Control basado en reconocimiento facial para un robot diferencial

Ana Fernanda Arriaga Morales; Jesús Santiaguillo-Salinas

Autores/as

Ana Fernanda Arriaga Morales Universidad del Papaloapan https://orcid.org/0009-0006-6264-7995
Jesús Santiaguillo-Salinas Universidad del Papaloapan https://orcid.org/0000-0003-0219-9829

Palabras clave:

Redes Neuronales Convolucionales, Reconocimiento Facial, Robot Móvil Diferencial, Control de Movimiento

Resumen

En este trabajo se presenta el control de un robot móvil diferencial a partir del reconocimiento de un rostro objetivo. Para llevar a cabo el reconocimiento facial, se escogieron tres modelos de redes neuronales convolucionales (CNN's) pertenecientes al framework DeepFace: ArcFace, OpenFace y DeepID. Posteriormente, mediante un análisis comparativo de efectividad, velocidad y costo computacional, se seleccionó el modelo más adecuado para este trabajo. Las coordenadas del centroide del rostro, obtenidas del modelo elegido, son enviadas al robot diferencial para controlar su movimiento. Los resultados son validados experimentalmente utilizando una plataforma conformada por un robot diferencial Lego EV3 y un sistema de posicionamiento local OptiTrack.

Descargas

Los datos de descargas todavía no están disponibles.

Citas

Bhanupriya, M., Kirubakaran, N., y Jegadeeshwari, P. (2023). Emotiontracker: Real-time facial emotion detection with opencv and deepface. En 2023 International Conference on Data Science, Agents Artificial Intelligence (ICDSAAI), pp. 1–4.

Blum, T., Paillet, G., y Masawat, W., Yoshida, K. (2021). Segvisrl: Development of a robot’s neural visuomotor and planning system for lunar exploration. Advanced Robotics, 35(21–22), 1359–1373.

Bonam, J., Burra, L. R., Godavarthi, R. S. V., Jagabattula, D., Eda, S., y Gogulamudi, S. (2022). Multiple Face Recognition System Using OpenFace. En Intelligent Computing and Applications, volumen 315, pp. 339–349. Springer, Singapore.

Cao, M., Zhou, X., y Yunpeng, J. (2023). Robot motion planning based on improved RRT algorithm and RBF neural network sliding. IEEE Access, 11, 121295–121305.

Chang, L., Yuan, H., Wang, T., Mai, T., y Yang, L. (2024). A convex optimization based differentially driven mobile robot planner for crowd navigation. En 2024 IEEE/ASME International Conference on Advanced Intelligent Mechatronics (AIM), pp. 1531–1538.

Firmansyah, A., Fabrianti Kusumasari, T., y Novriza Alam, E. (2023). Comparison of face recognition accuracy of ArcFace, FaceNet and FaceNet512 models on DeepFace framework. En 2023 International Conference on Computer Science, Information Technology and Engineering (ICCoSITE), pp. 535–539.

Fujii, S., Tahara, J., Zhang, F., Koike, M., Ohta, Y., y Watanabe, Y. (2021). Motion control of deep sea vehicle “Ōtohime”: Modeling with neural network. Advanced Robotics, 35(24), 1500–1512.

Herrera-Ollachica, D. A., Asiedu-Asante, B. K., e Imamura, H. (2024). Autonomous UAV implementation for facial recognition and tracking in GPS-denied environments. IEEE Access, 12, 119464–119487.

Htet, A., Bobkov, A. V., y Lin Tun, N. (2021). Face detection in real time live video using YOLO algorithm based on VGG16 convolutional neural network. En 2021 International Conference on Industrial Engineering, Applications and Manufacturing (ICIEAM), pp. 697–702.

Huang, J., Tang, S., Teng, Z., Zhang, Y., y Zhou, X. (2022). Face tracking and recognition in video moving images based on convolutional neural network. Multimedia Tools and Applications, 81, 33771–33784.

Keerthana, P., Sabu, M., Shaji, P., Johnson, T., y George, R. A. (2025). Intelligent campus monitoring and tracking. En 2025 11th International Conference on Smart Computing and Communications (ICSCC), pp. 1–6.

Lee, G. C., Lee, Y., y Chiang, C. (2021). Low-resolution face recognition in multi-person indoor environments using convolutional neural networks. En 2021 International Conference on Computational Science and Computational Intelligence (CSCI), pp. 1629–1633.

Li, X. y Li, M. (2021). The direction analysis on trajectory of fast neural network learning robot. IEEE Access, 9, 125580–125589.

Liang, Y. (2025). Robot trajectory tracking control based on neural networks and sliding mode control. IEEE Access, 13, 96740–96757.

Lopez Pacheco, M. A. (2021). Redes neuronales convolucionales para el modelado de sistemas no lineales con aplicación al monitoreo de daño estructural. Tesis doctoral, CINVESTAV.

Mahmud, S. A., Kamarulariffin, A., Ibrahim, A. M., y Mohideen, A. J. H. (2024). Advancements and challenges in mobile robot navigation: A comprehensive review of algorithms and potential for self-learning approaches. Journal of Intelligent Robotic Systems, pp. 110–120.

Peng, L., Xin, Z., y Ping, G. (2019). Design and implementation of remote DeepFace model face recognition system based on SBRIO FPGA platform and NB-IoT module. En 2019 2nd International Conference on Safety Produce Informatization (IICSPI), pp. 505–509.

Santiaguillo, J. y Aranda, E. (2017). Containment problem with time-varying formation and collision avoidance for multiagent systems. International Journal of Advanced Robotic Systems, 14(3).

Seghiri, S. E., Mansouri, N., y Chemori, A. (2022). Implementation of SARL* algorithm for a differential drive robot in a Gazebo crowded simulation environment. En 2022 2nd International Conference on Advanced Electrical Engineering (ICAEE), pp. 1–6.

Siciliano, B. y Khatib, O., editores (2008). Springer Handbook of Robotics. Springer Berlin, Heidelberg, 1ª edición.

Srisuk, S. y Ongkittikul, S. (2017). Robust face recognition based on weighted DeepFace. En 2017 International Electrical Engineering Congress (iEECON), pp. 1–4.

Turk, M. y Pentland, A. (1991). Face recognition using eigenfaces. En Proceedings of the 1991 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 586–591.

Vyshnavi, M. K., Shaik, S., Kumar, M. S., Praveen, M., y Potti, S. (2024). Facial recognition based attendance system using OpenCV. The Journal of Computational Science and Engineering, 2, 1–10.