: a door. The robot's trajectory is determined using a Python-based algorithm that employs sensor fusion through the Kalman Filter to estimate the robot's position accurately. To investigate the feasibility of training a neural network with trajectory data obtained from the Kalman Filter, a separate Python script is developed to assess the accuracy between the estimated positions and those predicted by the neural network. The training results demonstrate that the neural network can be effectively trained, achieving a relatively high level of precision in position estimation. This research underscores the potential of combining sensor fusion and machine learning techniques to enhance the navigation capabilities of autonomous robots in dynamic environments.
Neural networks, Kalman filter, navigation systems, autonomous robots, machine learning
[1] Ma, H., Yan L., Xia, Y. and Fu, M. (2020) Kalman Filtering and Information Fusion. 1st Edition, Springer Singapore, 8. https://doi.org/10.1007/978-981-15-0806-6
[2] Diogenes, L. C. M. F. (2008) Uso de Filtro de Kalman e Visão Computacional para a Correção de Incertezas de Navegação de Robos Autonomos. PhD Thesis, Unicamp, Campinas, Brazil.
[3] Piga, N. A., Pattacini, U. and Natale L. (2021) A Differentiable Extended Kalman Filter for Object Tracking Under Sliding Regime. Frontiers in Robotics and AI, 8, 1-20. https://doi.org/10.3389/frobt.2021.686447
[4] Kim S., Petrunin I., Shin, H-S. (2022) A Review of Kalman Filter with Artificial Intelligence Techniques. Proceedings of the 2022 Integrated Communication, Navigation and Surveillance Conference (ICNS), Dulles, USA, 5-7 April 2022, 1-12. https://doi.org/10.1109/ICNS54818.2022.9771520
[5] Pang Z., Wang Y. and Yang F. (2024) Application of Optimized Kalman Filtering in Target Tracking Based on Improved Gray Wolf Algorithm. Scientific Reports, 14, 8955, 1-9. https://doi.org/10.1038/s41598-024-59610-6
[6] Condados, L. G. P. (2020) Controle Embarcado em Robôs com Acionamento Diferencial e Encoders de Baixa Resolução. Bachelor Thesis, Universidade Federal do Rio Grande do Norte, Natal.
[7] Al Azhima S.A.T., Hakim D. L., Nulfatwa R. I., Hakim N. F.A. and Al Qibtiya M. (2024) Cumulative Error Correction of Inertial Navigation Systems Using LIDAR Sensors and Extended Kalman Filter. Indonesian Journal of Electrical Engineering and Computer Science, 34, 2, May 2024, 878-887. http://doi.org/10.11591/ijeecs.v34.i2.pp878-887
[8] Tout B., Chevrie J., Vermeiren L. and Dequidt A. (2022) Design and Tuning of Extended Kalman Filter for Robotic System Identification, 17th International Conference on Control, Automation, Robotics and Vision (ICARCV), Singapore, 2022, 462-467. https://doi.org/10.1109/ICARCV57592.2022.10004282
[9] Abreu, O. S. L., Costa E. A., Silva T. O., Ribeiro M. P., Schnitman L. and Martins, M. A. F. (2022) Implementação em Tempo Real de um Filtro de Kalman Unscented para Estimação de Variáveis de Difícl Medição em um Poço Piloto Operado por BCS. Sociedade Brasileira de Automática (SBA) XXIV Congresso Brasileiro de Automática - CBA 2022, 3, 16-19 October 2022, 4255 - 4260. https://doi.org/10.20906/CBA2022/3753
[10] Li Q., Li R., Ji K. and Dai W. (2015) Kalman Filter and Its Application. 2015 8th International Conference on Intelligent Networks and Intelligent Systems (ICINIS), Tianjin, China, 2015, 74-77. https://doi.org/10.1109/ICINIS.2015.35
[11] Urrea C. and Agramonte R. (2021) Kalman Filter: Historical Overview and Review of Its Use in Robotics 60 Years after Its Creation, Journal of Sensors, 9674015, 1-21. https://doi.org/10.1155/2021/9674015
[12] Kim J. H., Lee S. H, K., J. G., Jang W. J. and Kim D. H. (2024) Localization of Solar Panel Cleaning Robot Combining Vision Processing and Extended Kalman Filter. Science Progress, 107, 1-29. https://doi.org/10.1177/00368504241250176
[13] Vaz. D. J. F. (2016) Sistema de Navegação para Robot Móvel com Filtros de Kalman. Master Thesis. Academia Militar e Instituto Superior Técnico. Lisboa, Portugal.
[14] Neumann R. (2018) Auto Localização de Robôs Móveis por Fusão de Sensores na Presença de Interferência Eletromagnética. Master Thesis, PUC-Rio, Rio de Janeiro.
[15] Ristic B., Arulampalam S., Gordon N. (2004) Beyond the Kalman Filter. Particle Filters for Tracking Applications, Artech House Publishers. ISBN: 1-58053-631-x.
[16] Gibbs B. P. (2011) Advanced Kalman Filtering, Least-Squares and Modeling. A Practical Handbook-John Wiley & Sons.
[17] Kordic V. (2010) Kalman Filter. InTech, Croatia. https://doi.org/10.5772/233
[18] Martins M. D. L. (2020) Filtragem de Kalman Adaptativa e Robusta para a Reconstrução de Trajetórias. Master Thesis, Universidade da Beira Interior, Portugal.