Localización de robots basada en red neural utilizando características visuales

Contenido principal del artículo

Felipe Trujillo-Romero

Resumen

Este artículo presenta el desarrollo de un módulo que puede desarrollar un algoritmo de construcción de mapas mediante odometría inercial y características visuales. Utiliza un módulo de reconocimiento de objetos basado en características locales y redes neuronales artificiales no supervisadas para conocer elementos no dinámicos en una habitación y asignarles una posición. El mapa está representado por una red neuronal donde cada neurona corresponde a una posición absoluta en la habitación. Una vez construido el mapa, basta con capturar un par de imágenes del entorno para estimar la ubicación del robot. Los experimentos se realizaron mediante simulación y utilizando un robot real. Se utilizó el entorno Webots con el robot humanoide virtual NAO para realizar las simulaciones. Al mismo tiempo, se obtuvieron resultados utilizando un robot NAO real en un escenario con diversos objetos. Los resultados muestran una buena precisión en la localización dentro de los mapas bidimensionales de ±(0,06, 0,1)m en simulación en contraste con el entorno natural; el mejor valor obtenido fue ±(0,25, 0,16)m.

Detalles del artículo

Sección
Artículo Científico

Referencias

IFR. (2024) Homepage. International Federation of Robotics. International Federation of Robotics. [Online]. Available: https://ifr.org/

Y. Omori, T. Furukawa, T. Ishikawa, and M. Inaba, “Humanoid vision design for object detection, localization and mapping in indoor environments,” in 2018 IEEE International Symposium on Safety, Security, and Rescue Robotics (SSRR), 2018, pp. 1–6. [Online]. Available: https://doi.org/10.1109/SSRR.2018.8468604

X. Cui, M. Wang, B. Fan, and J. Yi, “Target detection based on binocular stereo vision,” in 2017 International Conference on Computer Technology, Electronics and Communication (ICCTEC), 2017, pp. 1093–1097. [Online]. Available: https://doi.org/10.1109/ICCTEC.2017.00239

R. Scona, S. Nobili, Y. R. Petillot, and M. Fallon, “Direct visual slam fusing proprioception for a humanoid robot,” in 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017, pp. 1419–1426. [Online]. Available: https://doi.org/10.1109/IROS.2017.8205943

L. K. Garzón Obregón, L. A. Forero Rincón, and O. M. Duque Suárez, “Diseño e implementación de un sistema de visión artificial usando una técnica de mapeo y localización simultánea (SLAM) sobre una plataforma robótica móvil,” Mundo FESC, vol. 8, no. 16, pp. 8–17, 2018. [Online]. Available: https://is.gd/pqjvTy

F. Blochliger, M. Fehr, M. Dymczyk, T. Schneider, and R. Siegwart, “Topomap: Topological mapping and navigation based on visual slam maps,” in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, pp. 3818–3825. [Online]. Available: https://doi.org/10.1109/ICRA.2018.8460641

E. Ovalle-Magallanes, N. G. Aldana-Murillo, J. G. Avina-Cervantes, J. Ruiz-Pinales, J. Cepeda-Negrete, and S. Ledesma, “Transfer learning for humanoid robot appearance-based localization in a visual map,” IEEE Access, vol. 9, pp. 6868–6877, 2021. [Online]. Available: https://doi.org/10.1109/ACCESS.2020.3048936

T. Lasguignes, I. Maroger, M. Fallon, M. Ramezani, L. Marchionni, O. Stasse, N. Mansard, and B. Watier, “Icp localization and walking experiments on a talos humanoid robot,” in 2021 20th International Conference on Advanced Robotics (ICAR), 2021, pp. 800–805. [Online]. Available: https://doi.org/10.1109/ICAR53236.2021.9659474

P. Wozniak, H. Afrisal, R. G. Esparza, and B. Kwolek, “Scene recognition for indoor localization of mobile robots using deep cnn,” in Computer Vision and Graphics, L. J. Chmielewski, R. Kozera, A. Orlowski, K. Wojciechowski, A. M. Bruckstein, and N. Petkov, Eds. Cham: Springer International Publishing, 2018, pp. 137–147. [Online]. Available: https://doi.org/10.1007/978-3-030-00692-1_13

E. S. Lahemer and A. Rad, “An adaptive augmented vision-based ellipsoidal slam for indoor environments,” Sensors, vol. 19, no. 12, 2019. [Online]. Available: https://doi.org/10.3390/s19122795

T.-j. Lee, C.-h. Kim, and D.-i. D. Cho, “A monocular vision sensor-based efficient slam method for indoor service robots,” IEEE Transactions on Industrial Electronics, vol. 66, no. 1, pp. 318–328, 2019. [Online]. Available: https://doi.org/10.1109/TIE.2018.2826471

M. Fourmy, D. Atchuthan, N. Mansard, J. Sola, and T. Flayols, “Absolute humanoid ocalization and mapping based on imu lie group and fiducial markers,” in 2019 IEEE-RAS 19th International Conference on Humanoid Robots (Humanoids), 2019, pp. 237–243. [Online]. Available: https://doi.org/10.1109/Humanoids43949.2019.9035005

S. J. Dignadice, J. R. Red, A. J. Bautista, A. Perol, A. Ollanda, and R. Santos, “Application of simultaneous localization and mapping in the development of an autonomous robot,” in 2022 8th International Conference on Control, Automation and Robotics (ICCAR), 2022, pp. 77–80. [Online]. Available: https://doi.org/10.1109/ICCAR55106.2022.9782658

S. Wen, M. Sheng, C. Ma, Z. Li, H. K. Lam, Y. Zhao, and J. Ma, “Camera recognition and laser detection based on ekf-slam in the autonomous navigation of humanoid robot,” Journal of Intelligent & Robotic Systems, vol. 92, no. 2, pp. 265–277, Oct 2018. [Online]. Available: https://doi.org/10.1007/s10846-017-0712-5

X. Deng, Z. Zhang, A. Sintov, J. Huang, and T. Bretl, “Feature-constrained active visual slam for mobile robot navigation,” in 2018 IEEE International Conference on Robotics and Automation (ICRA), 2018, pp. 7233–7238. [Online]. Available: https://doi.org/10.1109/ICRA.2018.8460721

A. Li, J. Wang, M. Xu, and Z. Chen, “DP-SLAM: A visual SLAM with moving probability towards dynamic environments,” Information Sciences, vol. 556, pp. 128–142, 2021. [Online]. Available: https://doi.org/10.1016/j.ins.2020.12.019

N. Krombach, D. Droeschel, S. Houben, and S. Behnke, “Feature-based visual odometry prior for real-time semi-dense stereo slam,” Robotics and Autonomous Systems, vol. 109, pp. 38–58, 2018. [Online]. Available: https://doi.org/10.1016/j.robot.2018.08.002

Y. S. Jiyu Cheng and M. Q.-H. Meng, “Improving monocular visual slam in dynamic environments: an optical-flow-based approach,” Advanced Robotics, vol. 33, no. 12, pp. 576–589, 2019. [Online]. Available: https://doi.org/10.1080/01691864.2019.1610060

S. Ganesan and S. K. Natarajan, “A novel directional sampling-based path planning algorithm for ambient intelligence navigation scheme in autonomous mobile robots,” Journal of Ambient Intelligence and Smart Environments, vol. 15, pp. 269–284, 2023, 3. [Online]. Available: https://doi.org/10.3233/AIS-220292

K. Zhang, H. Gui, Z. Luo, and D. Li, “Matching for navigation map building for automated guided robot based on laser navigation without a reflector,” Industrial Robot: the international journal of robotics research and application, vol. 46, no. 1, pp. 17–30, Jan 2019. [Online]. Available: https://doi.org/10.1108/IR-05-2018-0096

C. Wang, J. Wang, C. Li, D. Ho, J. Cheng, T. Yan, L. Meng, and M. Q.-H. Meng, “Safe and robust mobile robot navigation in uneven indoor environments,” Sensors, vol. 19, no. 13, 2019. [Online]. Available: https://doi.org/10.3390/s19132993

A. Roychoudhury, M. Missura, and M. Bennewitz, “3d polygonal mapping for humanoid robot navigation,” in 2022 IEEE-RAS 21st International Conference on Humanoid Robots (Humanoids), 2022, pp. 171–177. [Online]. Available: https://doi.org/10.1109/Humanoids53995.2022.10000101

F. Martín, J. Ginés, D. Vargas, F. J. Rodríguez-Lera, and V. Matellán, “Planning topological navigation for complex indoor environments,” in 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018, pp. 1–9. [Online]. Available: https://doi.org/10.1109/IROS.2018.8594038

Aldebaran. Nao documentation. Aldebaran NAO Documentation. Aldebaran NAO Documentation. [Online]. Available: https://is.gd/eSNPWH

MIA. (2023) Mathematical image analysis group. MIA Group. MIA Group. [Online]. Available:

https://is.gd/69mEso

P. Fernández Alcantarilla, “Fast explicit diffusion for accelerated features in nonlinear scale spaces,” in British Machine Vision Conference (BMVC), 09 2013. [Online]. Available: http://dx.doi.org/10.5244/C.27.13

H. Scharr, Optimale Operatoren in der Digitalen Bildverarbeitung. University of Heidelberg,

Germany, 2000. [Online]. Available: https://doi.org/10.11588/heidok.00000962

X. Yang and K. Cheng, “Ldb: An ultrafast feature for scalable augmented reality on mobile devices,” 2012 IEEE International Symposium on Mixed and Augmented Reality (ISMAR), pp. 49–57, 2012. [Online]. Available: https://doi.org/10.1109/ISMAR.2012.6402537

B. Fritzke, “Growing cell structures—a selforganizing network for unsupervised and supervised learning,” Neural Networks, vol. 7, no. 9, pp. 1441–1460, 1994. [Online]. Available: https://doi.org/10.1016/0893-6080(94)90091-4

T. Kohonen, “The self-organizing map,” Proceedings of the IEEE, vol. 78, no. 9, pp. 1464–1480, 1990. [Online]. Available: https://doi.org/10.1109/5.58325

Cyberbotics. (2023) Simulating your robots with webots. Cyberbotics - Robotics simulation services. Cyberbotics - Robotics simulation services. [Online]. Available: https://is.gd/Q31yau

K. L. Flores-Rodríguez, F. Trujillo-Romero, and W. Suleiman, “Object recognition modular system implementation in a service robotics context,” in 2017 International Conference on Electronics, Communications and Computers (CONIELECOMP), 2017, pp. 1–6. [Online]. Available:

https://doi.org/10.1109/CONIELECOMP.2017.7891833